Biomedical subjects

Patrice Degoulet

Publications and source records attributed to Patrice Degoulet.

17 recordsLinked to original sources

PubMed2006

Integrating anatomical pathology to the healthcare enterprise.

For medical decisions, healthcare professionals need that all required information is both correct and easily available. We address the issue of integrating anatomical pathology department to the healthcare enterprise. The pathology workflow from order to report, including specimen process and image acquisition was modeled. Corresponding integration profiles were addressed by expansion of the IHE (Integrating the Healthcare Enterprise) initiative. Implementation using respectively DICOM Structured Report (SR) and DICOM Slide-Coordinate Microscopy (SM) was tested. The two main integration profiles--pathology general workflow and pathology image workflow--rely on 13 transactions based on HL7 or DICOM standard. We propose a model of the case in anatomical pathology and of other information entities (orders, image folders and reports) and real-world objects (specimen, tissue samples, slides, etc). Cases representation in XML schemas, based on DICOM specification, allows producing DICOM image files and reports to be stored into a PACS (Picture Archiving and Communication System.

Diagnostic Imaging↗

PubMed2005

Building an ontology of adverse drug reactions for automated signal generation in pharmacovigilance.

Automated signal generation in pharmacovigilance implements unsupervised statistical machine learning techniques in order to discover unknown adverse drug reactions (ADR) in spontaneous reporting systems. The impact of the terminology used for coding ADRs has not been addressed previously. The Medical Dictionary for Regulatory Activities (MedDRA) used worldwide in pharmacovigilance cases does not provide formal definitions of terms. We have built an ontology of ADRs to describe semantics of MedDRA terms. Ontological subsumption and approximate matching inferences allow a better grouping of medically related conditions. Signal generation performances are significantly improved but time consumption related to modelization remains very important.

Adverse Drug Reaction Reporting Systems↗

PubMed2005

Impact of CPOE on doctor-nurse cooperation for the medication ordering and administration process.

The objective of this study was to analyze the impact of medication ordering and administration functions of CPOE on doctor-nurse communications and cooperation. We performed an extensive analysis of the work situations in several departments of three different hospitals. One of the hospitals is still using paper-based orders, the second one is currently implementing a patient care information system (PCIS), but the analysis was carried out with paper-based orders. The third hospital has a PCIS installed with available medication ordering functions. We used standard methods from cognitive psychology to analyze physicians, and nurses' activity, communications and cooperation. This approach was combined with a usability analysis of both work systems, paper and computer-based. The paper-based situation is characterized by a synchronous cooperation with a distributed decision-making where physicians and nurses rely mostly on verbal communications to coordinate their actions; paper order sheets are weakly structured and poorly support the documentation task. In the computer situation, physicians and nurses work in an asynchronous mode, and leave to the system the coordination of their actions. Orders are exhaustively documented but some data may be misinterpreted. Some of these problems are due to usability flaws of the Human Computer Interface. We conclude with recommendations for usability improvement of CPOE systems, combined with recommendations for the organization of doctor-nurse communication when implementing such systems.

Communication↗

PubMed2005

Implementation of automated signal generation in pharmacovigilance using a knowledge-based approach.

Automated signal generation is a growing field in pharmacovigilance that relies on data mining of huge spontaneous reporting systems for detecting unknown adverse drug reactions (ADR). Previous implementations of quantitative techniques did not take into account issues related to the medical dictionary for regulatory activities (MedDRA) terminology used for coding ADRs. MedDRA is a first generation terminology lacking formal definitions; grouping of similar medical conditions is not accurate due to taxonomic limitations. Our objective was to build a data-mining tool that improves signal detection algorithms by performing terminological reasoning on MedDRA codes described with the DAML+OIL description logic. We propose the PharmaMiner tool that implements quantitative techniques based on underlying statistical and bayesian models. It is a JAVA application displaying results in tabular format and performing terminological reasoning with the Racer inference engine. The mean frequency of drug-adverse effect associations in the French database was 2.66. Subsumption reasoning based on MedDRA taxonomical hierarchy produced a mean number of occurrence of 2.92 versus 3.63 (p < 0.001) obtained with a combined technique using subsumption and approximate matching reasoning based on the ontological structure. Semantic integration of terminological systems with data mining methods is a promising technique for improving machine learning in medical databases.

Adverse Drug Reaction Reporting Systems↗

PubMed2005

Cognitive analysis of physicians' medication ordering activity.

Computerized Physician Order Entry (CPOE) addresses critical functions in healthcare systems. As the name clearly indicates, these systems focus on order entry. With regard to medication orders, such systems generally force physicians to enter exhaustively documented orders. But a cognitive analysis of the physician's medication ordering task shows that order entry is the last (and least) important step of the entire cognitive therapeutic decision making task. We performed a comparative analysis of these complex cognitive tasks in two working environments, computer-based and paper-based. The results showed that information gathering, selection and interpretation are critical cognitive functions to support the therapeutic decision making. Thus the most important requirement from the physician's perspective would be an efficient display of relevant information provided first in the form of a summarized view of the patient's current treatment, followed by in a more detailed focused display of those items pertinent to the current situation. The CPOE system examined obviously failed to provide the physicians this critical summarized view. Following these results, consistent with users' complaints, the Company decided to engage in a significant re-engineering process of their application.

