The Development of AI in Medicine and the Research Environment of the SPHINX Project at the Start of the 1980s.

OBJECTIVES: To review the history of AI in Medicine in the 1980's, placing the SPHINX system in the context of other research in this field. METHODS: Summarize the main systems for AI in medicine developed in the 1970-1980 decade and their relationship to the development of clinical decision-making and consultation systems RESULTS: The approaches taken by AI in medicine research groups is compared and contrasted to those of others using statistical and logical methods for representing clinical inferences, and the different AI approaches are summarized, and related to the architecture and systems implementation of SPHINX CONCLUSION: The SPHINX system combined a number of advanced representational and inference choices from AI in designing a decision- support system for clinical consultation in the 1980s. The context within which the system was developed is outlined and related to the historical evolution of AI in medicine during that decade.

Can ICTs contribute to the efficiency and provide equitable access to the health care system in Sub-Saharan Africa? The Mali experience.

OBJECTIVE: The aim of this study is to demonstrate from actual projects that ICT can contribute to the balance of health systems in developing countries and to equitable access to human resources and quality health care service. Our study is focused on two essential elements which are: i) Capacity building and support of health professionals, especially those in isolated areas using telemedicine tools; ii) Strengthening of hospital information systems by taking advantage of full potential offered by open-source software. METHODS: Our research was performed on the activities carried out in Mali and in part through the RAFT (Réseau en Afrique Francophone pour la Télémédecine) Network. We focused mainly on the activities of e-learning, telemedicine, and hospital information systems. These include the use of platforms that work with low Internet connection bandwidth. With regard to information systems, our strategy is mainly focused on the improvement and implementation of open-source tools. RESULTS: Several telemedicine application projects were reviewed including continuing online medical education and the support of isolated health professionals through the usage of innovative tools. This review covers the RAFT project for continuing medical education in French-speaking Africa, the tele-radiology project in Mali, the "EQUI-ResHuS" project for equal access to health over ICT in Mali, The "Pact-e.Santé" project for community health workers in Mali. We also detailed a large-scale experience of an open-source hospital information system implemented in Mali: "Cinz@n". CONCLUSION: We report on successful experiences in the field of telemedicine and on the evaluation by the end-users of the Cinz@n project, a pilot hospital information system in Mali. These reflect the potential of healthcare-ICT for Sub-Saharan African countries.

Validation of a professionals' satisfaction questionnaire with electronic medical records (PSQ-EMR) in psychiatry.

BACKGROUND: Electronic medical records (EMR) are currently being implemented in psychiatric hospitals throughout Europe. The perceptions of health care professionals can contribute important information that may predict their acceptance of and desired mode of use for EMR, thus guiding EMR implementation. AIMS: To develop a self-administered instrument designed to assess health care professionals' satisfaction regarding EMR in a psychiatric hospital, based only on the professional point of view, according to the psychometric standards. METHODS: The development was supervised by a steering committee and undertaken by three standard steps. Item generation was derived from 115 face-to-face interviews with health care professionals in a French, public, psychiatric hospital. The item-reduction process resulted in a 25-item questionnaire. The validation process was based on construct validity, reliability and some aspects of external validity. RESULTS: The final version of the questionnaire contained 25 items that described five dimensions, leading to a global score. The factor structure accounted for 72% of the total variance. Internal consistency was satisfactory (item-internal consistency over 0.40 and Cronbach's alpha coefficients ranged from 0.86 to 0.95). The scalability was satisfactory with INFIT statistics inside an acceptable range. Scores of dimensions were strongly positively correlated with visual analogue scale scores (all p < 0.001). External validity showed statistical associations between scores and age, gender, seniority in psychiatry and ward type. Participation rate was 66%. CONCLUSION: The availability of a reliable and valid questionnaire (professionals' satisfaction questionnaire with electronic medical records [PSQ-EMR]) concerning health care professionals' satisfaction regarding EMR in psychiatry, exclusively generated from interviews with health care professionals, enables legitimate feedback to be incorporated into EMR implementation in order to formulate a high-quality health care.

