| 1. |
- Forsström, Jari, et al.
(författare)
-
DIAGAID : a connectionists approach to determine the information value of clinical data
- 1991
-
Ingår i: Artificial Intelligence in Medicine. - : Elsevier. - 0933-3657 .- 1873-2860. ; 3:4, s. 193-201
-
Tidskriftsartikel (refereegranskat)abstract
- In clinical medicine the diagnosis is usually based on several signs and symptoms and some laboratory test results. It would be of great benefit if we could learn the diagnostic criteria from example cases and represent systematically the most important findings supporting or rejecting the diagnosis. In rare diseases where the physician may not be familiar with the ailment the scoring of symptoms would be very useful. In this paper we describe a connectionist approach based on Minsky-Papert's perceptrons for evaluation of the information value of clinical data in diagnosing the Nephropathia epidemica. The scores are compared with those from the Bayesian approach and from the evaluation by an experienced clinician.
|
|
| 2. |
- Strömberg, Jan-Erik, et al.
(författare)
-
Extraction of Diagnostic Rules using Recursive Partitioning Systems : A Comparision of Two Approaches
- 1992
-
Ingår i: Artificial Intelligence in Medicine. - 0933-3657 .- 1873-2860. ; 4:5, s. 373-387
-
Tidskriftsartikel (refereegranskat)abstract
- There are several empirical systems based on principles of learning from examples that can be used as a tool for decision support by medical experts in medicine. We are comparing two systems of this kind, one based on Quinlan's ID3 algorithm, and the other based on Breiman's CART (Classification And Regression Trees) algorithm. Both of these methods represent the extracted knowledge in form of binary tree structured diagnostic rules. In this paper we present the most important features of the two systems and discuss important differences between the two; all this in a uniform framework. We then study the implications these differences and similarities make when applied to clinical data. The empirical study includes two medical data sets: the first one concerning patients with highly selective vagotomy (HSV) for duodenal ulcer surgery, and the second one concerning patients with non-specified liver disease.
|
|
| 3. |
|
|