Cognition↗

PubMed2005

Patient data synchronization process in a continuity of care environment.

In a distributed patient record environment, we analyze the processes needed to ensure exchange and access to EHR data. We propose an adapted method and the tools for data synchronization. Our study takes into account the issue of user rights management for data access and decreasing the amount of data exchanged over the network. We describe a XML-based synchronization model that is portable and independent of specific medical data models. The implemented platform consists of several servers, of local network clients, of workstations running user's interfaces and of data exchange and synchronization tools.

Access to Information↗

PubMed2004

A knowledge based approach for automated signal generation in pharmacovigilance.

BACKGROUND: Pharmacovigilance experts detect new adverse drug reactions (ADR) by manually reviewing spontaneous reporting systems. Automated signal generation aims to focus the attention of experts on drug-adverse event associations which are disproportionally present in the database. Although adverse events are coded by means of controlled vocabularies such as the MedDRA dictionary, this semantic information is not taken into account for signal generation. OBJECTIVE: To improve the performance of current signal detection algorithms using knowledge based approach. METHOD: We developed a formal ontology of ADRs and built a data mining tool that uses description logic representations of MedDRA terms to group medically related case reports. RESULTS: This knowledge based approach increased the sensitivity of signal detection with no decrease in specificity. DISCUSSION: A knowledge based approach improved the performance of signal detection tools. However, the huge work-load involved in the knowledge engineering step limits the use of this approach for machine learning.

Adverse Drug Reaction Reporting Systems↗

PubMed2004

Specifications and implementation of a new exchange format to support computerized consensus in pathology.

In the pathology domain, consensus sessions around multi-headed microscopes enhance reproducibility and can reduce inter- and intra-observer variability. Computerized tools and Web technology could facilitate the organization of consensus sessions and assist pathologists to agree on features that are relevant to diagnosis. In the context of the IDEM project, whose aim is to achieve a computerized platform to allow pathologists to derive consensual diagnostic during Internet-based collaborative sessions, we propose a new extension of the existing TELESLIDE format. This new extended format enables the storage and the exchange of multi-experts descriptions that will be processed by the IDEM consensus engine to produce consensual descriptions. We describe this new format and its implementation in the IDEM teleconsensus platform.

Consensus↗

PubMed2004

A usability study of CPOE's medication administration functions: impact on physician-nurse cooperation.

Implementation of CPOE systems in Healthcare Institutions has proven efficient in reducing medication errors but it also induces hidden side-effects on Doctor-Nurse cooperation. We propose a usability engineering approach to this problem. An extensive activity analysis of the medication ordering and administration process was performed in several departments of 3 different hospitals. Two of these hospitals are still using paper-based orders, while the 3rd one is in the roll-out phase of medication functions of its CPOE system. We performed a usability assessment of this CPOE system. The usability assessment uncovered usability problems for the entry of medication administration time scheduling by the physician and revealed that the information can be ambiguous for the nurse. The comparison of cooperation models in both situation shows that users tend to adopt a distributed decision making paradigm in the paper-based situation, while the CPOE system supports a centralized decision making process. This analysis can support recommendation for the re-engineering of the Human-Computer Interface.

Attitude of Health Personnel↗

PubMed2003

The HEGP component-based clinical information system.

OBJECTIVES: The opening of the Georges Pompidou University Hospital (HEGP) in southwest Paris from the merging of three aging facilities was the opportunity to conceive and deploy a brand new clinical information system (CIS) based on a component-based approach. This paper describes the process of selection of the business components, the main functions currently in use, and the technical infrastructure that proved necessary. METHODS: The HEGP CIS features generic and healthcare-related components. The generic components include a reference manager, a security manager, a document manager, a Corba bus, and various mediation and supervision tools. The healthcare-related components include the patient, healthcare record, act management, and resource scheduler components. RESULTS: Major functions of CIS were operational at the opening of the hospital in July 2000. Two years later, the unique patient record and the provider order entry system were used in 96% of the concerned healthcare units. Sixty-five percent of the biological orders and 55% of the imaging orders were directly entered by the physicians. Access to investigation results including on-line availability of images is used by physicians in 100% of the units. DISCUSSION AND CONCLUSION: A component-based approach was found to be high-performing and cost-effective for the design and deployment of HEGP CIS.

Hospital Information Systems↗

PubMed2003

A collaborative platform for consensus sessions in pathology over Internet.