[Establishment of an electronic medical record in a psychiatric hospital: evolution of professionals' perceptions]. / Mise en place d'un dossier patient informatisé dans un établissement public de psychiatrie : évolution des perceptions des professionnels de santé

OBJECTIVE: The potential benefits of the application of an electronic medical record (EMR) in medical care are well recognized. However, if these benefits are to be accomplished, professionals must adopt and utilize EMR as a part of their practice. The aim of this study was to assess the evolution of the health care professionals' opinions of EMR and their use on a period of 1 year in a French Public Psychiatric Hospital. SETTING: Our institution is a 204-bed psychiatric hospital, employing 328 professionals and comprising three sectors: six units of complete hospitalisation (102 beds), one unit of week hospitalisation (15 beds), one unit of emergency (seven beds) and one unit of night hospitalisation (15 beds). Three extrahospital structures include the day hospitalisation (65 places), the medicopsychological centres (CMP) and the part-time therapeutic reception centres (CATTP) of the three sectors. METHODS: We conducted face-to-face, semi-structured interviews with health care professionals of a public psychiatric hospital on two occasions: 1 month after the establishment of the EMR (t0) and one year later (t1). All the solicited people agreed to participate in the investigation. The interviews were conducted until no new ideas emerged in the content analysis performed in real time, comprising 60 care professionals at t0 (10 psychiatrists, 42 nurses and eight paramedical professionals) and 55 at t1 (six psychiatrists, 42 nurses and seven paramedical professionals). Content analysis was performed by two members of the steering committee who were skilled in textual analysis. A descriptive analysis was also performed. The variables were described by proportions and means. The proportions were compared using the Chi-squared test or Fisher exact test where appropriate. A two-tailed p-value of greater than 0.05 was considered to indicate statistical significance. Statistical analyses were carried out using SPSS version. RESULTS: The proportion of EMR use remained stable and high (respectively 97% in 2007 and 93% in 2008). However, there was an increase in the proportion of pages used in 2008 (77% of the pages) compared to 2007 (58%) (p=0.02). The analysis of interviews highlighted some elements which explained the "under-utilization" of the EMR: "the record contains too many pages", "complete all the pages is sometimes hard", "It's difficult to have a global vision of the EMR". These difficulties are reported in an equivalent way between 2007 and 2008. For the "good users", the EMR had real strengths: "the EMR contains information recorded in a synthetic and precise way"; "the EMR provides complete and rapid information on the patient". There is an improvement of positive perceptions between 2007 and 2008; for example 38% of respondents in 2008 (against 18% in 2007) appreciated the multidisciplinary nature of the EMR and 51% in 2008 (against 40%) in 2007 appreciated the "centralisation of data". The general opinion on EMR had not changed between 2007 and 2008: 70% of professionals had a favourable opinion. Similarly, we did not find statistical difference between 2007 and 2008 on the perception of the impact of EMR on the quality of relationships between professionals and between professionals and patients. The impact on the quality of care remained high. In 2007, 72% of professionals reported that EMR could have a positive impact on the care of patients against 85% in 2008 (non significant). The main impact was the improvement of the continuity and coordination of care. The proportion of professionals who did not consider that EMR could deteriorate impact on professionals-patients relationships was not statistically different between in 2007 (44%) and 2008 (56%). Sixty-six percent of professionals in 2008 against 50% in 2007 did not consider that EMR deteriorates relationships between professionals (p=0.06). However, the rates of adverse opinions remained high in 2008 on the impact of EMR on relationships in general. This was directly related to the "loss of time in completing the EMR". However, in analysing the verbatim, there was a change of potential consequences of this loss of time. "The lack of availability for patients" was less expressed than "the loss of oral communication between professionals" which was reported more frequently. CONCLUSION: This study allowed us to identify the residual problems which each hospital could face, 1 year after setting up an EMR. This preliminary work constitutes the first step in the development of a measurement tool of the use and perception of the EMR by health care professionals.

[Perception and use of an electronic medical record system by professionals of a public psychiatric hospital]. / Perception et utilisation d'un dossier patient informatisé par les professionnels d'un établissement public de psychiatrie.

