A neural network approach to the outcome definition on first treatment with sertraline in a psychiatric population

Citation
L. Franchini et al., A neural network approach to the outcome definition on first treatment with sertraline in a psychiatric population, ARTIF INT M, 23(3), 2001, pp. 239-248
Citations number
49
Categorie Soggetti
Research/Laboratory Medicine & Medical Tecnology
Journal title
ARTIFICIAL INTELLIGENCE IN MEDICINE
ISSN journal
09333657 → ACNP
Volume
23
Issue
3
Year of publication
2001
Pages
239 - 248
Database
ISI
SICI code
0933-3657(200111)23:3<239:ANNATT>2.0.ZU;2-X
Abstract
Therapy decision is one of the most important tasks clinicians have to perf orm in their clinical practice. The decision process requires taking into a ccount many different factors. The Authors have proposed a neural computing approach for supporting clinical decision analysis. The mathematical model of artificial neural network (ANN) has been applied on a pool of clinical information gathered through case description freely filled by senior psych iatrists into 416 clinical charts. Sertraline, as drug for treatment, has b een chosen since its clinical uses range from treatment of depression to th at of many other psychiatric clinical conditions so that it has been though t to be a good candidate to this type of study. The ANN performance in fore casting successful and unsuccessful treatment cases showed an overall accur acy of classification of 97.35%. This result suggests a possible future app lication of this method to obtain a reliable prediction of a given psychiat ric patient outcome during a specific psychopharmacological therapy, optimi sing the decisional making process. (C) 2001 Elsevier Science B.V. All righ ts reserved.