Abstract—An intrinsic disease where blood clots form in a deep vein in the body is known as Deep Venous Thrombosis (DVT). Since DVT has a high mortality rate, predicting it early is important. Decision trees are simple and practical prediction models but often suffer from excessive complexity and can even be incomprehensible. Here a genetic algorithm is used to construct decision trees of increased accuracy and efficiency compared to those constructed by the conventional ID3 or C4.5 decision tree building algorithms. Experimental results on two DVT datasets are presented and discussed.
Index Terms—Decision Trees, DVT and Genetic Algorithm
C. Nwosisi is with the Computer Science Department, Pace University, White Plains, NY USA and Department of Thoracic and Cardiovascular Surgery, Montefiore Medical Center, Bronx, NY USA (e-mail:cnwosisi@montefiore.org).
S. Cha and C. C. Tappert are with the Computer Science Department, Pace University, White Plains, NY USA. (e-mail: scha@pace.edu;ctappert@pace.edu).
Y. An is with the Computer Science Department, Farleigh Dickenson University, NJ USA (e-mail: yoojung@fdu.edu).
E. Lipsitz is with the Department of Thoracic and Cardiovascular Surgery, Montefiore Medical Center, Bronx NY USA. (e-mail:elipsitz@montefiore.org).
Cite: Christopher Nwosisi, Sung-Hyuk Cha, Yoo Jung An, Charles C. Tappert and Evan Lipsitz, "Predicting Deep Venous Thrombosis Using Binary Decision Trees," International Journal of Engineering and Technology vol. 3, no. 5, pp. 467-472, 2011.
Copyright © 2008-2025. International Journal of Engineering and Technology. All rights reserved.
E-mail: ijet_Editor@126.com