Use of genetic programming to diagnose venous thromboembolism in the emergency department
- 94 Downloads
Pulmonary thromboembolism as a cause of respiratory complaints is frequently undiagnosed and requires expensive imaging modalities to diagnose. The objective of this study was to determine if genetic programming could be used to classify patients as having or not having pulmonary thromboembolism using exhaled ventilatory and gas indices as genetic material. Using a custom-built exhaled oxygen and carbon dioxide analyzer; exhaled flows, volumes, and gas partial pressures were recorded from patients for a series of deep exhalation and 30 s tidal volume breathing. A diagnosis of pulmonary embolism was made by contrast-enhanced computerized tomography angiography of the chest and indirect venography supplemented by 90-day follow-up. Genetic programming developed a series of genomes comprising genes of exhaled CO2, O2, flow, volume, vital signs, and patient demographics from these data and their predictions were compared to the radiological results. We found that 24 of 178 patients had pulmonary embolism. The best genome consisted of four genes: the minimum flow rate during the third 30 s period of tidal breathing, the average peak exhaled CO2 during the first 30 s period of tidal breathing, the average peak of the exhaled O2 during the first 30 s period of tidal breathing, and the average peak exhaled CO2 during the fourth period of tidal breathing, which immediately followed a deep exhalation. This had 100% sensitivity and 91% specificity on the construction population and 100% and 82%, respectively when tested on the separate validation population. Genetic programming using only data obtained from exhaled breaths was very accurate in classifying patients with suspected pulmonary thromboembolism.
KeywordsGenetic programming Pulmonary embolism Venous thromboembolic disease Capnometry Oximetry
Milo Engoren, MD has no financial involvement or relationship to any product in the manuscript. Jeffrey A. Kline, MD, was issued an US utility patent on the device used for data collection.
- 2.Becker, L.A., Seshadri, M.: Comprehensibility and Overfitting Avoidance in Genetic Programming for Technical Trading Rules. http://www.cs.bham.ac.uk/~wbl/biblio/gp-html/LeeABecker.html February 19 (2004)
- 9.Jacob, C.: Illustrating Evolutionary Computation with Mathematica. Academic Press, San Francisco, CA (2001)Google Scholar
- 17.Liu, Y., Khoshgoftaar, T.M.: Reducing overfitting in genetic programming models for software quality classification. In Proceedings of the Eighth IEEE Symposium on International High Assurance Systems Engineering, pp. 54–65 (2004)Google Scholar
- 18.Loubeyre, P., Revel, D., Douek, P., Delignette, A., Baldy, C., Genin, G., Amiel, M.: Dynamic contrast-enhanced MR angiography of pulmonary embolism: comparison with pulmonary angiography. AJR Am. J. Roentgenol. 162, 1035–1039 (1994)Google Scholar
- 19.No authors listed: Value of the ventilation/perfusion scan in acute pulmonary embolism. Results of the prospective investigation of pulmonary embolism diagnosis (PIOPED). The PIOPED Investigators. JAMA 263, 2753–2759 (1990)Google Scholar
- 23.Pheby, D.F., Codling, B.W.: Pulmonary embolism at autopsy in a normal population: implications for air traffic fatalities. Aviat. Space Environ. Med. 73, 1208–1214 (2002)Google Scholar
- 24.Qanadli, S.D., Hajjam, M.E., Mesurolle, B., Barre, O., Bruckert, F., Joseph, T., Mignon, F., Viellard-Baron, A., Dubourg, O., Lacombe, P.: Pulmonary embolism detection: prospective evaluation of dual-section helical CT versus selective pulmonary arteriography in 157 patients. Radiology 217, 447–455 (2000)Google Scholar
- 26.Richman, P.B., Wood, J., Kasper, D.M., Collins, J.M., Petri, R.W., Field, A.G., Cowles, D.N., Kline, J.A.: Contribution of indirect computed tomography venography to computed tomography angiography of the chest for the diagnosis of thromboembolic disease in two United States emergency departments. J. Thromb. Haemost 1, 652–657 (2003)CrossRefGoogle Scholar
- 28.Turner, D.A.: An intuitive approach to receiver operating characteristic curve analysis. J. Nucl. Med. 19, 213–20 (1978)Google Scholar