OBJECTIVES: The aim of this study was to evaluate the interest taken by the health care providers in the electronic medical file and its use within the quality improvement process. SETTING: Our institution is a 204-bed psychiatric hospital, employing 328 professionals and comprising three sectors: six units of complete hospitalisation (102 beds), one unit of week hospitalisation (15 beds), one unit of emergency (7 beds) and one unit of night hospitalisation (15 beds). Three extrahospital structures include the day hospitalisation (65 places), the medicopsychological centers (CMP) and the part-time therapeutic reception centers (CATTP) of the three sectors. METHODS: We conducted face-to-face, semi-structured interviews with health care providers of a public psychiatric hospital. All the solicited people agreed to answer the investigation. The interviews were conducted until no new ideas emerged in the content analysis performed in real time, comprising 60 care providers: 10 psychiatrists, 42 nurses and eight paramedical professionals. Content analysis was performed by two members of the steering committee who were skilled in textual analysis. A descriptive analysis was also performed. The variables were described by proportions and means. The proportions were compared using the Chi-squared test or Fisher exact test where appropriate. A two-tailed P-value of greater than 0.05 was considered to indicate statistical significance. Statistical analyses were carried out using SPSS version 13.0. RESULTS: Ninety-six percent of the interviewed subjects used the electronic medical file. The average number of daily use was seven (S.D.=5). Sixty-seven percent had a favorable opinion of the electronic medical file. Physicians had more frequent favorable opinions than nurses who considered that electronic medical files cannot capture real nursing activity. Health care providers considered that electronic medical file could be associated with improved quality of care, but two points should be taken into account: the increased documentation time (slow system response, multiple screens, the lack of computer knowledge, the absence of bedside documentation technology...) and dysfunctions in the information processing system. This could have an impact on documentation completeness, and quality and could also lead to a reduction of time devoted to care. CONCLUSION: This study proposes tracks of improvement in the use of the DPIP. In spite of this, a true debate must be initiated on these new information systems in psychiatry since their real objectives can be perceived as ambiguous, so that programs of clarification, education and reinsurance can be set-up.

[Searching for evidence-based data]. / Recherche de données factuelles.

The foundation of evidence-based medicine is critical analysis and synthesis of the best data available concerning a given health problem. These factual data are accessible because of the availability on the Internet of web tools specialized in research for scientific publications. A bibliographic database is a collection of bibliographic references describing the documents indexed. Such a reference includes at least the title, summary (or abstract), a set of keywords, and the type of publication. To conduct a strategically effective search, it is necessary to formulate the question - clinical, diagnostic, prognostic, or related to treatment or prevention - in a form understandable by the research engine. Moreover, it is necessary to choose the specific database or databases, which may have particular specificity, and to analyze the results rapidly to refine the strategy. The search for information is facilitated by the knowledge of the standardized terms commonly used to describe the desired information. These come from a specific thesaurus devoted to document indexing. The most frequently used is MeSH (Medical Subject Heading). The principal bibliographic database whose references include a set of describers from the MeSH thesaurus is Medical Literature Analysis and Retrieval System Online (Medline), which has in turn become a subpart of a still more vast bibliography called PubMed, which indexes an additional 1.4 million references. Numerous other databases are maintained by national or international entities. These include the Cochrane Library, Embase, and the PASCAL and FRANCIS databases.

Virtual biomedical universities and e-learning.

In this special issue on virtual biomedical universities and e-learning we will make a survey on the principal existing teaching applications of ICT used in medical Schools around the world. In the following we identify five types of research and experiments in this field of medical e-learning and virtual medical universities. The topics of this special issue goes from educational computer program to create and simulate virtual patients with a wide variety of medical conditions in different clinical settings and over different time frames to using distance learning in developed and developing countries program training medical informatics of clinicians. We also present the necessity of good indexing and research tools for training resources together with workflows to manage the multiple source content of virtual campus or universities and the virtual digital video resources. A special attention is given to training new generations of clinicians in ICT tools and methods to be used in clinical settings as well as in medical schools.

[Regression models for crude and relative survival: a comparative review]. / Revue comparative des modèles régressifs de survie brute et de survie relative.

