PATIENT-CENTRED LABORATORY VALIDATION USING SOFTWARE AGENTS

John McGrory, Frank Clarke, Jane Grimson and Peter Gaffney

Guidelines are self-contained documents which healthcare professionals reference to obtain specific disease or medical condition knowledge for a particular population cohort. They interface with these documents and apply known facts about specific patients to gain useful supportive information to aid in developing a diagnosis or manage a condition. Traditional CIG models decompose these guidelines into workflow plans, which are then called using certain motivational condition triggers controlled by a centralised management engine. Therefore CIG guidelines are not self-contained documents, which specialise in a specific condition or disease, but are effectively a list of sub-recipes (workflow plans), which are called and used when the ingredients (patient information) are available. The software BDI agent offers an alternative dynamic which more closely matches the modus operandi of narrative based medical guidelines. An agent’s beliefs capture information attributes, plans capture the deliberative and action attributes, and desire captures the motivational attributes of the guideline in a self-contained autonomous software module. Agents acting on behalf of guidelines which overlap and interweave in similar domains can collaborate and coordinate in a loosely coupled fashion without the need for an all encompassing centralised plan.

COMMUNICATION OF MEDICAL INFORMATION USING AGENTS

John McGrory, Frank Clarke, Jane Grimson and Peter Gaffney

Agents are self-contained software entities which act faithfully and autonomously on behalf of a body of knowledge. They can operate in a standalone capacity, or as part of a social group collaborating and coordinating activities with other software agents. To access their knowledge, agents are interfaced with using message passing communication. The principle behind medical communications is to provide a means for exchanging information and knowledge from one computerised location to another, whilst preserving its true meaning and understanding between the listener and sender. Agent communication is similar to medical communications, but must provide an additional framework element to allow agents to interact at a social and operational level. Social aspects relate to agents collaborating on shared objectives, and operational aspects relate to coordination of tasks between the loosely coupled agents working as part of a group. Medical communications focus on data exchanges specific to the medical domain, while agent communication was designed for a much broader audience. Therefore, it is essential to verify if agent communications can support standard medical data exchanges. This paper investigates current forms of agent based communications and demonstrates they can support medical communication, yet retain their social and interaction information exchange functionality.

SOFTWARE AGENTS REPRESENTING MEDICAL GUIDELINES

John McGrory, Frank Clarke, Jane Grimson and Peter Gaffney

Guidelines are self-contained documents which healthcare professionals reference to obtain specific disease or medical condition knowledge for a particular population cohort. They view these documents and apply known facts about their patients to access useful supportive information to aid in developing a diagnosis or manage a condition. Traditional CIG models decompose these guidelines into workflow plans, which are then called using certain motivational trigger conditions controlled by a centralised management engine. Therefore CIG guidelines are not self-contained documents, which specialise in a particular condition or disease, but are effectively a list of sub-recipes (workflow plans), which are called and used when the ingredients (patient information) are available. The software BDI agent offers an alternative approach which more closely matches the modus operandi of narrative based medical guidelines. An agent’s beliefs capture information attributes, plans capture the deliberative and action attributes, and desire captures the motivational attributes of the guideline in a self-contained autonomous software module. This synergy between the narrative guideline and the BDI agent offers an improved solution for computerising medical guidelines when compared to the CIG approach.

PRE-DIABETES - An Informatics Research Agenda

Barbara Hayes and William Aspray

The paper sets out a research agenda for practitioners of the relatively new, interdisciplinary field of informatics who wish to improve the health experience for people who have susceptibility to diabetes – a condition known as pre-diabetes. Using information technology tools and methods, but with sensitivity to the social and organizational complexities of the health care system, the article suggests addressing a set of problems that will improve the lives of patients and their friends and families, as well as making the provision of pre-diabetes care more effective and cost-efficient. Topics include public health and community informatics, knowledge dissemination, information alerts, decision support, clinical guidelines, health literacy, patient, pharmacy, and laboratory feedback systems, interface design, reminder systems, consumer informatics, and privacy and security issues.

COMPARISON OF THREE NEURAL NETWORK CLASSIFIERS FOR APHASIC AND NON-APHASIC NAMING DATA

Antti Järvelin

This paper reports a comparison of three neural network models (Multi-Layer Perceptrons, Probabilistic Neural Networks, Self-Organizing Maps) for classifying naming data of aphasic and non-aphasic speakers. The neural network classifiers were tested with the artificial naming data generated from confrontation naming data of 23 aphasic patient and one averaged control subjet. The results show that one node MLP neural network performs best in the classification task, while the two other classifiers performed typically 1-2 % worse than the MLP classifier. Although the differences between the different classifier types are small, these results suggests that a simple one node MLP classifier should be preferred over more complex neural network classifiers when classifying naming data of aphasic and non-aphasic speakers.

TRUSTED SMS - A Novel Framework for Non-repudiable SMS-based Processes

Antonio Grillo, Alessandro Lentini, Gianlugi Me and Giuliano Rulli

The exponential growth of the Short Message Service (SMS) use has led this service to an indispensable tool for social, marketing and advertising messaging. Moreover, mobile devices such as smartphones, handsets and PDAs represent an enabling factor for distributing digital content. Mobile devices are quickly becoming Personal Trust Device (PDT); mobile devices embed personal data, which allow sending/receiving confidential information from/to the PTD. This paper aims to introduce Trusted-SMS, a novel framework to exchange secure SMS. This system is composed by three main entities: the Service Supplier, which publishes and delivers services; the Final User, which choices and eventually pays for a specific service, that belongs to the service-set offered by a Service Supplier; the Trusted Service Provider(TSP) which rapresents the trusted entity that is shared by the Service Supplier and the Final User. The TSP play the role of the Certification Authority. The main requirements of the overall system are strictly security, user friendliness and platform portability. The security requirement includes customer transaction authentication, confidentiality, integrity and non repudiation, in an enviroment composed of heterogeneous networks and devices, with different security weaknesses. Trusted-SMS allows to exchange SMS digitally signed with Elliptic Curve Digital Signature Algorithm between two entities. The SMS digitally signed can be utilized in many scenarios, such as commercial transaction, production of delegation from a remote site and realization of e-healthcare services. The signature is fully contained in a single SMS; the size of a digital signature amount to fifty bytes leaving more than one hundred bytes (110 bytes) for the SMS payload. Moreover the application of Elliptic Curve Integrated Encryption Schema cryptographic algorithm, which is based on the same credentials needed by the digital signature algorithm, allows to protect the payload from intrusions.

INTELLIGENT SYSTEM FOR ASSISTING ELDERLY PEOPLE AT HOME

Juan Pascual, Miguel A. Sanz-Bobi and David Contreras

Nowadays the number of elderly people in our society is increasing thanks to continuous and important advances related to health care. The ideal situation for these elderly people is to spend as much time as possible enjoying their life within their family and social environment, without the need to abandon their home to go live in specialized centres as long as their physical health permits. In many cases, simply because there do not exist sufficient means or vigilance time by a caretaker in their home, these people are forced to leave their homes to go live in specialized centres such as nursing homes. This paper describes a multi-agent architecture in which the main objective is to extend the amount of time as much as possible that these elderly people can reside in their own homes by means of providing continuous vigilance for certain parameters concerning daily activities which possibly could be risky, by facilitating reminders to complete specific tasks, by easing communication with the exterior world, and in the case that it is necessary, by automatically calling for emergency services. This multi-agent system is based on intelligent agents capable of integrating pro-active assistant services to elderly people in their own homes by detecting possible risk situations by using different kinds of sensors and intelligent processing of their information.

SEGMENTATION AND CLASSIFICATION OF CUTANEOUS ULCERS IN DIGITAL IMAGES THROUGH ARTIFICIAL NEURAL NETWORKS

André de Souza Tarallo, Adilson Gonzaga and Marco Andrey Cipriano Frade

Treatments of leg ulcers are generally expensive and those conducted through the direct manipulation for analysis of its evolution. The treatment efficiency is observed through the reduction of the size of ulcers in relation to the amount of tissues found in their beds, which are classified as granulated/slough. These results are obtained through analyses performed after consultation due to the time these analyses take. This work proposes a new non-invasive technique for the follow-up of treatments aimed at cutaneous ulcers. In this methodology, it was proposed that digital photos of cutaneous ulcers would be submitted to an artificial neural network (ANN), so that all surrounding the wound except for the wound itself could be extracted (skin/background), thus obtaining the ulcerated area. Computer vision techniques have been applied in order to classify the different types of tissues found in the ulcer bed, thus obtaining the corresponding granulation and slough percentages as well as its area. The results obtained have been compared with the results obtained by Image J software. Finally, this methodology will be a useful tool for health professionals in relation to the quickness and precision that it will provide results along the consultation.

ASSISTING WELLBEING - The Challenges of Using Technology to Improve Wellbeing in Older Adults

Douglas Millward and Wendy Nicholls

Telecare is an increasingly important application of technology that is designed to increase the independence of older adults, amongst other goals. The programme of research described below aims to identify important issues with the deployment of this technology to the target group. It describes an on-going programme of research that attempts to classify these issues, and posit solutions. It additionally proposes a new area of research into the effects of telecare and related technologies on a client’s psychosocial wellbeing.

ECGAWARE: AN ECG MARKUP LANGUAGE FOR AMBULATORY

Bernardo Gonçalves, José G. Pereira Filho and Rodrigo V. Andreão

By taking advantage of information and communication technologies (ICT), telecardiology has found in the transmission of electrocardiogram (ECG) an economic and efficient way of rendering remote medical services. Moreover, jointly with mobile and wireless technologies and devices currently available, ambulatory ECG makes possible real-time telemonitoring anytime and anywhere. In this trend, context-aware platforms integrating ECG analysis systems provide efficient emergency services and support physician’s decision making. With this in mind, this paper presents an ECG markup language that extends existing ECG data standards, specially incorporating contextual aspects of an ECG recording session, and proposes it in a real scenario of patient’s heart telemonitoring.

CLINICAL PRACTICAL GUIDELINE EDITOR - Clinical Practical Guideline-based Decision Support Tool

Aleš Plavčak

According to the quick growth of information and the complexity of medicine, the development of informatics in medicine is in full bloom. Medical decision support systems have been developed to help choose the appropriate medical treatment procedures, ensure the quality of health care and enable the control of medical resources. Clinical Practical Guidelines have greatly contributed to the accelerated development. Many different modelling methods and tools have been developed for executing guidelines. Here, the three of many applicable guideline modelling techniques are represented in greater scope. Also, a new technique of representing the clinical knowledge has been designed, taken from the studies of already existing models. The implementation of the application for editing, browsing and executing clinical guidelines has been implemented as well. The application is capable of generating recommendations for a specific clinical state and evaluation of the already existing health care process. This paper covers the general presentation of informatics in medicine and the techniques for modelling of medical knowledge which nowadays represents a gateway for prosperous development, and pave the way for broader use and implementation.

