The goal of this project is to optimize the clinical management of a significant acute clinical problem with a high variation in outcome between specialized centers and community hospitals, namely the initial definitive management of acutely injured patients after resuscitation and stabilization. The objective is to rigorously evaluate a recently developed artificial intelligence decision aid to improve the initial definitive management of patients with injuries, specifically to evaluate the recommendations of an expert system that makes recommendations for the initial definitive management of patients, currently confined to those with stab wounds and gunshot wounds of the chest and abdomen.
The specific aims of this pilot study are to show that the program makes recommendations comparable to actual care (face and criterion-based validity), to show that patients whose care is the same as the recommendations of the program are unlikely to have bad outcomes from errors in judgement (predictive validity), to show that the program can be changed to reflect changes in the standards of care, to show that it is practical to use the program during the actual care of the patient, and to show that using the program does improve the care plan for the patient. The evaluation will be done using 200 cases abstracted retrospectively and 100 cases tested prospectively in a trauma center. The recommendations will be evaluated using the best professional judgment of both local trauma surgeons and national trauma experts. The long term objective is to expand the expertise of the program to generate recommendations for the initial definitive management of multiple trauma for adult patients with penetrating or blunt injuries to any part of the body, specifically stab wounds, gunshot wounds, vehicular accidents, falls, or beatings. Such programs could be information resources for practice guidelines, quality assurance, education, intelligent data collection and other research. Meeting the standards of this initial evaluation would justify dissemination, continued refinement, and expansion of this computer-based decision aid that provides guidelines for the initial definitive management of injured patients in a format appropriate for clinical care, education, control of liability, and review of the quality of care.

Agency
National Institute of Health (NIH)
Institute
Agency for Healthcare Research and Quality (AHRQ)
Type
Research Project (R01)
Project #
5R01HS006740-02
Application #
3372435
Study Section
Special Emphasis Panel (HSDG)
Project Start
1991-04-01
Project End
1994-03-31
Budget Start
1992-04-01
Budget End
1993-03-31
Support Year
2
Fiscal Year
1992
Total Cost
Indirect Cost
Name
Allegheny University of Health Sciences
Department
Type
Schools of Medicine
DUNS #
City
Philadelphia
State
PA
Country
United States
Zip Code
19129
Clarke, J R; Spejewski, B; Gertner, A S et al. (2000) An objective analysis of process errors in trauma resuscitations. Acad Emerg Med 7:1303-10
Gertner, A S; Webber, B L; Clarke, J R et al. (1997) On-line quality [corrected] assurance in the initial definitive management of multiple trauma: evaluating system potential. Artif Intell Med 9:261-82
Clarke, J R; Webber, B L; Gertner, A et al. (1994) On-line decision support for emergency trauma management. Proc Annu Symp Comput Appl Med Care :1028