Domenico M. Pisanelli

Evaluation stages and design steps for knowledge-based systems in medicine

After the early experiments in artificial intelligence a methodology is emerging around advanced systems for the management of medical knowledge. The stress is moving away from the implementation of prototypes to the evaluation. It is possible to adapt and to apply this to field evaluation techniques already developed in similar contexts of knowledge management (books, drugs, epidemiology, consultants, etc.). The time is ready for a further step: to envisage a methodology for the design of real systems that cope with the knowledge environment of the user. Every stage of the evaluation process is re-examined here, and considered as a framework to define goals and criteria about a step of design: (1) the impact of the system on the progress of health care provision (priorities, cost-benefit analysis, share of tasks among different media); (2) effectiveness in the end-users environment and long-term effects on his behaviour (changes in peoples role and responsibilities, improvements in the quality of data, acceptance of the system); (3) the intrinsic efficiency of the system apart from the operational context (correctness of the knowledge base, appropriateness of the reasoning). The need to differentiate the test sample into three classes (obvious, typical, atypical) is emphasized, discussing the influence on both evaluation and design. In particular the difficulty of having gold standards on atypical cases, due to the disagreement among the experts, leads to the definition of two alternative attitudes: the standardization mode and the brain-storming mode.

An object-oriented model for a multimedia patient folder management system

The management of information related to clinical activities is a complex task. In fact, patient related information reported in patient folders comes from heterogeneous sources and may be rendered by means of different modalities. Data can originate from direct observations made by physicians like in the case of objective examination. In other cases physiologic phenomena are captured by means of the involved electrical activity (like in the case of heart or brain activity), whereas anatomical structure details are obtained by means of radiologic techniques. In this paper we propose an object-oriented model of a multimedia patient folder. This model has an adequate flexibility for adapting the most different clinical environment. It allows the physician to structure the information needed for his/her patient folder without employing a programming language. Finally we show some features of the CADMIO system, a tool for designing patient folder management systems, based on this model.

A survey of telemedicine in Italy.

Italy has a tradition of experimental telemedicine which dates back to the early 1970s. However, despite promising experience, widespread diffusion of telemedicine services has not occurred. The Ministry of Research recognized the potential of telemedicine for improving the quality of health care and reducing costs, and has launched a national plan for financing research and training. The plan is expected to have a major impact on the organization of telemedicine research in Italy. In this paper we describe the current situation, outline the structure of the national plan, and survey various applications in different fields, such as teleconsulting, teleradiology and telemonitoring.

ADAMS: Aggregate data management system for epidemiologists and health-care managers

An effective health-care policy is supported by the availability of data in the form of statistical tables for epidemiologists and health-care managers. Creation, analysis and exploitation of these data strongly support the monitoring of trends in mortality and morbidity phenomena and the evaluation of offered health services. This might imply the transformation of statistical tables to more suitable formats. A successful management, manipulation and querying of a statistical table is a complex activity requiring a considerable knowledge of statistical problems. Computerised support can be precious in this task and this led to the development of several data management systems. In this paper we sketch out the features of ADAMS (Aggregate Data Management System), a system conceived to allow an easy interaction with statistical tables, reshaping and browsing of their descriptive part. ADAMS aims at simplifying the problem of extracting information from a statistical database and performing statistical table manipulation. The following functionalities are provided: definition of a statistical database at descriptive level; storage of data in the database; manipulation of data according to the summarisation and reclassification operators; browsing between data and their descriptive part. It also supports different manipulation styles according to different user profiles.

An object-oriented information model for a patient definition and management system

Folder , Ob jec t -Or i en t ed The management of information related to clinical activities is a complex task. In fact, patient related information reported in patient folders comes from heterogeneous sources and may be rendered by means of different modalities. Data can originate from direct observations made by physicians like in the case of objective examination. In other cases physiologic phenomena are captured by means of the involved electrical activity (like in the case of heart or brain activity), whereas anatomical structure details are obtained by means of radiologic techniques, in this paper we propose an object-oriented model of a multimedia patient folder. This model has an adequate flexibility for adapting the most different clinical environment. It allows the physician to structure the information needed for his/her patient folder without employing a programming language. Finally we show some features of the CADMIO system, a tool for designing patient folder management systems, based on this

Expert Interface for Epidemiologic Data Management

TEA (Tool for Epidemiologic Assistance, formerly EPITOOL) is a research project carried on at the National Research Council. Its aim is the realization of a knowledge-based system to manage epidemiological data, in particular mortality and morbidity data [FA89].

Intelligent databases for medical statistical analysis

A research project concerning epidemiological and statistical databases is briefly described. The aim of the project is to define an integrated and knowledge-based system to support epidemiological data management. The support provided for epidemiological analysis can be applied throughout the process of statistical analysis, from the choice of study design and statistical indicators to data analysis and result interpretation. The system has to provide a simple but adequate man-machine interface that is suitable at all user levels.<<ETX>>

The Role of Knowledge Based Systems in Medicine

We examine some paradigms for a comprehensive evaluation of Knowledge Based Systems (KBSs) in the health field to envisage a methodology for the proper design of such systems.

The ontological lens: zooming in and out from genomic to clinical level

Ontology is the talk of the day in the medical informatics community. Its relevant role in the design and implementation of information systems in health care is now widely acknowledged. In this paper we present two case studies showing ontologies “at work” in the genomic domain and in the clinical context. First we show how ontologies and genomic controlled vocabularies can be effectively applied to help in a genomic approach towards the comprehension of fundamental biological processes and complex cellular patho-physiological mechanisms, and hence in biological knowledge mining and discovery. Subsequently, as far as the clinical context is concerned, we emphasize the relevance of ontologies in order to maintain semantic consistency of patient data in a continuity of care scenario. In conclusion we advocate that a deep analysis of the structure and the concepts present at different granular level – from genes to organs – is needed in order to bridge this different domains and to unify bio-medical knowledge in a single paradigm.

The MIC/MIE model for generating multimedia patient folders

The patient folder is the main source of documentation on the patients health state. It is not a mere collection of information, but a set of heterogeneous documents accessed by different users having different goals (e.g. choice of a therapeutic strategy, quality assessment). In this paper, we present an information model – the MIC/MIE model – able to represent the heterogeneous kinds of data composing a patient folder. The MIC/MIE model is based on an object-oriented approach and supports the definition of a multimedia patient folder. It is flexible enough to be adapted to diverse clinical environments and it allows physicians to structure the information needed in their patient folder without employing a programming language. Finally, we show some features of the CADMIO system, a tool based on this model which can be employed for designing patient folder management systems.