Combining geometric and probabilistic reasoning for computer-based penetrating-trauma assessment.

OBJECTIVE To ascertain whether three-dimensional geometric and probabilistic reasoning methods can be successfully combined for computer-based assessment of conditions arising from ballistic penetrating trauma to the chest and abdomen. DESIGN The authors created a computer system (TraumaSCAN) that integrates three-dimensional geometric reasoning about anatomic likelihood of injury with probabilistic reasoning about injury consequences using Bayesian networks. Preliminary evaluation of TraumaSCAN was performed via a retrospective study testing performance of the system on data from 26 cases of actual gunshot wounds. MEASUREMENTS Areas under the receiver operating characteristics (ROC) curve were calculated for each condition modeled in TraumaSCAN that was present in the 26 cases. The comprehensiveness and relevance of the TraumaSCAN diagnosis for the 26 cases were used to assess the overall performance of the system. To test the ability of TraumaSCAN to handle limited findings, these measurements were calculated both with and without input of observed findings into the Bayesian network. RESULTS For the 11 conditions assessed, the worst area under the ROC curve with no observed findings input into the Bayesian network was 0.542 (95% CI, 0.146-0.937), the median was 0.883 (95% CI, 0.713-1.000), and the best was 1.00 (95% CI, 1.000-1.000). The worst area under the ROC curve with all observed findings input into the Bayesian network was 0.835 (95% CI, 0.602-1.000), the median was 0.941 (95% CI, 0.827-1.000), and the best was 0.992 (95% CI, 0.965-1.000). A comparison of the areas under the curve obtained with and without input of observed findings into the Bayesian network showed that there were significant differences for 2 of the 11 conditions assessed. CONCLUSION A computer-based method that combines geometric and probabilistic reasoning shows promise as a tool for assessing ballistic penetrating trauma to the chest and abdomen.

[1]  J A Reggia,et al.  Transferability of Medical Decision Support Systems Based on Bayesian Classification , 1983, Medical decision making : an international journal of the Society for Medical Decision Making.

[2]  Arthur W. Toga,et al.  A Probabilistic Atlas of the Human Brain: Theory and Rationale for Its Development The International Consortium for Brain Mapping (ICBM) , 1995, NeuroImage.

[3]  Bonnie Webber,et al.  Traumascan: assessing penetrating injury with abductive and geometric reasoning , 1999 .

[4]  R. D. Eisler,et al.  Casualty Assessments of Penetrating Wounds from Ballistic Trauma , 2001 .

[5]  M L Fackler,et al.  The wound profile: illustration of the missile-tissue interaction. , 1988, The Journal of trauma.

[6]  N Yoganandan,et al.  Dynamic analysis of penetrating trauma. , 1997, The Journal of trauma.

[7]  J R Beck,et al.  The use of relative operating characteristic (ROC) curves in test performance evaluation. , 1986, Archives of pathology & laboratory medicine.

[8]  R D Eisler,et al.  Simulation and modeling of penetrating wounds from small arms. , 1996, Studies in health technology and informatics.

[9]  F. T. de Dombal,et al.  Computer-Assisted Diagnosis of Abdominal Pain using “Estimates” Provided by Clinicians , 1972, British medical journal.

[10]  Judea Pearl,et al.  Probabilistic reasoning in intelligent systems - networks of plausible inference , 1991, Morgan Kaufmann series in representation and reasoning.

[11]  Joseph O'Rourke,et al.  Computational Geometry in C. , 1995 .

[12]  Norman I. Badler,et al.  TraumaSCAN: assessing penetrating trauma with geometric and probabilistic reasoning , 2000, AMIA.

[13]  A. Toga,et al.  High-Resolution Random Mesh Algorithms for Creating a Probabilistic 3D Surface Atlas of the Human Brain , 1996, NeuroImage.

[14]  J. Hanley,et al.  A method of comparing the areas under receiver operating characteristic curves derived from the same cases. , 1983, Radiology.

[15]  Omolola Ogunyemi,et al.  Probabilistic predictions of penetrating injury to anatomic structures , 1997, AMIA.

[16]  Richard E. Neapolitan,et al.  Probabilistic reasoning in expert systems - theory and algorithms , 2012 .

[17]  N M Rich,et al.  Three-dimensional computer graphic modeling of ballistic injuries. , 1988, The Journal of trauma.

[18]  Bonnie L. Webber,et al.  Progressive horizon planning-planning exploratory-corrective behavior , 1993, IEEE Trans. Syst. Man Cybern..

[19]  E S Berner,et al.  Relationships among performance scores of four diagnostic decision support systems. , 1996, Journal of the American Medical Informatics Association : JAMIA.

[20]  A. L. Baker,et al.  Performance of four computer-based diagnostic systems. , 1994, The New England journal of medicine.

[21]  J. G. West,et al.  Systems of trauma care. A study of two counties. , 1979, Archives of surgery.

[22]  J. Hanley,et al.  The meaning and use of the area under a receiver operating characteristic (ROC) curve. , 1982, Radiology.

[23]  J. Reggia,et al.  Abductive Inference Models for Diagnostic Problem-Solving , 1990, Symbolic Computation.

[24]  O Ogunyemi,et al.  Generating penetration path hypotheses for decision support in multiple trauma. , 1995, Proceedings. Symposium on Computer Applications in Medical Care.

[25]  Bonnie L. Webber,et al.  Flexible support for trauma management through goal-directed reasoning and planning , 1992, Artif. Intell. Medicine.

[26]  J. O´Rourke,et al.  Computational Geometry in C: Arrangements , 1998 .

[27]  Omolola Ogunyemi,et al.  Using Bayesian networks for diagnostic reasoning in penetrating injury assessment , 2000, Proceedings 13th IEEE Symposium on Computer-Based Medical Systems. CBMS 2000.