Continual updating and monitoring of clinical prediction models: time for dynamic prediction systems?

Diagnostic and Prognostic Research

Richard D. Riley¹  Gary S. Collins²  Matthew Sperrin³  Niels Peek³  David A. Jenkins³  Glen P. Martin³  Thomas P. A. Debray⁴ 

[1] Centre for Prognosis Research, School of Primary, Community and Social Care, Keele University;Centre for Statistics in Medicine, Nuffield Department of Orthopaedics, Rheumatology and Musculoskeletal Sciences, University of Oxford;Division of Informatics, Imaging and Data Science, Faculty of Biology, Medicine and Health, The University of Manchester, Manchester Academic Health Science Centre;Julius Center for Health Sciences and Primary Care, University Medical Center Utrecht, Utrecht University;

关键词: Clinical prediction models;    Dynamic model;    Validation;    Model updating;    Model development;    Learning health system;   

DOI  :  10.1186/s41512-020-00090-3

来源: DOAJ

【 摘 要 】

Abstract Clinical prediction models (CPMs) have become fundamental for risk stratification across healthcare. The CPM pipeline (development, validation, deployment, and impact assessment) is commonly viewed as a one-time activity, with model updating rarely considered and done in a somewhat ad hoc manner. This fails to address the fact that the performance of a CPM worsens over time as natural changes in populations and care pathways occur. CPMs need constant surveillance to maintain adequate predictive performance. Rather than reactively updating a developed CPM once evidence of deteriorated performance accumulates, it is possible to proactively adapt CPMs whenever new data becomes available. Approaches for validation then need to be changed accordingly, making validation a continuous rather than a discrete effort. As such, “living” (dynamic) CPMs represent a paradigm shift, where the analytical methods dynamically generate updated versions of a model through time; one then needs to validate the system rather than each subsequent model revision.

【 授权许可】

Unknown