Designing a Decision Support System for Diagnosing Pulmonary Injuries in Chemical Victims

Document Type : Original Research

Authors

1 Health Information Management Department, School of Allied Medical Sciences, Tehran University of Medical Sciences, Tehran, Iran

2 Faculty of Health Management and Information Sciences, Iran University of Medical Sciences, Tehran, Iran

3 Chemical Injuries Research Center, Baqiyatallah University of Medical Sciences, Tehran, Iran

Abstract

Aims: Chronic Obstructive Pulmonary Disease (COPD) is the most common effect of getting poisoned by Mustard Gas. It is challenging for physicians to make a differential diagnosis between COPD and Asthma. Therefore, some criteria are prepared in different guidelines to facilitate differentiation between COPD and other similar diseases. To improve the guidelines’ acceptance among the potential users, decision support systems are applied in different areas. One of the modeling methods used in such systems are the qualitative multi-attribute models. The ultimate objective of this research was to design a qualitative multi-attribute model that provides differential diagnosis for COPD.

Methods: Firstly, effective attributes were extracted from the guidelines and were approved by specialists. Secondly, the qualitative multi-attribute model was implemented. The system was evaluated using useful information from 50 patients who had registered in the Baqiyatallah hospital. Evaluations have been done using sensitivity and specificity.

Results: The system’s output was compared with the physician diagnosis and the obtained results showed that the sensitivity and specificity were 92.3% and 96% respectively. It clearly showed that the system had accepted functionality to diagnose COPD.

Conclusion: The suggested methodology was a useful solution for data analysis and modeling in medical decision making fields. It also had an appropriate performance and could be effective and helpful for physicians.

Keywords

Journal of Military Medicine
Volume 16, Issue 3 - Serial Number 57
November and December 2014
Pages 161-167

Files

Share

How to cite

Statistics