A Methodology for Customizing Clinical Tests for Esophageal Cancer based on Patient Preferences

作者: Kalyan Guin , Sourangshu Bhattacharya , Asis Roy

DOI:

关键词:

摘要: Tests for Esophageal cancer can be expensive, uncomfortable and have side effects. For many patients, we predict non-existence of disease with 100% certainty, just using demographics, lifestyle, medical history information. Our objective is to devise a general methodology customizing tests user preferences so that expensive or avoided. We propose use classifiers trained from electronic health records (EHR) selection tests. The key idea design false normal rates, possibly at the cost higher abnormals. compare Naive Bayes classification (NB), Random Forests (RF), Support Vector Machines (SVM) Logistic Regression (LR), find kernel regression most suitable task. an algorithm finding best probability threshold LR, based on test set accuracy. Using proposed algorithm, describe schemes selecting tests, which appear as features in automatic costs discomfort users. our EHRs collected more than 3000 part project carried out by reputed hospital Mumbai, India. Kernel SVM LR polynomial degree 3, yields accuracy 99.8% sensitivity 100%, without MP features, i.e. only clinical demonstrate two case studies, one other "discomfort" values compute sets corresponding lowest abnormals each criterion described above, exhaustive enumeration 15 turn different, substantiating claim customize preferences.

参考文章(29)
Pedro Henriques Abreu, Hugo Amaro, Daniel Castro Silva, Penousal Machado, Miguel Henriques Abreu, Noémia Afonso, António Dourado, Overall Survival Prediction for Women Breast Cancer Using Ensemble Methods and Incomplete Clinical Data Springer, Cham. pp. 1366- 1369 ,(2014) , 10.1007/978-3-319-00846-2_338
Harry Zhang, The Optimality of Naive Bayes. the florida ai research society. pp. 562- 567 ,(2004)
James P. Egan, Signal detection theory and ROC analysis Academic Press. ,(1975)
Bernhard Schölkopf, Alexander J. Smola, Learning with Kernels The MIT Press. pp. 626- ,(2018) , 10.7551/MITPRESS/4175.001.0001
Mai Shouman, Tim Turner, Rob Stocker, Using data mining techniques in heart disease diagnosis and treatment 2012 Japan-Egypt Conference on Electronics, Communications and Computers. pp. 173- 177 ,(2012) , 10.1109/JEC-ECC.2012.6186978
Zehra Aysun Altikardes, Hasan Erdal, A. Fevzi Baba, Hakan Tezcan, Ali Serdar Fak, Hayriye Korkmaz, A study to classify Non-Dipper/Dipper blood pressure pattern of type 2 diabetes mellitus patients without Holter device Computer Applications and Information Systems (WCCAIS), 2014 World Congress on. pp. 1- 5 ,(2014) , 10.1109/WCCAIS.2014.6916555
Dheeraj Raju, Xiaogang Su, Patricia A. Patrician, Lori A. Loan, Mary S. McCarthy, Exploring factors associated with pressure ulcers: a data mining approach. International Journal of Nursing Studies. ,vol. 52, pp. 102- 111 ,(2015) , 10.1016/J.IJNURSTU.2014.08.002
Peter B. Jensen, Lars J. Jensen, Søren Brunak, Mining electronic health records: towards better research applications and clinical care Nature Reviews Genetics. ,vol. 13, pp. 395- 405 ,(2012) , 10.1038/NRG3208
Jionglin Wu, Jason Roy, Walter F. Stewart, Prediction Modeling Using EHR Data Medical Care. ,vol. 48, pp. S106- S113 ,(2010) , 10.1097/MLR.0B013E3181DE9E17
Brain Leke-Betechuoh, Tshilidzi Marwala, Taryn Tim, Monica Lagazio, Prediction of HIV Status from Demographic Data Using Neural Networks systems, man and cybernetics. ,vol. 3, pp. 2339- 2344 ,(2006) , 10.1109/ICSMC.2006.385212