The design of valid databases in pathology faces the problem of diagnostic disagreement between pathologists. Organizing consensus sessions between experts to reduce the variability is a difficult task. The TRIDEM platform addresses the issue to organize consensus sessions in pathology over the Internet. In this paper, we present the basis to achieve such collaborative platform. On the one hand, the platform integrates the functionalities of the IDEM consensus module that alleviates the consensus task by presenting to pathologists preliminary computed consensus through ergonomic interfaces (automatic step). On the other hand, a set of lightweight interaction tools such as vocal annotations are implemented to ease the communication between experts as they discuss a case (interactive step). The architecture of the TRIDEM platform is based on a Java-Server-Page web server that communicate with the ObjectStore PSE/PRO database used for the object storage. The HTML pages generated by the web server run Java applets to perform the different steps (automatic and interactive) of the consensus. The current limitations of the platform is to only handle a synchronous process. Moreover, improvements like re-writing the consensus workflow with a protocol such as BPML are already forecast.

Computer Systems↗

PubMed2003

Analysis of hospitalised patient flows using data-mining.

UNLABELLED: Face to the development of hospital information system in the "Hôpital Européen George Pompidou" (HEGP), computerized patients records made medical data easier to analyse than before. We use data-mining technology to analyse intra-hospital patients' paths with one year of PMSI data (a French medical information system similar to Diagnosis Related Group). METHODS: 1. "sequential patterns mining" was used to analyse the most frequent patients' paths, 2. an integrated framework of "association rules mining" and "classification rule mining" was used to build prediction rules of patients' paths. RESULT: We construct a rule based prediction model, which gives the tendency of the patient's paths between the different medical units.

Computer Communication Networks↗

PubMed2003

Pragmatic objects modeling environment for Electronic Health Records Systems.

Customizable shared Electronic Health Care Records require new mechanisms to dynamically generate user defined objects. An object model based on a semantic network of concepts has been implemented (pragmatic database model). This model offers an easier way to represent "archetypes" of user objects including the concepts, their relationships and the specific organization and representation of the associated knowledge that are necessary to model the context of production of record elements. The aim of this paper is the presentation of this framework and its implementation in an online electronic health record system using Java Web Services technologies. A web-based registry on tobacco was implemented according to this framework and is today daily used in 150 tobacco addiction centers.

Database Management Systems↗

PubMed2003

New terminology services based on term comparison using semantic definitions and similarity computation.

As medical information can be encoded within different terminological systems, terms comparison is an important issue to allow communication between applications. In description logics, terms are compared by the means of semantic definitions and subsumption relations. Similarity is also a convenient method for term comparison but is not supported by terminology servers which implement subsumption relations. We present new terminology services built on a semantic distance that could help for semantic mediation between medical applications ranging from semi-automatic encoders to data mining tools. These services are 1) comparison between terms 2) k-nearest-neighbors 3) support for concept coding 4) automatic generation of similarity tables 5) distance based queries 6) support for clustering.

Artificial Intelligence↗

PubMed2002

A generic computerized method for estimate of familial risks.

Most guidelines developed for cancers screening and for cardiovascular risk management use rules to estimate familial risk. These rules are complex, difficult to memorize, and need to collect a complete pedigree. This paper describes a generic computerized method to estimate familial risks and its implementation in an internet-based application. The program is based on 3 generic models: a model of the family; a model of familial risk; a display model for the pedigree. The model of family allows to represent each member of the family and to construct and display a family tree. The model of familial risk is generic and allows easy update of the program with new diseases or new rules. It was possible to implement guidelines dealing with breast and colorectal cancer and cardiovascular diseases prevention. First evaluation with general practitioners showed that the program was usable. Impact on quality of familial risk estimate should be more documented.

Breast Neoplasms↗

PubMed2002

A customizable similarity measure between histological cases.

IDEM, a computerized environment dedicated to pathologists, includes a Case Based Reasoning (CBR) procedure to retrieve similar histological cases in the database. The relevancy of a retrieved case strongly depends on the similarity measure comparing case descriptions. The present work deals with the definition of a similarity measure in the context of IDEM. In a first step, a theoretical measure (relational, numerical and informed), based on the domain constraints, was selected. In a second step, the theoretical measure is optimized according to the current case base. Results are presented for a database of 53 cases of breast tumors. The contribution of this work is to give to pathologists an interactive environment that optimizes the similarity measure between histological cases. This work is also a contribution to the CBR cycle life since the similarity measure can be adapted while new cases are added to the base.

Artificial Intelligence↗

PubMed2002

Terminology extraction from text to build an ontology in surgical intensive care.

In many medical fields, the maintenance of unabiguous terminologies, the comparison and aggregation of different terminologies go through the building of formal specialized clinical terminologies, the ontologies. In this paper, we describe the building of an ontology in the surgical intensive care medical domain. We considered textual reports as the main source of information and a natural language processing tool, the SYNTEX software, is used to build the ontology. We have tested the possibility for an expert to build a sizeable ontology in a reasonable time. The quality of the ontology has been evaluated according to its capacity to cover the ICD-10 terminology in the field. Examples of coding activity with the ontology are proposed and discussed.

Critical Care↗