A BPM-BASED MOBILE U-HEALTH SERVICE FRAMEWORK

Dongsoo Han, In-Young Ko, Sungjoon Park, Minkyu Lee and Suntae Jung

With the wide spread use of cellular phones and the increased interests in the well-being of people, many vendors of cellular phones start to embed a variety of u-health services in their cellular phones. While the u-health services look different from the service point of view, they share many common features at various levels such as the service structure, unit service, and data levels. Thus, it is necessary to have a common platform on which various u-health services can be developed by effectively sharing and reusing the common features and services rather than developing the services independently from scratch. In this paper, we propose such a u-health platform that provides core functions and tools to develop u-health services. Main elements of the platform include the u-health ontology and common data structures, and the BPM (Business Process Management) based service integration framework. The platform allows common features and services be registered and reused in the course of developing u-health services. According to the early evaluation, our platform demonstrated strength in terms of service flexibility, accessibility, evolvability, reusability, adaptability, interoperability and guideline provision for developing u-health services .

INTEGRATION SOLUTION FOR THE ACCESS TO HETEROGENEOUS MEDICAL DEVICES - Communication with Healthcare Devices in Intensive Care Units

Susana Martin-Toral, Jose Luis Rodriguez-Gonzalez and Javier Perez-Turiel

This paper presents a free Critical Care Information System (CCIS) that shows an essential infrastructure for critical care medical and nursing practice. Concretely, a Patient Integral Analysis Aid System (SAIP) in Intensive Care Units (ICU) has been developed to cover the needs discovered in these scenarios. An importart part of this system is the one related to medical equipment, that offers important information to help in medical diagnosis. ICU patients are usually connected to several of these devices and they allow to get their physiological parameters. The integration of these devices, in order to exchange the generated information, is difficult because they are developed by different manufacturers and with different communication protocols and information representations. Due to this, it has been necessary to develop a set of communication drivers for each medical device, according to the existent normative. To reach this objective, the drivers developed have a common interface for the access and the collection of medical device data. The main goal of the present paper is to show the work done to obtain a real interoperability among medical devices from different manufacturers and with different communication protocols in ICU services for automatic data collection, storage and retrieval.

MEDICAL IMAGE UNDERSTANDING THROUGH THE INTEGRATION OF CROSS-MODAL OBJECT RECOGNITION WITH FORMAL DOMAIN KNOWLEDGE

Manuel Möller, Michael Sintek, Paul Buitelaar, Saikat Mukherjee, Xiang Sean Zhou and Jörg Freund

Rapid advances in medical imaging scanner technology have increased dramatically in the last decade the amount of medical image data generated every day. By contrast, the software technology that would allow the efficient exploitation of the highly informational content of medical images has evolved much slower. Despite the research outcomes in image understanding and semantic modeling, current image databases are still indexed by keywords assigned by humans and not by the image content. The reason for this slow progress is the lack of scalable and generic information representations capable of overcoming the high-dimensional nature of image data. Indeed, most of the current content-based image search applications are focused on the indexing of certain image features that do not generalize well and use inflexible queries. We propose a system combining medical imaging information with semantic background knowledge from formalized ontologies, that provides a basis for building universal knowledge repositories, giving clinicians a fully cross-lingual and cross-modal access to biomedical information of all forms.

STAINING PATTERN CLASSIFICATION IN ANTINUCLEAR AUTOANTIBODIES TESTING

Paolo Soda and Giulio Iannello

In Indirect Immunofluorescence (IIF) the use of Computer-Aided Diagnosis (CAD) tools can support physicians' estimation of both fluorescence intensity and staining pattern. This paper reports our experiences in the staining pattern recognition of IIF wells. Since several cells constitute each well, we have developed a Multiple Expert System (MES) based on the one-per-class approach devised to classify the pattern of individual cells. As a novelty, we introduce an aggregation rule based on the estimation of the reliability of each composing experts. Then, the whole well staining pattern is computed using the reliability of its cells classification. The approach has been successfully tested on an annotated set of IIF images.

HOW TO EVALUATE HUMAN FACTORS AFFECTING WIRELESS BIOMEDICAL SENSORS - Identifying Aspects of Patient Acceptance based on a Preliminary Clinical Trial

Rune Fensli and Egil Boisen

In this paper, we highlight some important aspects of how to evaluate patient acceptance with wearable sensors recording vital signs information, used in a telehomecare environment. Questions of human factors and patient satisfaction need to be addressed, where the patient is able to carry out daily life activities in his own environment. We compare results from a preliminary clinical trial with patients using a wireless ECG sensor for three days out-of-hospital service, to available published results from telehomecare projects, and propose important aspects and plans for future investigations. It is important not only to observe the patient, but also the possible changes in the family situation when a sick patient is transferred to his own home for active treatment. At the same time, emotional barriers and stigmatisation is a challenging factor where time is needed to let the patient adopt this new situation. Therefore, measures should be on an on-going basis with long-time use of the technological equipment in order for the patient to integrate this into his body scheme as well as daily activities. Of special importance will be the evaluation of the communication between the patient and the health professionals, as quick feedback from the doctor to the patient on his or her own measurements is of outmost importance.

INTERACTION OF TECHNOLOGICAL AND INSTITUTIONAL CHANGE IN THE DEVELOPMENT OF AN ELECTRONIC COMMERCE SYSTEM IN CHINA’S PHARMACEUTICAL DISTRIBUTION CHAIN - A Transaction Cost Perspective

Kai Reimers and Mingzhi Li

In this paper, we describe the introduction of electronic commerce into the drug distribution industry in China. This case is especially interesting because massive institutional changes coincide with the introduction of a new technology. For these reasons, it becomes possible to study the interaction of technological and institutional change in real time and in their real-life context. We use two alternative transaction cost-theoretic perspectives on the interaction between institutional and technological change as our theoretical framework. The case study suggests that the rationale which motivates introduction of a new technology in the context of institutional change may be different from the rationale which underlies the practices which develop on the basis on the newly introduced systems and institutions.

CLINICAL AND TRANLATIONAL SCIENCE INFORMATICS INFRASTRUCTURE - A Framework and Case Study

Arkalgud Ramaprasad, Annette L. Valenta and Ian Brooks

This paper presents a comprehensive socio-technical framework for the design and development of a Clinical and Translational Science Informatics Infrastructure (CTSII). The framework is being used by the authors at their institution. Based on our experience with developing and applying the framework we present a case study to illustrate the issues that arise in the creating a CTSII, and how possibly these issues can be resolved. The framework is presented as a ‘Chinese Menu’ with six columns, each column representing a dimension of the framework. The six dimensions represent: (a) the different types of integration central to translation, (b) the different areas of research that have to be translated, (c) the resources available for translation, (d) the diseases that form the focal point of translational research, (e) the methodological steps in any research (including translation research), and (f) the tools for translation. The categories within each dimension can be concatenated, with the conjunctive phrases/words between the columns, to form sentences that describe all the functions of the CTSII. Elucidation of all the combinations will provide an exhaustive list of all the possible functions of CTSII. The combinations can be prioritized intuitively or using various methods of evaluating alternatives.

USING WEB SERVICES TO DYNAMICALLY EMBED MEDICAL CONTENT IN A CLINICAL INFORMATION SYSTEM

Martin Luethi

This paper describes a software application that makes use of Web services to retrieve medical content from an external Application Service Provider (ASP) service. The retrieved data is used to dynamically generate user interface components within a user-customizable department information system and to obtain results for medical decision-making. Medical forms are frequently built and rearranged by medical system admin-istrators. From the perspective of clinical end users the content is seamlessly integrated and allows querying of dosages, interactions, and formulations using collected parameters such as age, weight, and physiological data. Whereas the use of standalone personal digital assistant (PDA) devices provides measurable benefits to clinicians, the feasibility of a seamless integration with user-customizable information systems has not been researched well. This paper describes an approach that was taken to integrate such medical calculators into an existing clinical information system that is based on Web technology.

A GENERIC SOLUTION FOR THE CONSTRUCTION OF DIAGNOSTIC EXPERT SYSTEMS BASED ON PRODUCT LINES

Ma Eugenia Cabello Espinosa and Isidro Ramos Salavert

This paper presents a generic solution for the construction of diagnostic expert systems using aspect-oriented-software architectures and product line techniques. The approach is shown by specifying a case study using Computaion Independent Models (CIMs)) and automatically generating a Platform Independent Model (PIM). The case study presented is a medical diagnosis system for the detection of infantile infectious diseases. PRISMA models are used as Platform Independent Models (PIMs). We follow the Model Driven Architecture (MDA) initiative of the Object Management Group (OMG) for building domain models (CIMs), which are automatically transformed into PIMs and are then compiled to a .NET executable application. The Software Product Line techniques have been used to capture the variability of systems of this kind

AN ONTOLOGY-BASED INFORMATION SYSTEM FOR MULTICENTER EPIDEMIOLOGIC STUDIES ON CANCER

J. M. Vázquez, M. Martínez, M. G. López, B. González-Conde, F. M. Arnal, J. Pereira and A. Pazos

Cancer is caused by a variety factors whose study requires a large amount of data. Compiling these data is an expensive and time-consuming task which can be carried out in an easy, quick, safe and effective way with the support of Information and Communication Technologies (ICT). However, most epidemiologic studies take place without this support of informatics or with basic tools that are developed by unqualified professionals. As a consequence, the integrity of the compiled data cannot be guaranteed, and the reliability of the studies is affected. This work presents an Information System for the development of multicenter epidemiologic studies which has been successfully applied in the execution of an epidemiologic study of colorectal cancer in Galicia, Spain.

SMART TRANSPLANTATION - Fever of Unknown Origin after Stem Cell Transplantation as a Model for a Knowledge-Based Decision Support System in Medicine

Gerrit Meixner, Nancy Thiels, Ingo Haschler, Andreas Wicht and Ulrike Klein

Public health care has to make use of the potentials of IT to meet the enormous demands on patient management in the future. Embedding artificial intelligence in medicine may lead to an increase in health care quality and patient safety. One possibility in this respect is the use of knowledge-based decision support systems which facilitate the practice of evidence-based medicine. Conditions for such a system are structured data sources to extract relevant data for the proposed decision. Therefore, the demonstrator "allotool" was designed. To develop the allo-tool a user-orientated process was applied and future users of the later software were integrated in each step of the development process. The concept of introducing a "Medical decision support system based on the model of Stem Cell Transplantation" was developed afterwards. The objectives are (1) to improve patient safety (2) to support patient autonomy and (3) to optimize the work flow of medical personnel.

TELEHEMATOLOGY - ICT Solution of a Shared Digital Image Repository

Daniel Schwarz, Miroslav Penka, Ladislav Dusek and Petr Brabec

Telehematology, the educational program at the Faculty of Medicine of Masaryk University, presents formation and utilization of a web image archive and connected telehematology workstations. The archive includes a clinical part as well as an educational part. It allows physicians to remotely consult indefinite findings with the use of a shared image repository. In the educational part, it is available for contact tuition as well as for effective distant learning in a wide range of medical specialties.

