TY - JOUR

T1 - Derivation and validation of a bayesian network to predict pretest probability of venous thromboembolism

AU - Kline, Jeffrey A.

AU - Novobilski, Andrew J.

AU - Kabrhel, Christopher

AU - Richman, Peter B.

AU - Courtney, D. Mark

PY - 2005/3

Y1 - 2005/3

N2 - Study objective: A Bayesian network can estimate a numeric pretest probability of venous thromboembolism on the basis of values of clinical variables. We determine the accuracy with which a Bayesian network can identify patients with a low pretest probability of venous thromboembolism, defined as less than or equal to 2%. Methods: Using commercial software, we derived a population of Bayesian networks from 25 input variables collected on 3,145 emergency department (ED) patients with suspected venous thromboembolism who underwent standardized testing, including pulmonary vascular imaging, and 90-day follow-up (11.0% of patients were venous thromboembolism positive). The best-fit Bayesian network was selected using a genetic algorithm. The selected Bayesian network was tested in a validation population of 1,423 ED patients prospectively evaluated for venous thromboembolism, including 90-day follow-up (8.0% were venous thromboembolism positive). The Bayesian network probability estimate was normalized to a score of 0% to 100%. Results: Of 1,423 patients in the validation cohort, 711 (50%; 95% confidence interval [CI] 47% to 52%) had a score less than or equal to 2% that predicted a low pretest probability. Of these 711 patients, 700 (98.5%; 95% CI 97.2% to 99.2%) had no venous thromboembolism at follow-up. Conclusion: A Bayesian network, derived and independently validated in ED populations, identified half of the validation cohort as having a low pretest probability (≤2%); 98.5% of these patients were correctly classified by the network.

AB - Study objective: A Bayesian network can estimate a numeric pretest probability of venous thromboembolism on the basis of values of clinical variables. We determine the accuracy with which a Bayesian network can identify patients with a low pretest probability of venous thromboembolism, defined as less than or equal to 2%. Methods: Using commercial software, we derived a population of Bayesian networks from 25 input variables collected on 3,145 emergency department (ED) patients with suspected venous thromboembolism who underwent standardized testing, including pulmonary vascular imaging, and 90-day follow-up (11.0% of patients were venous thromboembolism positive). The best-fit Bayesian network was selected using a genetic algorithm. The selected Bayesian network was tested in a validation population of 1,423 ED patients prospectively evaluated for venous thromboembolism, including 90-day follow-up (8.0% were venous thromboembolism positive). The Bayesian network probability estimate was normalized to a score of 0% to 100%. Results: Of 1,423 patients in the validation cohort, 711 (50%; 95% confidence interval [CI] 47% to 52%) had a score less than or equal to 2% that predicted a low pretest probability. Of these 711 patients, 700 (98.5%; 95% CI 97.2% to 99.2%) had no venous thromboembolism at follow-up. Conclusion: A Bayesian network, derived and independently validated in ED populations, identified half of the validation cohort as having a low pretest probability (≤2%); 98.5% of these patients were correctly classified by the network.

UR - http://www.scopus.com/inward/record.url?scp=13844311801&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=13844311801&partnerID=8YFLogxK

U2 - 10.1016/j.annemergmed.2004.08.036

DO - 10.1016/j.annemergmed.2004.08.036

M3 - Article

C2 - 15726051

AN - SCOPUS:13844311801

SN - 0196-0644

VL - 45

SP - 282

EP - 290

JO - Annals of emergency medicine

JF - Annals of emergency medicine

IS - 3

ER -