Challenges in evaluating complex decision support systems: Lessons from Design-a-Trial.
In: Quaglini, S and Barahona, P and Andreassen, S, (eds.)
ARTIFICIAL INTELLIGENCE IN MEDICINE, PROCEEDINGS.
(pp. 453 - 456).
Decision support system developers and users agree on the need for rigorous evaluations of performance and impact. Evaluating simple reminder systems is relatively easy because there is usually a gold standard of decision quality. However, when a system generates complex output (such as a critique or graphical report), it is much less obvious how to evaluate it. We discuss some generic problems and how one might resolve them, using as a case study Design-a-Trial, a DSS to help clinicians write a lengthy trial protocol.
|Title:||Challenges in evaluating complex decision support systems: Lessons from Design-a-Trial|
|Event:||8th Conference on Artificial Intelligence in Medicine in Europe (AIME 2001)|
|Dates:||2001-07-01 - 2001-07-04|
|Keywords:||decision support, evaluation, Design-a-Trial, randomised controlled trial|
|UCL classification:||UCL > School of Life and Medical Sciences > Faculty of Population Health Sciences > Institute of Epidemiology and Health Care > CHIME|
Archive Staff Only