EXPLOITING SERVICE ORIENTED ARCHITECTURES FOR THE DESIGN OF E-HEALTH SYSTEMS

Marcos Da Silveira and Nicolas Guelfi

The design of e-Health systems is a hard task since their requirements are complex and heterogeneous. These systems merge functional requirements with an important set of non–functional requirement like security, safety, standardization or technology related constraints concerning the hardware and software components to be used. The ICT research community has proposed recently architectural models for the development of open and dynamic distributed systems centered on the concept of “service”. This approach has been followed by all the major actors of ICT for their frameworks due to its adaptation to the World-Wide-Web. This paper is a position paper where we analyze the current status and needs for e-Health systems and the limitation upon them. We present the main characteristics of middlewares that follow a service-oriented architecture and we explain how these frameworks could be exploited, as a vision to the future, to design e-health systems for a better insurance of their functional and non-functional requirements.

A SURVEY OF INTEROPERABILITY IN E-HEALTH SYSTEMS - The European Approach

Marcos Da Silveira, Nicolas Guelfi, Jerry-David Baldacchino, Pierre Plumer, Marc Seil and Anke Wienecke

The interoperability is often associated with the capacity of exchanging information that belongs to different workflows in a distributed environment. In e-health, the implementation of interoperable systems has a direct consequence on the access of medical services, the costs and the quality of those services. The current state of the e-health systems often do not integrate readily with the rest of a clinical organization’s information infrastructure. Also, the nature of many current e-health system designs makes it difficult to extend them with additional clinical capabilities. This paper summarizes the efforts of standardization of communication technologies and information exchange into the healthcare domain. The assessment of this standardization effort is made through a study of its relation with FP5 and FP6 European projects that address the healthcare domain.

PROCESS AND E-SERVICE CUSTOMIZATION - For Coordination in Healthcare Networks

Günter Schicker, Carolin Kaiser and Freimut Bodendorf

Coordination in healthcare networks becomes increasingly important. A process-oriented coordination approach is introduced which enhances integrated care scenarios by IT-driven coordination of interorganizational treatment processes – the concept of process-based e-service logistics. The allocation of e-services is based on a model describing services and coordination tasks between roles in a healthcare network. The underlying system’s architecture is presented which implements process-based e-service logistics by designing and executing individual treatment processes, identifying coordination tasks between network actors, and dynamically allocating e-services. A solution for automated individualization of processes and e-services based on Case Based Reasoning (CBR) technology is discussed.

INTRODUCING A MOBILE SYSTEM FOR THE EARLY DETECTION OF CARDIAC DISORDERS AS A PRECAUTION FROM A CARDIOLOGISTS’ VIEW - Evaluation of a Survey

Onur von Burg, Marco Savini, Henrik Stormer and Andreas Meier

This paper illustrates the results of a survey of practicing cardiologists that were asked about various aspects of a simplified telecardiology scenario using mobile devices. Such devices are becoming ubiquitous assets in everybody’s life. Their application in a healthcare environment aims not only at supporting the patients over traditional consultations but also maximizes the content of their health status information. The results of the survey may help application developers to focus their efforts of applications in a similar setting.

ARTIFICIAL NEURAL NETWORKS FOR DIAGNOSES OF DYSFUNCTIONS IN UROLOGY

David Gil Mendez, Magnus Johnsson, Antonio Soriano Paya and Daniel Ruiz Fernandez

In this article we evaluate the work out of artificial neural networks as tools for helping and support in the medical diagnosis. In particular we compare the usability of one supervised and two unsupervised neural network architectures for medical diagnoses of lower urinary tract dysfunctions. The purpose is to develop a system that aid urologists in obtaining diagnoses, which will yield improved diagnostic accuracy and lower medical treatment costs. The clinical study has been carried out using the medical registers of patients with dysfunctions in the lower urinary tract. The current system is able to distinguish and classify dysfunctions as areflexia, hyperreflexia, obstruction of the lower urinary tract and patients free from dysfunction.

ON PSEUDONYMOUS HEALTH REGISTERS - While They Work As Intended, They Are Still Controversial in Norway

Herbjørn Andresen

Patient health data has a valuable potential for secondary use, such as decision support on a national level, reimbursement settlements, and research on public health or on the effect of various treatment methods. Unfortunately, extensive secondary use of data is very likely to have disproportionate negative impact on the patients’ privacy. Traditionally, privacy regulations require a balancing process; the use of data should be minimized and kept within a level where proportionate privacy is maintained. An alternative strategy is to use technological remedies to enhance privacy protection. Norwegian health data processing regulation prescribes four different ways of organising health registers (anonymous, de identified, pseudonymous or identified data subjects). Pseudonymity is the most innovative of these methods, and it has been available as a legitimate means to achieve extensive secondary use of accurate and detailed data since 2001. Up to now, two national health registers have been organised this way. The evidence from these experiences should be encouraging: Pseudonymity works as intended. Yet, there is still discernible reluctance against extending the pseudonymity principle to encompass other national health registers as well.

PROCESS MINING IN HEALTHCARE - A Case Study

R. S. Mans, M. H. Schonenberg, M. Song, W. M. P. van der Aalst and P. J. M. Bakker

To gain competitive advantage, hospitals try to streamline their processes. In order to do so, it is essential to have an accurate view of the ``careflows" under consideration. In this paper, we apply process mining techniques to obtain meaningful knowledge about these flows, e.g., to discover typical paths followed by particular groups of patients. This is a non-trivial task given the dynamic nature of healthcare processes. The paper demonstrates the applicability of process mining using a real case of a gynecological oncology process in a Dutch hospital. Using a variety of process mining techniques, we analyzed the healthcare process from three different perspectives: (1) the control flow perspective, (2) the organizational perspective and (3) the performance perspective. In order to do so we extracted relevant event logs from the hospital’s information system and analyzed these logs using the ProM framework. The results show that process mining can be used to provide new insights that facilitate the improvement of existing careflows.

INTEROPERABILITY IN SMART HOME MIDDLEWARE - The MPOWER Project

Sten Hanke and Thomas Fuxreiter

The paper describes the use of interoperability standards and interoperability frameworks in a smart / sensor home project. During the EU funded project MPOWER an open middleware platform will be developed which should speed up the task of developing and deploying services for persons with cognitive disabilities and elderly. The developed middleware has different interfaces where interoperability standards are required. The paper points out these requirements and presents solutions in the different layers of the Service-Oriented Architecture approach. In future, standards and defined interfaces are more and more needed because of the need for a secure and easy data and messaging transfer. The middleware will be developed non-proprietary and is open for different applications and sensor integration.

WHO SHOULD ACCESS ELECTRONIC PATIENT RECORDS

A. Ferreira, L. Antunes, C. Pinho, C. Sá, E. Mendes, E. Santos, F. Silva, F. Sousa, F. Gomes, F. Abreu, F. Mota, F. Aguiar, F. Faria, F. Macedo, S. Martins and R. Cruz-Correia

Access control to Electronic Patient Records (EPR) may greatly depend on users’ objectives and needs. The purpose of this study is to assess the opinions of medical doctors within a university hospital towards access control to an EPR. We selected a randomized sample of 58 doctors from a university hospital and 45 structured interviews were applied. 42 respondents (93%) agree with the existence of access control levels to patient information according to healthcare professionals’ category and 31 (69%) think that more sensitive information (e.g. HIV) should be accessed only by doctors that treat those patients. As 24 doctors (53%) feel that there is no need for them to see all information about all the patients, 41 (91%) think that nurses should not be able to do it also. Further, 31 doctors (69%) believe that patients themselves should not access their full medical record. These results show that it is very hard to get to a consensual policy regarding access control to EPR by its regular users. There is therefore the need for a multidisciplinary agreement that should include healthcare professionals’ experiences and needs in order to define the most appropriate and efficient way to perform access control to the EPR.

AUTOMATIC BREAST CONTOUR DETECTION IN DIGITAL PHOTOGRAPHS

Jaime S. Cardoso, Luis F. Teixeira and Maria J. Cardoso

Breast cancer conservative treatment (BCCT), due to its proven oncological safety, is considered, when feasible, the gold standard of breast cancer treatment. However, aesthetic results are heterogeneous and difficult to evaluate in a standardized way, due to the lack of reproducibility of the subjective methods usually applied. The objective assessment methods, considered in the past as being less capable of evaluating all aspects of BCCT, are nowadays being preferred to overcome the drawbacks of the subjective evaluation. A recent computer-aided medical system was developed to objectively and automatically evaluate the aesthetic result of BCCT. In this system, the detection of the breast contour on the digital photograph of the patient is a necessary step to extract the features subsequently used in the evaluation process. In this paper an algorithm based on the shortest path on a graph is proposed to detect automatically the breast contour. The proposed method extends an existing semi-automatic algorithm for the same purpose. A comprehensive comparison with manually-drawn contours reveals the strength of the proposed method.

REQUIREMENTS ENGINEERING TO AUDIT PRIVACY ISSUES IN MEDICAL AND HEALTH SOFTWARE

Miguel A. Martinez, Ambrosio Toval and Manuel Campos

In recent years, there has been a growing interest to guarantee that health organizations make a suitable treatment and protection of the personal data with which they deal in their daily activity. The privacy of personal data is regulated by law in many countries and is considered an important issue in a number of Quality Standards. This paper presents a systematic method to make an audit of the privacy in health sector software based on Requirements Engineering (RE). The aplication and validation of the method is ilustrated in a operative tool of report and clinical record management in the Intensive Care Unit (ICU) in a hospital.

THE STRUCTURED STORAGE OF ONCOLOGICAL CHEMOTERAPEUTIC REGIMENS - Contribution to Standardization of Therapeutic Procedures in Current Oncology

D. Klimes, L. Dusek, M. Kubasek, J. Novotny, J. Finek and R. Vyzula

The aim of the chemotherapeutic regimens (CHR) digitalization project is the proposal of a universal structure and creation of a publicly accessible database of contemporary CHR as a universal utility for the communication and evaluation of contemporary and newly defined clinical schedules in anti-tumor chemotherapy. After analysis of contemporary anti tumor CHR a standard XML structure was proposed, which enables the recording of simple CHR from the field of chemotherapy in solid adult tumors, and also has the potential of recording the complex treatment protocols in the field of paediatric oncology. The resulting XML documents were saved on a web server. A publicly accessible CHR database was constructed. There were a total of 130 XML documents with definitions of individual CHR in the first phase. Linked to this data store, three examples of web applications were added to demonstrate the potential uses of this newly created database

ON DESIGNING AN EHCR REPOSITORY

Petr Aubrecht, Kamil Matoušek and Lenka Lhotská

In an ongoing project, a pilot study and implementation of repository design for electronic home care records (EHCR) is described. Electronic home care record is based on the idea of electronic health record, however it also satisfies additional information and functionality requirements specific for home care. The design is based on the home care data and service model (K4Care model). First we analyzed the problem and decided about the platform, storage technology, cooperation with other parts of the system being developed, and basic structure of the EHCR. Then we focused on the design of data storage and transformation of the K4Care model into a database structure. Finally cooperation between the database and multiagent system is proposed.

