Logo image
Artificial Intelligence: A Computerized Decision Aid for Trauma
Journal article

Artificial Intelligence: A Computerized Decision Aid for Trauma

JOHN Clarke, DAVID Cebula and BONNIE Webber
The journal of trauma, v 28(8), pp 1250-1254
Aug 1988
PMID: 3045338

Abstract

A computerized decision support system has been developed to advise ATLS-trained surgeons on the initial definitive management of patients with penetrating injuries of the abdomen immediately following resuscitation and stabilization. The program was developed as an “expert system,” using the techniques of artificial intelligence. It is able to suggestthe need for further examination; additional tests; diagnoses; and treatments. In this study, the advice offered by the expert system was compared to that of physicians-in-training. Five actual patient care situations were presented to the system and to 13 medical students and surgical residentsfour MS-III, three PGY-I, three PGY-III, and three PGY-V. The suggestions of each of the 13 trainees, the advice of the expert system, and the actual management were blinded. Five surgeons versed in trauma and otherwise not involved in the project judged whether each of the 15 purported management plans was acceptable and ranked them in order of preference. Only the actual care and the advice from the system were judged acceptable for all five problems. The rankings of the expert system were better than those of any individual trainee. The differences were statistically significant for two of the three chief residents, five of nine residents overall, and all four students. This preliminary validation of a prototype expert system is encouraging for the prospect of a computerized decision support system that can help surgeons make initial definitive management plans for patients with major trauma.

Metrics

14 Record Views
16 citations in Scopus

Details

UN Sustainable Development Goals (SDGs)

This publication has contributed to the advancement of the following goals:

#3 Good Health and Well-Being

InCites Highlights

Data related to this publication, from InCites Benchmarking & Analytics tool:

Collaboration types
Domestic collaboration
Web of Science research areas
Critical Care Medicine
Surgery
Logo image