Evaluation of clinical decision aids–more to think about
- 1 January 1990
- journal article
- research article
- Published by Taylor & Francis in Medical Informatics
- Vol. 15 (3) , 275-284
- https://doi.org/10.3109/14639239009025275
Abstract
Validation and clinical testing of medical decision aids is a hot topic at present. We state a few main points which, in our opinion, have not received the attention they deserve. Our main concerns have to do with the statistical design and analysis of field evaluation studies; with long-term effects; and with the interplay between medicine and the software industry. The points represent our reaction to a recent symposium on the topic, published in this special issue. We take the opportunity to supplement the papers at hand in various ways and, where we see a risk of misconceptions or poor practice becoming cemented, try to point out the proper course.Keywords
This publication has 11 references indexed in Scilit:
- Evaluating medical expert systems: what to test and how?Medical Informatics, 1990
- Evaluating black-boxes as medical decision aids: issues arising from a study of neural networksMedical Informatics, 1990
- Evaluating and validating very large knowledge-based systemsMedical Informatics, 1990
- The evaluation of decision aids: the role of the decision ownerMedical Informatics, 1990
- A performance evaluation of the expert system ANEMIAComputers and Biomedical Research, 1988
- Prognosis in medicine: An analysis of its meaning and rôlesTheoretical Medicine and Bioethics, 1987
- Validating Expert System PerformanceIEEE Expert, 1987
- Clinical Prediction RulesNew England Journal of Medicine, 1985
- Evaluation of clinical decision‐aids, with an application to a system for dyspepsiaStatistics in Medicine, 1983
- The Measurement of Performance in Probabilistic DiagnosisMethods of Information in Medicine, 1978