Pierre Le Beux

Automatic concept extraction from spoken medical reports

OBJECTIVE The objective of this project is to investigate methods whereby a combination of speech recognition and automated indexing methods substitute for current transcription and indexing practices. METHODS We based our study on existing speech recognition software programs and on NOMINDEX, a tool that extracts MeSH concepts from medical text in natural language and that is mainly based on a French medical lexicon and on the UMLS. For each document, the process consists of three steps: (1) dictation and digital audio recording, (2) speech recognition, (3) automatic indexing. The evaluation consisted of a comparison between the set of concepts extracted by NOMINDEX after the speech recognition phase and the set of keywords manually extracted from the initial document. The method was evaluated on a set of 28 patient discharge summaries extracted from the MENELAS corpus in French, corresponding to in-patients admitted for coronarography. RESULTS The overall precision was 73% and the overall recall was 90%. Indexing errors were mainly due to word sense ambiguity and abbreviations. A specific issue was the fact that the standard French translation of MeSH terms lacks diacritics. A preliminary evaluation of speech recognition tools showed that the rate of accurate recognition was higher than 98%. Only 3% of the indexing errors were generated by inadequate speech recognition. DISCUSSION We discuss several areas to focus on to improve this prototype. However, the very low rate of indexing errors due to speech recognition errors highlights the potential benefits of combining speech recognition techniques and automatic indexing.

A Web Terminology Server Using UMLS for the Description of Medical Procedures

The Model for Assistance in the Orientation of a User within Coding Systems (MAOUSSC) project has been designed to provide a representation for medical and surgical procedures that allows several applications to be developed from several viewpoints. It is based on a conceptual model, a controlled set of terms, and Web server development. The design includes the UMLS knowledge sources associated with additional knowledge about medico-surgical procedures. The model was implemented using a relational database. The authors developed a complete interface for the Web presentation, with the intermediary layer being written in PERL. The server has been used for the representation of medico-surgical procedures that occur in the discharge summaries of the national survey of hospital activities that is performed by the French Health Statistics Agency in order to produce inpatient profiles. The authors describe the current status of the MAOUSSC server and discuss their interest in using such a server to assist in the coordination of terminology tasks and in the sharing of controlled terminologies.

Automatic Methods for Integrating Biomedical Data Sources in a Mediator-Based System

The information needed by biologists and physicians for research purposes is distributed over many heterogeneous sources. Integration systems provide a single, centralized and homogeneous interface for users to query multiple information sources simultaneously. The major limitation of integration systems, including mediator-based systems, is that the tasks involved in their creation and maintenance remain mainly manual. To address this limitation, we developed automated methods for facilitating the creation of a mediator-based system. We first implemented an automatic method for acquiring the local schemas of the sources to be integrated. We derived the global schema from the UMLS. Finally, we proposed schema-and instance-based approaches to mapping data elements from the local schemas to the global schema. To illustrate the applicability of our methods, we created a mediator-based system integrating eleven biomedical sources. This prototype is operational, available on the Internet (http://www.med.univ-rennes1.fr/cgi-bin/mougin/These/system.pl) and its evolution is managed semi-automatically.

Évaluation de l’utilisabilité de la fonction prescription connectée d’un dossier patient informatisé

Software usability is a critical aspect for user acceptance and user efficiency, especially in medical informatics. Usability is often underestimated both by vendors and customers (here hospitals). The aim of this work was to assess the usability of the CPOE function of DxCare (developed by Medasys which is the leader editor of HIS in France). A similar study was carried out 6 years ago by Evalab (EVALAB is a usability lab devoted to usability engineering of New Information Technologies in Healthcare). Our evaluation method was based on both an inspection evaluation, based on Bastien and Scapin usability criteria, and an analytical evaluation based on observation of users interactions with DxCare. For both aspects, the CPOE function of DxCare still suffers from lack of usability, identified in the previous study (readability, feedback, workload, density of information, flexibility, adaptability). This study was useful for giving objective and reliable arguments to the vendor, and for adapting training actions for end-users. An approach based on the usability certification is highly desirable to improve ergonomics in medical software.

Collecte et baladodiffusion de ressources médico-pédagogiques à destination des étudiants en médecine de PCEM2 et de DCEM1 à l’Université de Rennes 1

Information technology and communication (ITC) becomes an important way for the knowledge transmission, especially in the field of medicine. Podcasting (mobile broadcast content) has recently emerged as an efficient tool for distributing information towards professionals, especially for e-learning contents. The goal of this work is to implement software and hardware tools for collecting Medical lectures at its source by direct recording (halls and classrooms) and to provide the automatic delivery of these resources for students on different type of devices (computer, smartphone or videogames console). We describe the overall architecture and the methods used by medical students to master this technology in their daily activities. We highlight the benefits and the limits of the Podcast technologies for medical education.

La qualité des données médicales dans les dossiers patient de deux services d’accueil des urgences avant et après informatisation

Computerization of patient records now seems essential to improvement of professional practices, particularly in care traceability, care continuity or care safety. However, user acceptance of technology should not be overlooked. It is not clear, about clinical content, that information quality persists with computer-based records. This study aimed to describe medical records’ content before and after computerization of a pediatric and an adult emergency department. For both departments, 60 paper-based and 60 computer-based patient records were compared. Respectively, 25 and 14 items of the 34 evaluated items of adult and pediatric records were significantly improved in the computer version. Administrative data, traceability of patient care and prescriptions mainly benefited from shift in electronic health records, but presence of data close to medical reasoning, without being reduced, did not really show significant improvement. It could be eventually concluded that computer-based records in two different emergency structures improved overall completeness of patient records while maintaining a quality of clinical data similar to paper-based ones.