BACKGROUND: Statistical analysis of lifetime data is frequently used in the biomedical area. Our objective was to present a comparative review of the different regression models according to the survival concept (crude survival or relative survival) in order to express guidelines. METHODS: From a methodological point of view, we compared a regressive crude survival model (Cox model) and regressive relative survival models for grouped data (Hakulinen and Tenkanen) and for individuals data (Esteve et al.). We illustrated our work with an analysis of survival data of 3,355 incident cases of breast cancer identified by a hospital registry. Comportment of the models was studied in situation where censors rates ranged from 31.7 to 96.5%. RESULTS: Because relative survival analysis takes into account natural mortality, the risk of death was smaller for women older than 50 years than for women aged from 35 to 49; this was not demonstrated in the crude survival analysis (Cox). Estimations obtained from Cox model were more accurate than those obtained from both studied regressive relative survival models. Estimations obtained from Esteve et al. model were not very different from those obtained from Hakulinen and Tenkanen model and they were more accurate. CONCLUSION: By definition, analysis of relative survival is more appropriate to estimate survival to a specific cause of death. It is preferable to use models based on individual estimation when data set is small or when the number of individual per strata is small.

Medical decision support systems: old dilemmas and new paradigms?

OBJECTIVES: The purpose of this paper is to examine past and present medical decision support systems and the environment in which they operate and to propose specific research tracks that improve integration and adoption of these systems in today's health care systems. METHODS: In preamble, we examine the objectives, decision models, and performances of past decision support systems. RESULTS: Medical decision support tools were essentially formulated from a technical capability perspective and this view has met limited adoption and slowed down new development as well as integration of these important systems into patient management work flows and clinical information systems. The science base of these systems needs to include evidence-based medicine and clinical practice guidelines and the paradigms need to be extended to include a collaborative provider model, the users and the organization perspectives. The availability of patient record and medical terminology standards is essential to the dissemination of decision support systems and so is their integration into the care process. CONCLUSION: To build new decision support systems based on practice guidelines and taking into account users preferences, we do not so much advocate new technological solutions but rather suggest that technology is not enough to ensure successful adoption by the users, the integration into practice workflow, and consequently, the realisation of improved health care outcomes.

A preliminary study to assess a French code of ethics for health teaching resources on the Internet.

BACKGROUND: Constant assessment of the quality of health information on the Internet is an absolute necessity as peer review is often lacking in this media. OBJECTIVE: To develop a simple and easy French Code of Ethics, which will enable medical students to judge quality of health information in teaching material available on the Internet. DESIGN: Three medical informaticians selected ten criteria from previously established codes of ethics from Europe and the USA. This instrument was tested on a sample of 30 health Internet teaching resources. RESULTS: For the panel of experts, chance corrected inter-observer agreement (kappa) for quality rating ranged from k = -0.19 and k = 0.33, demonstrating poor agreement among the raters. CONCLUSION: If negative results of this preliminary study are confirmed by further research, this finding may detrimentally affect projects in Europe to accredit or certify Internet health resources.

Modelling health care processes for eliciting user requirements: a way to link a quality paradigm and clinical information system design.

Healthcare institutions are looking at ways to increase their efficiency by reducing costs while providing care services with a high level of safety. Thus, hospital information systems have to support quality improvement objectives. The elicitation of the requirements has to meet users' needs in relation to both the quality (efficacy, safety) and the monitoring of all health care activities (traceability). Information analysts need methods to conceptualise clinical information systems that provide actors with individual benefits and guide behavioural changes. A methodology is proposed to elicit and structure users' requirements using a process-oriented analysis, and it is applied to the blood transfusion process. An object-oriented data model of a process has been defined in order to organise the data dictionary. Although some aspects of activity, such as 'where', 'what else', and 'why' are poorly represented by the data model alone, this method of requirement elicitation fits the dynamic of data input for the process to be traced. A hierarchical representation of hospital activities has to be found for the processes to be interrelated, and for their characteristics to be shared, in order to avoid data redundancy and to fit the gathering of data with the provision of care.

From paper-based to electronic guidelines: application to French guidelines.

