logo BDSP

Base documentaire

  1. Improving the statistical approach to health care provider profiling.

    Article, Communication - En anglais

    Regenstrief Conference. Marshall, IN, USA, 1996/09/04.

    This paper reviews and compares existing statistical methods for profiling health care providers.

    It recommends improvements that are based on the use of better statistical models and the adoption of more realistic, medically based criteria for judging the performance of health care providers.

    Unlike most profiling methods, the proposed hierarchical models allow the probability of acceptable provider performance to be calculated ; thus, they can answer such questions as, « What is the probability that a given hospital's true mortality rate for cardiac surgery patients exceeded 3.33% last year ? » The commonly encountered problems of regression-to-the-mean bias and small caseloads can be handled by using hierarchical models to extract more information from profiling data.

    Mots-clés Pascal : Soin santé primaire, Critère décision, Facteur prédictif, Analyse statistique, Critère performance, Classification hiérarchique, Estimation erreur, Outil logiciel, Homme, Profilométrie, Organisation santé, Informatique

    Mots-clés Pascal anglais : Primary health care, Decision criterion, Predictive factor, Statistical analysis, Performance requirement, Hierarchical classification, Error estimation, Software tool, Human, Profilometry, Public health organization, Computer science

    Logo du centre Notice produite par :
    Inist-CNRS - Institut de l'Information Scientifique et Technique

    Cote : 98-0051840

    Code Inist : 002B28F. Création : 14/05/1998.