ADAPTIVE CLINICAL PATHWAYS WITH SEMANTIC WEB RULES

Dimitrios Alexandrou, Fotis Xenikoudakis and Gregoris Mentzas

The optimization of treatment quality offered by the healthcare organizations is one of the main challenges of the modern health informatics. The personalization of treatment presupposes the real-time adaptation of treatment schemes since the clinical status of the patient and circumstances inside a healthcare organization constantly change. In this paper we present SEMPATH prototype which aims at providing a solution concerning the real-time adaptation of healthcare business processes. The prototype consists of a healthcare process execution engine assisted by a semantic framework for the adaptation. The semantic framework consists of an ontology enclosing the required knowledge based on which a semantic rule set was created. During the execution time of the clinical pathways, the system reasons over the rules, the knowledge and information collected, and provides decisions and recommendations for the next steps of the treatment. Moreover, the results of the rule-set execution may produce new knowledge objects which are inserted in the ontology.

CLASSIFICATION OF PREMATURE VENTRICULAR BEAT USING BAYESIAN NETWORKS

Lorena S. C. de Oliveira, Rodrigo V. Andreão and Mário Sarcinelli-Filho

This paper presents a system based on Bayesian networks (BN) to support medical decision-making. The proposed approach is able to learn from available data, and provides an intuitive graphical interpretation of the problem, which can be easily configured by a physician. This approach is evaluated for the first time in the problem of detecting premature ventricular contraction (PVC) using a representative set of recordings from the MIT-BIH database. The results obtained emphasize the capability of the Bayesian network to make decisions even when the information about some symptoms or events is not complete. Moreover, the good performance obtained open many perspectives of using BN to the problem of beat classification.

A COMMUNITY-CENTERED ARCHITECTURE FOR THE DEPLOYMENT OF UBIQUITOUS TELEMEDICINE SYSTEMS

Federico Cabitza, Marco P. Locatelli and Carla Simone

In this paper, we present an ubiquitous and pervasive computing architecture, CASMAS, aimed at supporting cooperation among the members of a community and their devices. We also show how CASMAS can be augmented by the WOAD framework, which was developed independently to model and express coordination mechanisms in document-mediated communities. We take the distributed hypertension monitoring case as an exemplifying and sufficiently complex scenario to show the feasibility and advantages of the our semantically informed modular approach. The scenario is then declined in terms of architectural components and cooperation-oriented mechanisms that are shared between the devices and entities of the designed community of care.

A SMART MEDICINE MANAGER DELIVERING HEALTH CARE TO THE NETWORKED HOME AND BEYOND - An Overview of the iCabiNET System

Martín López-Nores, José J. Pazos-Arias, Jorge García-Duque and Yolanda Blanco-Fernández

Misuse of prescription and over-the-counter drugs is a growing problem that impinges heavily on the well-being of people and the economics of public health systems. Most commonly, misuses arise from forgetfulness or lack of information about drugs and their interactions, hence there is much place for solutions to automatically monitor medicine intake, issue reminders and deliver medical advice. This paper presents a system that accomplishes these tasks by harnessing recent advances in smart medicine packaging, residential networks and semantic reasoning. Such a combination yields a medicine manager featuring great precision in drug monitoring, plus unprecedented capabilities to reach the users and provide them with valuable information.

USING A COMPLEX NUMERICAL AND MULTIMEDIA DATABASE IN INTERNAL MEDICINE. PRE-RELEASE EVALUATIONS

Liana Stanescu, Dumitru Burdescu, Cosmin Stoica-Spahiu, Anca Ion and Dorin Stanescu

The paper presents a software tool implemented using Firebird and Delphi technologies, dedicated for managing and querying multimedia databases. The database contains images related to the internal medicine area. This on-line application allows creation of complex medical files of patients that can be viewed and updated both by internist and general practitioner. The main functions of the application are: managing patients contact information, examinations, imagery and personal folders; simple text based query; content based query using color and color texture characteristic for images provided by medical devices. It can be used in individual offices, laboratories or in the hospital clinics and departments. The application provides security and confidentiality for patient’s data.

A LIFE SUPPORT NETWORK FOR ELDERLY PEOPLE LIVING IN A RURAL AREAS

Bayme Abaydulla, Jun Sasaki, Michiru Tanaka, Keizo Yamada and Yutaka Funyu

This paper proposes a new concept of a Life Support Network (LSN) for elderly people living in a rural area. The network is a type of Intranet, which incorporates a safety confirmation system, a remote healthcare system and an emergency information system. We developed an experimental LSN system and carried out a field experiment in a typical rural town “Shiwa” in the Iwate Prefecture in Japan. We clarified that the experimental LSN, called “Yui Net,” which has a user authentication system as well as a safety confirmation system and a remote healthcare system, works well and has the expected effects in the field.

PERFORMANCE ANALYSIS OF WIRELESS SYSTEMS IN TELEMEDICINE - Hybrid Network for Telemedicine with Satellite and Terrestrial Wireless Links

M. Luglio and F. Zampognaro

Telemedicine services represent a valuable opportunity to provide medical assistance ensuring high flexibility and prompt set up and to significantly reduce costs. The use of hybrid networks based on satellites and terrestrial wireless systems can be extremely advantageous in terms of flexibility, capillarity and integration with modern medical equipment, in particular representing a suitable solution in case of disaster. In the paper such an architecture is described and performance of some parameters for some reference applications, evaluated through simulation, are shown and discussed.

DEALING WITH THE COMPLEXITIES WHEN IMPLEMENTING INFORMATION SECURITY PRACTICES IN HEALTHCARE ORGANIZATIONS

Heitor Gottberg and Ivan Torres Pisa

With the increasing use of electronic healthcare records and other medical systems, private and confidential information are electronically stored on different databases in several computers. A new set of processes and controls are necessary to assure the information system security and personal privacy. One of the approaches to meet these demands is to establish information security practices based on international standards. Due to the complexity of healthcare operations, managers must be aware that there are additional complexities on implementing those practices. This article depicts these additional efforts, highlighting four of the extra controls that shall be implemented: disposal of media, clock synchronization, backup, and network services – as well as threats as repudiation, theft, and terrorism that must be taken into consideration by healthcare CIOs in order to become compliant to the information security standards and, therefore, fostering the use of IT on medical practice.

HEALTH CARE PROCESS MODELLING AND IMPROVEMENT

Nadja Damij and Janez Grad

The paper discusses the problem of process modelling and aims to introduce a new technique called the activity table to find a better solution for the problem mentioned. The activity table is a technique for process modelling and improvement. Business process modelling is done by identifying the business processes and is continued by choosing a process, defining its work processes and activities. Process improvement is achieved by analysis and simulation of the activity table, suggesting changes and improvements, and giving solutions for existing problems. To do this, we concentrate our work on understanding and analyzing the activity table. A complete understanding of the activity table is an essential precondition to moving forward with the simulation, which enables us to make further improvements of the process modelled. The problem of conducting a surgery is used as an example to test the technique.

MINING OF HEALTH INFORMATION FROM ONTOLOGIES

Maja Hadzic, Fedja Hadzic and Tharam Dillon

Data mining techniques can be used to efficiently analyze semi-structured data. Semi-structured data are predominantly used within the health domain as they enable meaningful representations of the health information. Tree mining algorithms can efficiently extract frequent substructures from semi-structured knowledge representation such as XML. In this paper we demonstrate application of the data mining algorithms on the health information. We illustrate this on an example of Human Disease Ontology (HDO) which represents information about diseases in 4 ‘dimensions’: (1) disease types, (2) phenotype (observable characteristics of an organism) or symptoms (3) causes related to the disease, namely genetic causes, environmental causes or micro-organisms, and (4) treatments available for the disease. The extracted data patterns can provide useful information to help in disease prevention, and assist in delivery of effective and efficient health services.

DIABETES SCREENING DATABASE - A Comprehensive Electronic Patient Record for Global Risk Assessment in a Rural Community

E. Pecoul and H. F. Jelinek

Cross professional health care is becoming more prevalent with an increase in chronic diseases such as diabetes and cardiovascular disease. In addition preventative models often require large numbers of risk factors for identification of preclinical cases. CSU has established a diabetes screening clinic and augmented by an ACCESS database. The novelty of our work is that the university-based clinic integrates into the public health sector and provides a more comprehensive review of health/disease indicators. Information on traditional health indicators is provided. Additional factors include autonomic nervous system function tests, fundus examination and foot assessment results as well as pro-inflammatory, pro-coagulation and antioxidant biochemistry. Screening results for diverse cohorts over one year have identified 16.2% of people with no previous medical condition to have pre-diabetes. 2% had retinal disease. 21.5% had foot problems. Moderate to severe ECG anomalies were identified in 19.3% of the participants. Of these, 68.8% were either commenced on treatment, had their treatment changed or received surgery following referral from the university clinic. Our results indicate that a comprehensive EPR manager as part of a multifaceted university-based health screening initiative is able to track people that require intervention but were missed in the public health system.

A FIRST APPROACH FOR A REGIONAL WIDE VEPR

Pedro Vieira-Marques, Arthur Cunha, Luís Antunes, Ricardo Cruz-Correia and Altamiro Costa-Pereira

Patients visit multiple health institutions and leave a trail of information scattered around hospitals, healthcare centres and laboratories. Information availability is of major importance in healthcare delivery. Most of the Electronic Patient Record systems are unarticulated and usually address only the specificities of a single medical specialty. Virtual Electronic Patient Records such as MAID (Multi Agent system for the Integration of Data) system provide for the necessary means for intra-institutions departmental information integration. In this paper is presented a mobile agent based extension to the agent based MAID system in order to enable inter-institution patient data integration. This system was designed as a MAID extension with additionally patient data integration features. In order to accomplish this, modules for external data discovery and collection where developed using mobile agents. Data collection activities are trigged by scheduled clinical events. The system is intended to enhance an existing institutional system taking it beyond the institutional barrier. This will provide health professionals with a more complete patient clinical history aiming at helping decision making.

AUTHENTICITY AND INTEGRITY OF PORTABLE ELECTRONIC HEALTH RECORDS

Chung-Yueh Lien, Chia-Hung Hsiao, Lu-Chou Huang and Tsair Kao

In this paper, we proposed a prototype of a secure portable electronic health record (EHR) stored using portable data storage media (CDs/DVDs, diskettes, flash drives, etc.) when leaving the hospital. This prototype is targeted at patients who are travelling or seeking second consultations. We applied cryptography to realize the authenticity and integrity of the portable EHR by using a manifest digital signature and a trusted notary re-signing mechanism. The performance of this prototype is faster than the regular digital signature mechanism.

FOR HOW LONG IS DATA FROM PREVIOUS ADMISSIONS ACCESSED BY HOSPITAL DOCTORS?