In order to develop an internet-based decision support system, making available for French general practitioners several prevention guidelines is was necessary to implement paper based guideline. We propose a framework allowing to transform paper based practice guideline into their electronic form. Three different problems were identified: computability (e.g. determinism of the eCPG), logic (e.g. ambiguities when combining Booleans operators) and external validity (i.e. stability of decision for variations around thresholds and proportion of subjects classified in the various terminal nodes). The last problem concerned documentation of evidence: the level of evidence was associated only with the terminal decision node and not with the pathway through the decision tree. We concluded that computerisation of guidelines is not possible without expertise or authors advice. To improve computability it is necessary to provide authors with a framework that checks ambiguities, and logical errors.

ARIANE: a mediation framework with health information sources.

OBJECTIVES: to design and implement mediators dedicated to access heterogeneous information sources in a homogeneous way. METHOD: processes translate a query into the syntax of a target source built thanks to the UMLS knowledge sources and a catalog of information sources. Communication services connect users with information sources at the point they deliver results. RESULTS: examples show the benefits healthcare professionals may found in searching information in this way. DISCUSSION: improvements on the current developments may be done according to the current architecture of ARIANE. Specially, the user interface should be easier to use than the present one.

Guideline development: focus on breast cancer screening in the EsPeR project.

We describe in this paper, the implementation of a clinical practice guideline focused on breast cancer screening. Our aim in conceiving such a computerized guideline was first to help general practitioners in appreciating the risks their female patients might develop breast cancer and secondly to suggest them the screening measures adapted to each particular case. This implementation enables us to present our general methodology to elaborated and promulgate guidelines within the EsPeR project. This methodology aims at providing guidelines based on knowledge validated according to the EBM principles, that can be used in real time and updated according to current knowledge.

An adaptive medical e-learning environment: the MEDIDACTE project.

Most e-learning systems offer the same tools and resource materials to students who are different in terms of motivations, training backgrounds, technical skills and learning objectives. Adaptive systems development is a challenge intended to improve the efficiency of these systems. This communication presents the design and implementation of an adaptive medical e-learning environment. The authors describe the MEDIDACTE architecture developed in three levels namely, the educational resource, educational project and user level. Current MEDIDACTE implementation and integration in Marseille Medical University curriculum are presented.

Elaboration and formalization of current scientific knowledge of risks and preventive measures illustrated by colorectal cancer.

OBJECTIVES: Present the method used to elaborate and formalize current scientific knowledge to provide physicians with tools available on the Internet, that enable them to evaluate individual patient risk, give personalized preventive recommendations or early screening measures. METHODS: The approach suggested in this article is in line with medical procedures based on levels of evidence (Evidence-based Medicine). A cyclical process for developing recommendations allows us to quickly incorporate current scientific information. At each phase, the analysis is reevaluated by experts in the field collaborating on the project. The information is formalized through the use of levels of evidence and grades of recommendations. GLIF model is used to implement recommendations for clinical practice guidelines. RESULTS: The most current scientific evidence incorporated in a cyclical process includes several steps: critical analysis according to the Evidence-based Medicine method; identification of predictive factors; setting-up risk levels; identification of prevention measures; elaboration of personalized recommendation. The information technology implementation of the clinical practice guideline enables physicians to quickly obtain personalized information for their patients. Cases of colorectal prevention illustrate our approach. CONCLUSIONS: Integration of current scientific knowledge is an important process. The delay between the moment new information arrives and the moment the practitioner applies it, is thus reduced.

Issues in the design of medical ontologies used for knowledge sharing.

Recent work in Medical Informatics is exploring the development and the use of formal ontologies as a way of specifying content-specific agreements for the sharing and reuse of knowledge among several computer systems. We describe the role of ontologies in supporting knowledge sharing activities in medicine Principles for the design of ontologies have been proposed, mainly in other domains: these principles include parsimony, clarity, representation of categories versus terms, and coherence. We analyze how and why these principles can or cannot be applied from case studies from medical systems. Regarding the fact that most of medical concepts are empirical, selected design decisions are discussed. An alternative representation choice consists in mapping principled general core ontologies and domain ontologies.