Research on penetrating trauma has shown that the early administration of expert care to victims would considerably reduce the number of deaths due to these injuries. Assessment of penetrating trauma requires knowledge of the relationships among human anatomy, physiology and physical manifestations of injury. Tools or knowledge aids that reinforce understanding of these relationships for a patient presenting with penetrating injury may be of value in enhancing patient care. A computer program that integrates anatomic and diagnostic reasoning in assessing a patient could serve as such a tool or knowledge-aid. To address this issue, we have proposed a method for computer-assisted diagnosis of penetrating trauma to the chest and abdomen that assesses anatomical structure involvement in injury based on surface wound location information, and uses this information to drive diagnostic reasoning about the consequences of injury. The method takes into account uncertainty about the extent of damage caused by a mechanism of injury and variability in information available about patient signs, symptoms, and test results. The goal of this proposal is to test the hypothesis that this computer-based method can provide value both as a diagnostic tool, and as an educational one. To assess this, we will conduct a study that retrospectively evaluates a large number of penetrating trauma cases for which the diagnoses are already known, and measure the system's performance in evaluating these cases. We will also examine the system's performance in comparison to physicians at different stages of training, to assess its potential in providing educational value.
| Ahmed, Bilal A; Matheny, Michael E; Rice, Phillip L et al. (2009) A comparison of methods for assessing penetrating trauma on retrospective multi-center data. J Biomed Inform 42:308-16 |
| Ogunyemi, Omolola (2006) Methods for reasoning from geometry about anatomic structures injured by penetrating trauma. J Biomed Inform 39:389-400 |
| Matheny, Michael E; Ogunyemi, Omolola I; Rice, Phillip L et al. (2005) Evaluating the discriminatory power of a computer-based system for assessing penetrating trauma on retrospective multi-center data. AMIA Annu Symp Proc :500-4 |