Ricardo João Cruz-Correia and Altamiro Costa-Pereira

Distinguishing relevant information enables for better user interfaces by highlighting that information, as well as better storage management by choosing storage devices with better performance for that data. However, it is hard to understand what information is really important to clinical care, and what is simply occasionally desirable. We aim to answer for how long are clinical documents useful for health professionals in a hospital environment considering its’ content and the context of information request. We have studied the databases of a Virtual Electronic Patient Record that included (1) patient identification and the list of clinical documents integrated, (2) the visualization logs; and (3) a hospital encounters database that includes the list of encounters since 1993. Our results show that some clinical reports are still used after one year regardless of the context in which they were created, although significant differences exist in reports created in distinct encounter types. The half-life of reports by encounter type is 1.7 days for emergency, 3.9 days for inpatient and 27.7 for outpatient encounters. Although the Hospital has not a unique patient record, it is obvious that doctors which to access to previous encounter reports.

PO@HEALTH - A Medical Training Telemedicine Case Study based on Ultrasound Images over an Hybrid Power Line Network

Alécio Pedro Delazari Binotto, Flávio Ávila, Carlos Eduardo Pereira, Cirano Iochpe, Ilias Sachpazidis and Georgios Sakas

The growth of fast internet, including the recent advance on using PLC (Power Line Communication) for reaching rural and remote areas in Brazil, and the state-of-the-art of image compression methods allowed rapid teleconsultations and medical training based on medical images. At the present time, one of the challenging problems in telemedicine is the real-time teleconsultation in case of emergency and for the medical training at remote regions where the internet access is precarious. In this paper, we present the kick-off of the applied project PO@Health, which merges the European-Latin American T@lemed Project (telemedicine based on ultrasound images) and the Brazilian PLC Restinga Project (communication via Power Line in a remote district). The platform used for medical teleconsultations and residents training is able to perform both on-line (in real-time) and off-line image-based teleconsultations over the Internet connection. For the ultrasound cases, the platform is being adapted to work with the DICOM medical images synchronized with the physician hand position images of the examination in order to increase the diagnosis precision. In addition, we describe the hybrid network over PLC that is being used by the telemedical platform.

FORMAL ANALYSIS OF INTELLIGENT AGENTS FOR MODEL-BASED MEDICINE USAGE MANAGEMENT

Mark Hoogendoorn, Michel Klein, Zulfiqar Memon and Jan Treur

A model-based agent system model for medicine usage management is presented and formally analysed. The model incorporates an intelligent ambient agent model that has an explicit representation of a dynamical system model to estimate the medicine level in the patient’s body by simulation, is able to analyse whether the patient intends to take the medicine too early or too late, and can take measures to prevent this.

MEDICAL IMAGE MINING ON THE BASE OF DESCRIPTIVE IMAGE ALGEBRAS - Cytological Specimen Case

I. Gurevich, V. Yashina, H. Niemann and O. Salvetti

The paper is devoted to the development and formal representation of the descriptive model of information technology for automating morphologic analysis of cytological specimens (lymphatic system tumors). The main contributions are detailed description of algebraic constructions used for creating of mathematical model of information technology and its specification in the form of algorithmic scheme based on Descriptive Image Algebras. It is specified the descriptive model of an image recognition task and the stage of an image reduction to a recognizable from. The theoretical base of the model is the Descriptive Approach to Image Analysis and its main mathematical tools. It is demonstrated practical application of algebraic tools of the Descriptive Approach to Image Analysis and presented an algorithmic scheme of a technology implementing the apparatus of Descriptive Image Algebras.

PROTECTING PRIVACY IN MEDICAL DATABASES - Efficient Local Generation of System-Wide Unique Health IDs

Peter Schartner and Martin Schaffer

In this paper we will introduce a replacement for linkable unique health identifiers: locally generated system-wide unique digital pseudonyms. The presented techniques are based on so called collision free number generators (CFNG) which are discussed in the introductory part of the article. After this brief introduction, we will pay attention to two specific variants of CFNGs: one based on asymmetric cryptography (RSA) and one based on hybrid cryptography (AES and ECC point multiplication). The main part of the article focuses on two applications of unique digital pseudonyms: centralized medical records and anonymous medical databases.

ON EXTRACTION OF NUTRITIONAL PATTERNS (NPS) USING ON EXTRACTION OF NUTRITIONAL PATTERNS (NPS) USING

M. Sulaiman Khan, Maybin Muyeba and Frans Coenen

This paper proposes a framework for mining market basket data to generate Nutritional Patterns (NPs) and a method for analysing generated nutritional patterns using Fuzzy Association Rule Mining. Edible attributes are filtered from transactional input data by projections and are then converted to Required Daily Allowance (RDA) numeric values. The RDA database is then converted to a fuzzy database that contains expended normalized fuzzy attributes comprising of different fuzzy sets. Analysis of nutritional information is performed either from normal generated association rules or from a converted fuzzy transactional database. Our approach uses prototype support tool that extract Nutritional Patterns (NPs) and signifies the level of nutritional content in an association rule per item. The paper presents various performance tests and interestingness measures to demonstrate the effectiveness of the approach and concludes with experimental results and discussion on evaluating the proposed framework.

USING EXPLANATION FACILITIES IN HEALTHCARE EXPERT SYSTEMS

Keith Darlington

A great deal has been written about healthcare expert systems in recent years. This paper examines a particular feature of expert systems: namely explanation facilities. A limited explanation capability is an integral part of a rule based expert system. The role of explanation in expert systems has been largely ignored in healthcare literature, since the MYCIN system and its derivatives were developed in the mid 1980s. However, empirical research has shown that users are more likely to adhere to recommendations made by expert systems when explanation facilities are available. Furthermore, explanation provision have been shown to improve performance and aid the user with a better understanding of the subject domain as well as result in more positive user perceptions of an expert system. The key to quality explanation facilities, however, require additional effort by the designers and should also involve users in explanation design and evaluation. This paper looks at the evolution of explanation facilities in healthcare expert systems, and investigates user requirements for explanation facilities in the healthcare domain.

NOVEL SENSOR TECHNOLOGY INTEGRATION FOR OUTCOME-BASED RISK ANALYSIS IN DIABETES

Mahesh Subramanian, Edward C. Conley, Omer F. Rana, Alex Hardisty, Ali Shaikh Ali, Stephen Luzio, David R. Owens, Steve Wright, Tim Donovan, Bharat Bedi, Dave Conway-Jones, David Vyvyan, Gillian Arnold, Chris Creasey, Adrian Horgan, Tristram Cox and Rhys Waite

Novel sensor-based continuous biomedical monitoring technologies have a major role in chronic disease management for early detection and prevention of known adverse trends. In the future, a diversity of physiological, biochemical and mechanical sensing principles will be available through sensor device ‘ecosystems’ - interoperable families of devices applicable to (for example) personal health monitoring, assistive care, and disease early detection / prevention / management scenarios. In anticipation of these sensor-based ecosystems, we have developed Healthcare@Home (HH) - a research-phase generic intervention-outcome monitoring framework. HH incorporates a closed-loop intervention effect analysis engine to evaluate the relevance of measured (sensor) input variables to system-defined outcomes. HH offers real-world sensor type validation by evaluating the degree to which sensor-derived variables are relevant (intrinsic) to the predicted outcome. This ‘index of relevance’ is essential where clinical decision support applications depend on sensor inputs. Outcome-based validation functions can be applied to any combination of biological system reporters including novel biomarkers / algorithms emerging from R&D pipelines (e.g. antibody/nucleic acid-derived probes), biochemical and biophysical effect sensors, image derived (computed) variables and/or phenotypic associations with genetic (allelic) variable data. HH can help determine system-integrated cost-utility ratios of bespoke sensor families within defined applications – taking into account critical factors like device robustness / reliability / reproducibility, mobility / interoperability, authentication / security and scalability / quality / usability. Through examples of hardware / software technologies incorporated in the HH end-to-end monitoring system, this paper discusses aspects of novel sensor technology integration for outcome-based risk analysis in diabetes.

MDFLUXO: OPHTALMOLOGY EDUCATION WITH A PDA EFFICACY AND USABILITY EVALUATION

Vladimir Camelo Pinto, Thiago Martini da Costa, Marcelo Contardo Moscoso Naveira, Daniel Sigulem, Paulo Schor and Ivan Torres Pisa

In the last decade, handheld computers, also known as Personal Digital Assistants (PDAs), have become popular among physicians, residents and medical students. We have developed a PDA-software, called MDFluxo, to assist ophthalmologic teaching as a guide. We used a user-centered design to try to diminishe usability problems. It’s interesting that the literature concerning PDA use on health area doesn’t emphasize usability attributes and it’s evaluation, which is important to widespread PDA use among health professionals. MDFluxo efficacy was evaluated comparing it to traditional book guide and a non-guide self-learning. Usability inspection methods, such as Think Aloud Method, Nielsen Heuristic Evaluation, QUIS 5.0 adaptation, and Cognitive Walkthrough are being used to identify usability problems. The usability inspection methods help us to identify usability problems and correct them. We evidenced that the students who used MDFluxo improved the resolution of the clinical case when compared to participants which did not use any material as support, however there was no significant difference when comparing the MDFluxo students to students using a book, thus, as a support to ophthalmology learning, MDFluxo is an efficacy tool.

MIAWARE SOFTWARE - 3D Medical Image Analysis with Automated Reporting Engine and Ontology-based Search

Bartłomiej Wilkowski, Oscar N. M. Pereira, Paulo Dias, Miguel Castro and Marcin Janicki

This article presents MIAWARE, a software for Medical Image Analysis With Automated Reporting Engine, which was designed and developed for doctor/radiologist assistance. It allows to analyze an image stack from computed axial tomography scan of lungs (thorax) and, at the same time, to mark all pathologies on images and report their characteristics. The reporting process is normalized - radiologists cannot describe pathological changes with their own words, but can only use some terms from a specific vocabulary set provided by the software. Consequently, a normalized radiological report is automatically generated. Furthermore, MIAWARE software is accompanied with an intelligent search engine for medical reports, based on the relations between parts of the lungs. A logical tructure of the lungs is introduced to the search algorithm through the specially developed ontology. As a result, a deductive report search was obtained, which may be helpful for doctors while diagnosing patients’ cases. Finally, the MIAWARE software can be considered also as a teaching tool for future radiologists and physicians.

PROCESS MODELING OF THE HEALTH SECTOR USING BPMN: A CASE STUDY

Elvira Rolón, Félix García, Francisco Ruiz, Mario Piattini, Luis Calahorra, Marcial García and Rafael Martin

The importance of the analysis, modeling and management of a business process is not restricted to a specific enterprise sector. In the field of sanitary management, due to the nature of the service offered, sanitary institutions’ processes are also the basis for decision making focused on achieving their objectives to grant medical assistance of quality. In this work, we will present the application of business processes modeling to the processes of an institution of the health sector, using the BPMN standard notation. The objective of this work is to show our experience obtained in the elaboration of the conceptual models of some hospital processes that can be used as a basis for others in the collaboration with hospitals for modeling their processes using BPMN. Hospital processes are very complex, and with their graphical visualization, their management and improvements are facilitated by means of the understanding and detection of possible failures.

