Showing papers by "Antoine Geissbuhler published in 2009"

Clinical data mining: a review.

Abstract: Objective: Clinical data mining is the application of data mining techniques using clinical data. We review the literature in order to provide a general overview by identifying the status-of-practice and the challenges ahead. Methods: The nine data mining steps proposed by Fayyad in 1996 [4] were used as the main themes of the review. MEDLINE was used as primary source and 84 papers were retained based on our inclusion criteria. Results: Clinical data mining has three objectives: understanding the clinical data, assist healthcare professionals, and develop a data analysis methodology suitable for medical data. Classification is the most frequently used data mining function with a predominance of the implementation of Bayesian classifiers, neural networks, and SVMs (Support Vector Machines). A myriad of quantitative performance measures were proposed with a predominance of accuracy, sensitivity, specificity, and ROC curves. The latter are usually associated with qualitative evaluation. Conclusion: Clinical data mining respects its commitment to extracting new and previously unknown knowledge from clinical databases. More efforts are still needed to obtain a wider acceptance from the healthcare professionals and for generalization of the knowledge and reproducibility of its extraction process: better description of variables, systematic report of algorithm parameters including the method to obtain them, use of easy-to-understand models and comparisons of the efficiency of clinical data mining with traditional statistical analyses. More and more data will be available for data miners and they have to develop new methodologies and infrastructures to analyze the increasingly complex medical data.

3D case–based retrieval for interstitial lung diseases

Abstract: In this paper, a computer–aided diagnosis (CAD) system that retrieves similar cases affected with an interstitial lung disease (ILDs) to assist the radiologist in the diagnosis workup is presented and evaluated. The multimodal inter–case distance measure is based on a set of clinical parameters as well as automatically segmented 3–dimensional regions of lung tissue in high–resolution computed tomography (HRCT) of the chest. A global accuracy of 75.1% of correct matching among five classes of lung tissues as well as a mean average retrieval precision at rank 1 of 71% show that automated lung tissue categorization in HRCT data is complementary to case–based retrieval both from the user's viewpoint and also on the algorithmic side.

TOWARDS AN AUTOMATED NOSOCOMIAL INFECTION CASE REPORTING - Framework to Build a Computer-aided Detection of Nosocomial Infection

Abstract: The prevalence survey is a valid and realistic surveillance strategy for nosocomial infection surveillance but it is resource and labor-consuming. Querying the hospital data warehouse with a set of relevant features and applying a classification algorithm on the results can reduce the amount of cases to be evaluated by the infection control practitioners. The objective of this work is to provide a framework to build a nosocomial infection model with a set of pre-selected features with Fisher’s linear discriminant algorithm. Application of the methodology to two datasets provides promising results. It permits to predict respectively an average of 41.5% and 43.54% positive cases including respectively 65.37% and 82.56% true positive cases. The proposed framework can be applied to other classification algorithms, which are planned as future work.

From ambient assisted living to global information management: IMIA-referencing publications in 2008.

Abstract: Objective: To give an overview of publications directly referencing the International Medical Informatics Association (IMIA) in 2008. Method: Systematic search for references to IMIA over the two official IMIA journals, and reports of the recent IMIA General Assembly and Board meetings, using PubMed/Medline, supplemented by searches with Google Scholar and Google Books. Results: Beyond the IMIA Yearbook 2008, 38 IMIA-referencing publications were found by these searches, encompassing a broad range of topics, ranging from ambient assisted living technologies in home environments to global information management methodologies. Conclusions: In 2008 IMIA-referencing publications found through both medical and general search engines were predominantly in journals. In years where IMIA’s world congress on medical informatics, Medinfo take place, it could be expected that the Medinfo proceedings will also play an important role in referencing IMIA explicitly.

Les aspects organisationnels et logistiques de la télémédecine: expériences du projet CERTES au Mali

Abstract: Les experiences de telemedecine en termes de formation medicale continue (FMC) et de teleexpenise prouvent qu’elle joue un role important dans l’ameliora tion de la qualite des soins surtout dans les pays vastes et en developpment. Cependant la coordination organisationnelle et logistique de ces activites devient un enjeu majeur pour eeviter la demotivation des professionnels de la sante s’agissant du delai de reponse a leurs demandes d’ou la mise en place du Centre d’Expenise et de Recherche en Telemedecine et E-Sante (CERTES) sous la forme d’un projet de recherche sur deux ans.

Closing the loops in biomedical informatics.

Abstract: Objectives To provide an editorial introduction to the 2009 IMIA Yearbook of Medical Informatics with an overview of its contents and contributors. Methods A brief overview of the main theme, and an outline of the purposes, contents, format, and acknowledgment of contributions for the 2009 IMIA Yearbook. Results This 2009 issue of the IMIA Yearbook highlights important, beneficial loops which, if closed, could lead to considerable advances in the field of biomedical informatics and, indirectly, in healthcare and biomedical research. Progress towards closing the loops and remaining gaps are identified from the recent literature, illustrated by selected papers published during the past 12 months. Conclusion Reviews and Surveys of the main research sub-fields in biomedical informatics in the Yearbook provide an overview of progress and current challenges across the spectrum of the discipline.

Les informations médicales en ligne dignes de confiance: étude des spéciflcités en Afrique francophone

Abstract: Access to quality medical information is an important part of a health system because it may help to improve people’s health. With the development ofinformation technology and communication, new tools are available to facilitate the production, publication and access to such information. However, these tools pose new challenges. It becomes increasingly difficult to assess the credibility of medical information on the Web. It is not clear if the techniques used to produce medical information online are reliable. In addition, it is unclear whether the confidence that we can give this information is based on reliable universal criteria. It seems important to take into account the diversity of social, economic and cultural contexts in which this information is used This project offers recommendations for production and access to online medical information for health professionals. II studies the situation in French speaking Africa and particularly in Mali.

Systèmes d’information cliniques: le défi de l’intégration de systèmes commerciaux

Abstract: This paper reports the integration complexity of a commercial departmental information system within a global clinical information system.

Méthodes et évolution de la certification de sites de santé sur le Web à travers l’expérience du HONcode

Abstract: Today, the Web is a media with increasing pervasiveness around the world. Its use is constantly growing and the medical field is no exception. According to the Pew Internet & American Life Project, 80% of Internet users have searched for American medical information in 2006. However, the problem is no longer about finding information but assessing the credibility of the publishers as well as the relevance and accuracy of the documents retrieved from the web. This problem is particularly relevant in the medical area which has a direct impact on the well-being of citizens and in the Web 2.0 context where information publishing is easier than ever. To address the quality of the medical Internet, the HONcode certification proposed by the Health On the Net Foundation (HON) is certainly the most successful initiative. The aims of this paper are to present certification activity through the HONcode experience and to show that certification is more complex than a simple code of conduct. Therefore, we first present the HONcode, its application and its current evolutions. Following that, we give some quantitative results and describe how the final user can access the certified information.