The process of applying a practice guideline to a patient requires a great deal of clinical data. AAPT (Appropriateness-Assessment Processing from Text) is an experimental computer program that can assess the appropriateness of coronary-artery bypass grafting surgery (CABG) in patients with coronary-artery disease (CAD) and chronic stable angina from the admission summaries of those patients. The AAPT architecture combines natural-language processing (NLP) and probabilistic inference. The NLP module identifies single clinical concepts of interest in the free-text document. The probabilistic inference module, a Bayesian belief network, estimates values for variables not specifically mentioned. AAPT produces a patient's summary of CAD that is similar to a manually generated clinical summary. Work is ongoing to improve AAPT and evaluate it as a tool to assist in the dissemination of guidelines and as a tool to encourage adherence to practice guidelines.
[1]
David J. Spiegelhalter,et al.
Local computations with probabilities on graphical structures and their application to expert systems
,
1990
.
[2]
D. Kanouse,et al.
The appropriateness of performing coronary artery bypass surgery.
,
1988,
JAMA.
[3]
E R Gabrieli,et al.
Automated screening for quality of care in the hospital--a feasibility study.
,
1989,
Journal of clinical computing.
[4]
M M Wagner,et al.
An automatic indexing method for medical documents.
,
1991,
Proceedings. Symposium on Computer Applications in Medical Care.