A HEART CELL GROUP MODEL FOR THE IDENTIFICATION OF MYOCARDIAL ISCHEMIA

Mohamed A. Mneimneh, Micheal T. Johnson and Richard J. Povinelli

Due to the increasing prices of medical care, and especially due to cardiovascular injury; scientists are looking for inexpensive and less invasive ways to diagnose myocardial ischemia. Many studies have shown that the variations of the ST-segment in the ECG signal are an indicator for ischemia. For this purpose, this work proposes an approach based on a heart cell model and principle component analysis, using a decision tree classifier to differentiate between the ischemic and healthy beats. The cardiac based model is based on a simple physiological model of the electrical cycle of depolarization and repolarization of the atria and ventricles. The model parameters are estimated through the minimization of the squared error between the generated signal and the recorded ECG. The approach is applied to beats from the Long-Term ST database, which consists of 86 subjects and more than 20000 beats in which 80% of the beats are ischemic and 20% are healthy. A 10-fold cross validation test is performed over the dataset. The accuracy of this approach is 91.62%, with sensitivity of 95.09% and specificity of 75.66%.

SELECTION OF AN ARTIFICIAL NEURAL NETWORK MODEL TO DIAGNOSIS MOUTH-BREATHING CHILDREN

Felipe Mancini, Ivan Torres Pisa, Liu Chiao Yi and Shirley Shizue Nagata Pignatari

A number of factors can lead to changes in body posture, basically determined by alterations in the natural curvature of the spine. Such changes, in turn, may also result in secondary health problems. Mouth breathing is thought to be one of these problems. Experiments with healthy nasal breathing individuals have showed that when they are forced to breathe through their mouth only the natural shape of their spine curves change. However the characterization of the spine curvature in mouth breathers has not been done yet and the matter lies on the personal experience of the health professional. This study reports on the preliminary findings of a broader research which attempts to characterize the changes in the behaviour of the spine, caused by mouth breathing, by using artificial neural network modelling and data from 52 subjects. Four different models – backprogation, learning vector quantization (LVQ), and self-organizing map (SOM) – were tested for best performances in sensitivity and specificity in diagnosing mouth and nasal breathing children. Competitive-learning-based algorithms – LVQ and SOM – presented the best performance for current data set.

ICT ARCHITECTURE FOR A COMMUNITY MEDICINE

Thomas Karopka, Ilvio Bruder, Neeltje van den Berg, Wolfgang Hoffmann and Andreas Heuer

In the Federal State of Mecklenburg-West Pomerania 35-40% of the general practitioners (GPs) will retire within the next 5-7 years. In rural regions, it is difficult to find successors for the vacant practices. Thus a problem of supplying primary health care to the elderly population in rural regions is foreseeable. An efficient way to lower the workload for the remaining GPs is the implementation of a special trained community medicine nurse (CMN). The CMNs are supported by telemedicine, video conference system and a mobile data management system. In this paper we report on the ICT architecture of the project.

TELEMEDICINE TEST-BED - A Tool for Determination of Accuracy in Asynchronous Collaborative Method

Josceli Tenório, Cristina Lucia Feijó Ortolani, Paulo Roberto de Lima Lopes and Ivan Torres Pisa

Store-and-forward method has been contributing for telemedicine practical as an efficient method to the clinical diagnosis acquisition. Studies in teledermatology demonstrated important outcomes, such as use of computer systems based in asynchronous method for long-distance diagnosis, categorization, triage, or clinical outcomes agreements. However, for some issues there is no consensus between studies, such as the image parameters or the data that must be submitted to analyze. The aim of this study is propose the development of a web system that allows establishing patterns to construct web asynchronous system. A prototype was constructed to test a structure (clinical data and images) to obtain clinical diagnosis concordance in teledermatology. The preliminary outcomes showed that rate clinical diagnosis is nearly when we compare face-to-face method (76.6%) and store-and-forward (70.3%). The most effectiveness occurs to some diseases, who present easy clinical diagnosis in traditional consult. We expect that this system could introduce a numerical method, established in statistical data, to construct store-and-forward system.

A DVB-T BASED SYSTEM FOR THE DIFFUSION OF TELE-HOME CARE PRACTICE

Gianmarco Angius, Danilo Pani, Luigi Raffo, Stefano Seruis and Paolo Randaccio

Typical telemedicine systems are usually PC based and in some cases use expensive custom developed devices to achieve the system requirements. For tele-home care uses by elderly or untrained peaple, these type of solutions are impracticable. As an example of user-friendly tele-home care system, in this paper we present the first tele-home care application of DVB-T technology over standard home entertainment equipments and a prototypal low cost microcontroller-based acquisition unit for 1-lead ECG. The usability and low cost of the system show the potentiality of the approach.

HUMAN FACE VERIFICATION BASED ON MULTIDIMENSIONAL POLYNOMIAL POWERS OF SIGMOID (PPS)

João Fernando Marar and Helder Coelho

Human face verification problem can be formulated as function approximation problems and from the viewpoint of artificial neural networks these can be seen as the problem of searching for a mapping that establishes a relationship from an input to an output space through a process of network learning. A family of polynomial wavelets generated from powers of sigmoid functions is presented, in order to abolish restrictions of the backpropagation algorithm. We described how a multidimensional wavelet neural networks based on these functions can be constructed, trained and applied in image processing tasks. In this sense, a novel and uniform framework for face verification is presented in this paper. The framework is based on a family of PPS wavelets, and can be considered appearance based in that features are extracted from the face image. The feature vectors are then subjected to subspace projection of PPS-wavelet. The design of PPS-wavelet neural networks is also discussed, which is seldom reported in the literature. The Stirling Universitys face database were used to generate the results. Our method has achieved 92 % of correct detection and 5 % of false detection rate on the database.

E-ORDERING IN THE PHARMACEUTICAL SUPPLY CHAIN - Explaining Standardisation from a Collective Action Perspective

Stefan Schellhammer, Kai Riemer and Stefan Klein

In this paper, we describe critical success factors for the constitution of an electronic ordering system as an industry-wide standard between wholesalers and community pharmacies in the Republic of Ireland. The existence of multiple parties involved in this standardisation process and the nature of the standard make it worthwhile to study the case from a collective action perspective. The emergence and the diffusion of an industry-wide standard are being studied as distinct but connected set of dilemmas. The case leads us to theorise that strong industry associations play a significant role in the initiation and success of such standardisation efforts on the industry level. We conclude by pointing out essential learnings from our study and some limitations.

SPECIFYING SECURITY POLICIES FOR ELECTRONIC HEALTH RECORDS

Felix Apitzsch, Stefan Liske, Thomas Scheffler and Bettina Schnor

Sensitive data in electronic health records needs marking for special handling in order to maintain privacy. Person-centred records need mechanisms for individual and flexible marking. Policy mechanisms currently applied with shared health records in integrated care environments lack the ability to model complex privacy requirements. The paper examines the state-of-the-art policy languages for distributed processing environments XACML and XrML used for web-services or digital rights management and describes how they can be applied with XML health records. Furthermore, it prescinds the abstract concepts that need to be adopted and presents a respective reference monitor distributed policy enforcement architecture model.

A NEUROCOGNITIVE PROTOCOL SYSTEM TO SUPPORT HEALTH AND CARE OF ABUSED CHILDREN

Carlo Oliveira, Carla Marques and Jorge Moll Neto

Abused children is highly endangered of developing critical cognitive dysfunctions. Clinical observation has encountered many related cases of abuse and poor learning performance. Authorities unaware of these conditions may take longer to act, detrimentally to the child welfare. This work provides a wide coverage of medical protocols for every area concerned with endangered children procedures. These protocols were researched with the collaboration of specialist in each area to achieve the most detailed and conspicuous information of children status. These protocols are proposed as a Web system available to all concerning professionals and authorities to input and access the relevant information. This data can be processed and analyzed to provide decision support and handling indications derived from statistical and heuristic treatment of the whole information.

AUTHENTICATION OF PROFESSIONALS IN THE RTS E-HEALTH SYSTEM

André Zúquete, Helder Gomes and João Paulo Silva Cunha

This paper describes the design and implementation of a PKI-based eHealth authentication architecture. This architecture was developed to authenticate eHealth Professionals accessing RTS (Rede Telemática da Saúde), a regional platform for sharing clinical data among a set of affiliated health institutions. The architecture had to accommodate specific RTS requirements, namely the security of Professionals’ credentials, the mobility of Professionals, and the scalability to accommodate new health institutions. The adopted solution uses short lived certificates and cross-certification agreements between RTS and eHealth institutions for authenticating Professionals accessing the RTS. These certificates carry as well the Professional’s role at their home institution for role-based authorization. Trust agreements between health institutions and RTS are necessary in order to make the certificates recognized by the RTS. As a proof of concept, a prototype was implemented with Windows technology.

HEALTHCARE RISK MODELING FOR MEDICAID PATIENTS - The Impact of Sampling on the Prediction of High-Cost Patients

Sai T Moturu, Huan Liu and William G Johnson

Health care data from the Arizona Health Care Cost Containment System, Arizona’s Medicaid program provides a unique opportunity to exploit state-of-the-art data processing and analysis algorithms to mine data and provide actionable findings that can aid cost containment. Our work addresses specific challenges in this real-life health care application to build predictive risk models for forecasting future high-cost patients. We survey the literature and propose novel data mining approaches customized for this compelling application with specific focus on non-random sampling. Our empirical study indicates that the proposed approach is highly effective and can benefit further research on cost containment in the health care industry.

BRAZILIAN TELEMEDICINE NETWORKS

Ricardo Alfredo Quintano Neira, Leandro Galassi Zavitoski, Paulo Roberto de Lima Lopes, Henrique Manuel Lederman, Paulo Schor, Ivan Torres Pisa and Daniel Sigulem

One of the outcomes of the telemedicine evolution was the emergence of telemedicine networks which can be characterized as the interconnection of centers or healthcare professionals to provide telemedicine services. This paper aims to present a study and analysis of the characteristics of the Brazilian telemedicine networks. For the implementation of this study and the selection of the projects, the authors proceeded to a search and revision of articles and sites obtained in the Google and PubMed repositories. As conclusion, the existence of two types of networks was verified: physics and service; all of the networks use asynchronous telemedicine, most of them acting in inter-cities, nevertheless there are not telemedicine cases inside the own municipal district to eliminate socioeconomic barriers; there were not find inside these networks any project or initiative to regulate the remuneration of the professionals involved in the processes as well as, the payment for the services that were used.

MEDLINE ABSTRACTS CLASSIFICATION - Average-based Discrimination for Noun Phrases Selection and Weighting Applied to Categorization of MEDLINE Abstracts

Fernando Ruiz-Rico, José Luis Vicedo and María-Consuelo Rubio-Sánchez

Many algorithms have come up in the last years to tackle automated text categorization. They have been exhaustively studied, leading to several variants and combinations not only in the particular procedures but also in the treatment of the input data. A widely used approach is representing documents as Bag-Of-Words (BOW) and weighting tokens with the TFIDF schema. Many researchers have thrown into precision and recall improvements and classification time reduction enriching BOW with stemming, n-grams, feature selection, noun phrases, metadata, weight normalization, etc. We contribute to this field with a novel combination of these techniques. For evaluation purposes, we provide comparisons to previous works with SVM against the simple BOW. The well known OHSUMED corpus is exploited and different sets of categories are selected, as previously done in the literature. The conclusion is that the proposed method can be successfully applied to existing binary classifiers such as SVM outperforming the mixture of BOW and TFIDF approaches.

MEDICAL DIAGNOSIS ASSISTANT BASED ON CATEGORY RANKING

Fernando Ruiz-Rico, José-Luis Vicedo and María-Consuelo Rubio-Sánchez

This paper presents a real-world application for assisting medical diagnosis which relies on the exclusive use of machine learning techniques. We have automatically processed an extensive biomedical literature to train a categorization algorithm in order to provide it with the capability of matching symptoms to MeSH diseases descriptors. To interact with the classifier, we have developed a web interface so that professionals in medicine can easily get some help in their diagnostical decisions. We also demonstrate the effectiveness of this approach with a test set containing several hundreds of real clinical histories. A full operative version can be accessed on-line through the following site: www.dlsi.ua.es/omda/index.php

TOWARDS ON-DEMAND BIOMEDICAL KNOWLEDGE EXTRACTION

Vincenzo Lanza, M. Ignazia Cascio and Chun-Hsi Huang

This paper outlines a UMLS-compatible distributed genomic semantic network. The system aims at providing cooperative reasoning on distributed genomic information, complying with the UMLS concept representation, from distributed repositories. The distributed semantic network has currently incorporated most of the 871,584 concepts (named by 2.1 million terms) of the 2002 version UMLS Metathesaurus, with inter-concept relationships across multiple vocabularies and concept categorization supported. Modern information and compute infrastructure is incorporated to allow seamless access to geographically dispersed users.

AN ONTOLOGICAL APPROACH TO REPRESENTING AND REASONING WITH TEMPORAL CONSTRAINTS IN CLINICAL TRIAL PROTOCOLS

Ravi D. Shankar, Susana B. Martins, Martin J. O’Connor and Amar K. Das

Temporal constraints play an important role in the specification and implementation of clinical trial protocols, and subsequently, in the querying of the generated trial data. Protocols specify a temporal schedule of clinical trial activities such as tests, procedures, and medications. The schedule includes temporal constraints on the sequence of these activities, on their duration, and on potential cycles. In this paper, we present our approach to formally represent temporal constraints found in clinical trials. We have identified a representative set of temporal constraints found in protocols to study immune tolerance. Our research group has developed a temporal constraint ontology that allows us to formulate the temporal constraints to the extent required to support clinical trials management. We use this ontology to provide temporal annotation of clinical activities in an encoded clinical trial protocol. We have developed a temporal model that represents time-stamped data and facilitates interval-based temporal operations on the data. Using semantic web technologies, we are building a knowledge-based framework that integrates the temporal constraint ontology with the temporal model to support queries on clinical trial data. Using our approach, we can formally specify temporal constraints, and reason with the temporal knowledge to support management of clinical trials.

CONNECTING HOSPITALS AND HEALTH CENTRES COULD BENEFIT MOST OF PORTO’S CHILDREN POPULATION - Current Trends in Paedriatic Patients’ Mobility between Institutions Requires Implementation of Electronic Patient Records

Ana Edral, Ana Sofia Matos, Beatriz Soares, Carlos Leite, Joana Almeida, João Girão, João Nunes, Maria Isabel Pereira, Miguel Lobato, Mónica Silva, Rita Boaventura, Sofia Faria and Ricardo Cruz-Correia

Nowadays, data is spread across many institutions. Aim: This study aims establish the need for the implementation of a regional Electronic Patient Record (EPR)in the Oporto area, to support the mobility and the characteristics of the population that attends Paediatric Unit of Oporto (UPP) Methods: The study is crossectional with a consecutive sampling method. A questionnaire was applied during three days. The study population consisted of children attending to Paediatrics Emergency of Oporto (UPP). Individuals accompanying those children were approached, in the waiting room, to answer the designed questionnaire about the patient. Individuals who refused to answer, entered directly to the emergency room or did not complete the interview were excluded. Results: 151 patients entered the emergency room during the shifts, 126 were approached, 25 were immediately non available, 6 refused answering and 8 were incomplete – the response rate was 74%. The age mean was 4, with 46% being aged under 2. Within children who visited UPP, 37% have been referred: being 63% from health centres, 26% from other hospitals and the remaining from private care institutions; 25% of the patients went only to health centres for out patient care; 56% attended UPP from 2 to 5 times in the determined period. Conclusions: Implementing an EPR accessible in health centres and the UPP is relevant for the population studied, especially those under 2 years of age.

GESTURE THERAPY - A Low-Cost Vision-Based System for Rehabilitation after Stroke

L. Enrique Sucar, Ron S. Leder, David Reinkensmeyer, Jorge Hernández, Gidardo Azcárate, Nallely Casteñeda and Pedro Saucedo

An important goal for rehabilitation engineering is to develop technology that allows individuals with stroke to practice intensive movement training without the expense of an always-present therapist. We have developed a low-cost, computer vision system that allows individuals with stroke to practice arm movement exercises at home or at the clinic, with periodic interactions with a therapist. The system intgrates a web-based system for facilitating repetitive movement training, with state-of-the art computer vision algorithms that track the hand of a patient and obtain its 3-D coordinates, using two inexpensive cameras and a conventional personal computer. An initial prototype of the system has been evaluated in a pilot clinical study with positive results.

ELECTROPHYSIOLOGICAL CONTROL SIGNALS FOR PERSONS WITH NEURODEGENERATIVE CONDITIONS: BLENDED CONTROL SIGNALS

Ana Londral, Luis Azevedo and Pedro Encarnação

Severe neurological conditions may considerably affect one’s functional capabilities. Special computer interfaces and access methods have been developed in attempt to provide a mean to overcome the functional disabilities experienced by persons in these conditions. In this paper, a case study on the usage of a brainbody interface by a young man with Amyotrophic Lateral Sclerosis is presented. From the study different ways of interacting with the computer, beyond the traditional direct selection and scanning methods, emerge. These resort to control signals that combine binary and continuous features, blended control signals. Such control signals may provide more flexible and efficient ways of interacting with Assistive Technology systems, especially for those individuals with neurodegenerative conditions.

AUTOMATED QUESTION-ANSWERING TECHNIQUES AND THE MEDICAL DOMAIN

Andrea Andrenucci

The question-answering (QA) paradigm, i.e. the process of retrieving precise answers to natural language (NL) questions, was introduced in late 1960-ies and early 1970-ies within the framework of Artificial Intelligence. The advent of WWW and the need to provide advanced, user-friendly search tools has extended the QA paradigm to a larger audience of people and a larger number of fields, including medicine. This paper reviews three research approaches utilized in automated QA in medical domains and discusses their application areas

A NEW MODEL FOR SUCCESSFUL CPOE DEPLOYMENT AND IMPLEMENTATION IN HOSPITALS

Majid M. Altuwaijri

In spite of the importance of information technology (IT) for many health organizations to help manage the enterprise daily transaction, IT project failure rates still remain high. This suggests continued exploration of new process model and organization structure to nurture strong project performance. In this paper we propose a new model for successful implementation of IT projects. The proposed model calls for the establishment of a program management office (PMO) to implement corporate strategy for project management and to transform the organization into a learning one. The model is explained in details using an example of a CPOE implementation.

ORGANIC COMPUTING FOR HEALTH CARE SYSTEMS - Possible Benefits and Challenges

Florian Nafz, Frank Ortmeier, Hella Seebach and Wolfgang Reif

Todays health care institutions will undergo major changes in the next two decades. The reason for this is the change of ageing structure in many industrialized countries. In Germany statistics indicate that the costs for health care systems will at least double per person while the number of contributing, working citizens will significantly lower. At the same time average life expectation will rise above 80 years. To cope up with this developement adaptations to organization and process of health care are necessary. Typically tasks in stationary health care can be divided in two groups: task which incorporate direct interaction with the patient (care tasks) and tasks which focus on logistics and organization (background tasks). In health care it is not desirable and feasible to reduce efforts in care tasks. So costs and efforts must be reduced within the second group of tasks. This is possible if new paradigms -- both in organization and underlying software architecture -- are applied. A very promising paradigm is Organic Computing which allows for self-organizing and self-adapting systems, which can take away a lot of organizatorial work form the staff and thus allow for more and better care without rising budgets.

ASyMS©-SERAT: A SIDE-EFFECT RISK ASSESSMENT TOOL TO PREDICT CHEMOTHERAPY RELATED TOXICITY IN PATIENTS WITH CANCER RECEIVING CHEMOTHERAPY

Julie Cowie, Kevin Swingler, Clare Leadbetter, Roma Maguire, Kathryn McCall and Nora Kearney

Patients undergoing chemotherapy want specific information on potential toxicities of their treatment. Such information includes what side-effects they are likely to experience, how severe these side-effects will be, how long they will experience them for, and the best ways of managing them. As well as improving the experiences of patients, information about potential side-effects may also be of significant benefit clinically, as patients who are ‘at risk’ of developing certain toxicities may be identified, facilitating more targeted, cost-effective interventions. This paper describes research that uses risk-modelling techniques for identifying patterns in patient side-effect data to aid in predicting side-effects patients are likely to experience. Through analysis of patient data, a patient can receive information specific to the symptoms they are likely to experience. A user-friendly software tool ASyMS-SERAT (Advanced Symptom Management System-Side-Effect Risk Assessment Tool) has been developed, which presents side-effect information to the patients both at the start of treatment and reviews and monitors predictions with each new cycle of chemotherapy received.

TOWARD MOBILE HEALTHCARE SERVICES BY USING EVERYDAY MOBILE PHONES

Akio Sashima, Yutaka Inoue, Takeshi Ikeda, Tomohisa Yamashita, Masayuki Ohta and Koichi Kurumatani

Today, more than two billions people use mobile phones in the world. Current mobile phone is not just a potable telephone but a portable computer that has a WWW browser working on a multi-task OS. In this position paper, we specifilally examine the possibility of mobile healthcare services by using everyday mobile phones. We describe a prototype of the healthcare service, which consists of the following components that cooperatively work with mobile phones: wireless biological sensors, mobile sensor router and sensor middleware. The service aims for maintaining and improving user's condition by monitoring one's biological information, such as heartbeat, posture and movements.

ARE BETTER FEATURE SELECTION METHODS ACTUALLY BETTER? - Discussion, Reasoning and Examples

Petr Somol, Jana Novovicova and Pavel Pudil

One of hot topics discussed recently in relation to pattern recognition techniques is the question of actual performance of modern feature selection methods. Feature selection has been a highly active area of research in recent years due to its potential to improve both the performance and economy of automatic decision systems in various applicational fields, with medical diagnosis being among the most prominent. Feature selection may also improve the performance of classifiers learned from limited data, or contribute to model interpretability. The number of available methods and methodologies has grown rapidly while promising important improvements. Yet recently many authors put this development in question, claiming that simpler older tools show to be actually better than complex modern ones -- which, despite promises, are claimed to actually fail in real-world applications. We investigate this question, show several illustrative examples and draw several conclusions and recommendations regarding feature selection methods' expectable performance.

IMPLEMENTATION OF EPS_T2DM

Dan Bi Kim, Ju-young Lee, Eun-jung Jang, Ji-young Lee and Taek Kim

This position paper describes the implementation of an early prediction system for Type 2 diabetes mellitus. Type 2 diabetes mellitus is a multifactorial disease. It is not only associated with an unhealthy lifestyle but also has a strong genetic component. Accordingly, in order to decrease an incidence rate of T2DM, it is important to predict T2DM risk with using multifactors which are supposed to affect T2DM. We have implemented a prediction system for T2DM, and it employs several statistical prediction models. These models are produced by statistical analysis about cohort data of Korean Genome and Epidemiology Study (KoGES), and include risk factors which are adequate for preventing T2DM in Korean populations. The prediction system is written in JSF and Java, and developed into web application which is designed through object oriented modeling. Web application of this system offers user interfaces in order to input data which is needed for predicting risk group, select predefined prediction models, and so on. The system provides the results which are predicted by selected models using inputted information.

PET-CT IMAGING AND DIAGNOSIS SYSTEM FOLLOWING DOCTOR’S METHOD

Hiroshi Arisawa, Takako Sato and Sinya Hata

The diagnosis of cancer using PET (Positron Emission Tomography) and X-ray CT (Computed Tomography) images of a whole body is essential in modern medical world. This diagnosis is good at finding small cancer and discriminating a benign or a malignant tumor. However, this diagnosis is so laborious for doctor that the development of automatic diagnosis systems is expected. In this research, we propose new diagnosis model and method of description in automatic diagnosis system of PET Image Diagnosis.

A VISUAL INTERFACE BASED ON THE MVC PARADIGM TO LOCATE PEOPLE

Francisco Javier Ferrández Pastor, Juan Manuel García Chamizo and Rafael Jesús Valdivieso Sarabia

Location and tracking of mobiles, i.e. people, vehicles and systems, where global positioning systems are unable need the use of ad-hoc local techniques. There is a vast field of applications that include children and elderly cares, location of specialists in hospitals and industry, security systems, etc. Our approach proposes supervisory software and radio frequency data acquisition system to offer location and tracking services. In this paper, we present a graphical interface for simulating, monitoring and managing what each scholar does and where he is. The proposal is based on the model-view-controller paradigm and a Java implementation has been developed.

HEALTHCARE IN CONTINUUM FOR AN AGEING POPULATION - National Self Monitoring or Remote Offshore Monitoring for Australia?

Heather Grain, Kerin Robinson, Belinda Torney, Bardo Fraunholz and Chandana Unnithan

Australia is a country, similar to other developed nations, confronting an ageing population with complexities in the demographics. Ensuring continued healthcare for the ageing, while providing sufficient support for the already aged population requiring assistance, is at the forefront of national agenda. Varied initiatives are in the anvil that leverages the advantages of ICTs leading to e-Health provisioning and assisted technologies. While these initiatives increasingly put budgetary constraints on local and federal governments, there is also a case for offshoring of non-critical health services, to enable continuum of care, as the nation faces acute shortages of medical practitioners and nurses. However, privacy and confidentiality concerns in the context is being debated in Australia. In this paper, we take the position that if the electronic health records system initiative, HealthConnect is fully implemented, offshoring can be a feasible complementary option, resulting in a win-win situation of cutting costs and enabling continuum of healthcare.

MEDICAL KNOWLEDGE REPRESENTATION WITHIN HEARTFAID PLATFORM

Dragan Gamberger, Marin Prcela, Alan Jović, Tomislav Šmuc, Ganfranco Parati, Mariaconsuelo Valentini, Kalina Kawecka-Jaszcz, Katarzyna Styczkiewicz, Andrzej Kononowicz, Antonio Candelieri, Domenico Conforti and Rosita Guido

The paper presents the results of the development of the knowledge base for the HEARTFAID platform. The means and methods used to collect, systematize and formalize medical knowledge, as well as to test the developed knowledge representation are described. The descriptive part of the knowledge base is realized as an ontology which conceptualizes the heart failure medical domain. The procedural part of the knowledge base is realized through sets of production rules. The procedural knowledge covers the tasks of heart failure diagnosis, severity assessment, treatment process, medication prescription and dosage, medication contraindications, prognosis estimation, and acute decompensation detection. Finally, medical plans are used to present medical actionable knowledge. Currently they are used only to systemize procedural knowledge development process but they present a challenge for the future work in the field of medical knowledge representation.

DECISION SUPPORT AND IMAGE & SIGNAL ANALYSIS IN HEART FAILURE - A Comprehensive Use Case

Sara Colantonio, Massimo Martinelli, Davide Moroni, Ovidio Salvetti, Francesco Perticone, Angela Sciacqua, Franco Chiarugi, Domenico Conforti, Antonio Gualtieri and Vincenzo Lagani

The European STREP project HEARTFAID aims at defining an innovative platform of services able to intelligently support clinical operators in the daily management of heart failure patients. The core of the platform intelligence is a Clinical Decision Support System, developed by integrating innovative knowledge representation techniques and hybrid reasoning methods, and including advanced tools for the analysis of diagnostic data, i.e. signals and images. Aiming at showing how all these issues are combined in the HEARTFAID platform, we present a comprehensive use case, centred on echocardiography workflow and covering the clinical course leading from visit scheduling to therapeutic choices, highlighting the intervention and the value added by the Clinical Decision Support System.

A SEMANTIC GRID SERVICES ARCHITECTURE IN SUPPORT OF EFFICIENT KNOWLEDGE DISCOVERY FROM MULTILEVEL CLINICAL AND GENOMIC DATASETS

Manolis Tsiknakis, Stelios Sfakianakis, Stefan Rueping, Oswaldo Trelles, Thierry Siestang, Brecht Claerhout and Vasiilis Virvilis

This paper presents the architectural considerations of the Advancing Clinico-Genomic Trials on Cancer (ACGT) project aiming at delivering a European Biomedical Grid in support of efficient knowledge discovery in the context of post-genomic clinical trials on cancer. Our main research challenge in ACGT is the requirement to develop an infrastructure able to produce, use, and deploy knowledge as a basic element of advanced applications, which will mainly constitute a Biomedical Knowledge Grid. Our approach to offer semantic modelling of available services and data sources to support high level services and dynamic services for discovery and composition will be presented. In particular, ontologies and metadata are the basic elements through which Grid intelligence services can be developed, and the current achievmnets of the project in this domain will be discussed.

ONTOLOGY BASED INTEGRATION OF DISTRIBUTED AND HETEROGENEOUS DATA SOURCES IN ACGT

Luis Martín, Alberto Anguita, Víctor Maojo, Erwin Bonsma, Anca Bucur, Jeroen Vrijnsen, Mathias Brochhausen, Christian Cocos, Holger Stenzhorn, Manolis Tsiknakis, Martin Doerr and Haridimos Kondylakis

In this work, we describe the set of tools comprising the Data Access Infrastructure within Advancing Clinico-genomic Trials on Cancer (ACGT), a R&D Project funded in part by the European. This infrastructure aims at improving Post-genomic clinical trials by providing seamless access to integrated clinical, genetic, and image databases. A data access layer, based on OGSA-DAI, has been developed in order to cope with syntactic heterogeneities in databases. The semantic problems present in data sources with different nature are tackled by two core tools, namely the Semantic Mediator and the Master Ontology on Cancer. The ontology is used as a common framework for semantics, modelling the domain and acting as giving support to homogenization. SPARQL has been selected as query language for the Data Access Services and the Mediator. Two experiments have been carried out in order to test the suitability of the selected approach, integrating clinical and DICOM image databases.

MY-HEART PROJECT: ANALYSIS OF SLEEP AND STRESS PROFILES FROM BIOMEDICAL SIGNAL

Sergio Cerutti, Anna M. Bianchi and Martin O. Mendez

Advances in micro and nanotechnology, wireless technology, word-wide web networking, biomedical digital signal processing, textile tissue and implantable devices, etc. have permitted the development of alternative solutions for a better diagnosis of various pathologies, health care and prevention. These advances allow the remote continuous monitoring of persons, whenever and wherever they are. My-Heart FP6 EU Project integrates these components to develop a new concept of prevention and diagnosis for cardiovascular diseases. The present paper will mainly focus on a Concept of the Project which is called Take-Care and deals with the management, and integration of information for monitoring and personal motivation in the health care environment & applications. In its main goal, Take-Care Concept allows the learning in easy way about own self-body responses to different situations in the normal lifestyle: in particular, it offers an evaluation of life quality from sleep performance and stress management based on an integration of information between heart rate variability and respiration signals.

MYHEART - Fighting Cardio-vascular Diseases by Prevention and Early Diagnosis

Ralf Schmidt, Jörg Habetha and Matthew Harris

MyHeart is a so-called Integrated Project of the European Union aimed at developing intelligent systems for the prevention and monitoring of cardiovascular status. The approach of the MyHeart project is to monitor Vital Body Signs (VBS) with wearable technology, to process the measured data and to give the user (therapy) recommendations from the system. Using its broad base of technical and business expertise, four concepts adressing cardiac health have been developed and tested on a technical, business, realisability and usability level.

INITIAL RESULTS ON KNOWLEDGE DISCOVERY AND DECISION SUPPORT FOR INTRACRANIAL ANEURYSMS

Christoph M. Friedrich, Martin Hofmann-Apitius, Robert Dunlop, Ioannis Chronakis, Miriam C. J. M. Sturkenboom, Roelof Risselada, Baldo Oliva and Ferran Sanz

Intracranial Aneurysms are bulbous expansions of the intracranial vessels, that may rupture and lead to subarachnoid haemorrhage, which can result in severe disability or death of the affected person. The prediction of the individual rupture risk of a patient based on information from images, haemodynamic simulations, clinical parameters and genetic markers is one of the aims of the European Integrated Project @neurIST. The predicted rupture risk is meant to support decision making on clinical treatment. We will present initial results on Knowledge Discovery through a combination of text-mining, data integration from public bioinformatics data sources, and database mining. Additionally, we provide first results for decision support through knowledge based clinical guidelines and Bayesian networks.