Cemil Colak1, Esra Karaman2, M Gokhan Turtay2. 1. Inonu University, Faculty of Medicine, Department of Biostatistics and Medical Informatics, Malatya, Turkey. Electronic address: cemilcolak@yahoo.com. 2. Inonu University, Faculty of Medicine, Department of Emergency Medicine, Malatya, Turkey.
Abstract
OBJECTIVE: Stroke is a prominent life-threatening disease in the world. The current study was performed to predict the outcome of stroke using knowledge discovery process (KDP) methods, artificial neural networks (ANN) and support vector machine (SVM) models. MATERIALS AND METHODS: The records of 297 (130 sick and 167 healthy) individuals were acquired from the databases of the department of emergency medicine. Nine predictors (coronary artery disease, diabetes mellitus, hypertension, history of cerebrovascular disease, atrial fibrillation, smoking, the findings of carotid Doppler ultrasonography [normal, plaque, plaque+stenosis≥50%], the levels of cholesterol and C-reactive protein) were used for predicting the stroke. Feature selection based on the Cramer's V test was carried out for reducing the predictors. Multilayer perceptron (MLP) ANN and SVM with radial basis function (RBF) kernel were used for the prediction based on the selected predictors. RESULTS: The accuracy values were 81.82% for ANN and 80.38% for SVM in the training dataset (n=209), and 85.9% for ANN and 84.62% for SVM in the testing dataset (n=78), respectively. ANN and SVM models yielded area under curve (AUC) values of 0.905 and 0.899 in the training dataset, and 0.928 and 0.91 in the testing dataset, consecutively. CONCLUSION: The findings of the current study pointed out that ANN had more predictive performance when compared with SVM in predicting stroke. The proposed ANN model would be useful when making clinical decisions regarding stroke.
OBJECTIVE:Stroke is a prominent life-threatening disease in the world. The current study was performed to predict the outcome of stroke using knowledge discovery process (KDP) methods, artificial neural networks (ANN) and support vector machine (SVM) models. MATERIALS AND METHODS: The records of 297 (130 sick and 167 healthy) individuals were acquired from the databases of the department of emergency medicine. Nine predictors (coronary artery disease, diabetes mellitus, hypertension, history of cerebrovascular disease, atrial fibrillation, smoking, the findings of carotid Doppler ultrasonography [normal, plaque, plaque+stenosis≥50%], the levels of cholesterol and C-reactive protein) were used for predicting the stroke. Feature selection based on the Cramer's V test was carried out for reducing the predictors. Multilayer perceptron (MLP) ANN and SVM with radial basis function (RBF) kernel were used for the prediction based on the selected predictors. RESULTS: The accuracy values were 81.82% for ANN and 80.38% for SVM in the training dataset (n=209), and 85.9% for ANN and 84.62% for SVM in the testing dataset (n=78), respectively. ANN and SVM models yielded area under curve (AUC) values of 0.905 and 0.899 in the training dataset, and 0.928 and 0.91 in the testing dataset, consecutively. CONCLUSION: The findings of the current study pointed out that ANN had more predictive performance when compared with SVM in predicting stroke. The proposed ANN model would be useful when making clinical decisions regarding stroke.
Authors: Luca Saba; Skandha S Sanagala; Suneet K Gupta; Vijaya K Koppula; Amer M Johri; Narendra N Khanna; Sophie Mavrogeni; John R Laird; Gyan Pareek; Martin Miner; Petros P Sfikakis; Athanasios Protogerou; Durga P Misra; Vikas Agarwal; Aditya M Sharma; Vijay Viswanathan; Vijay S Rathore; Monika Turk; Raghu Kolluri; Klaudija Viskovic; Elisa Cuadrado-Godia; George D Kitas; Neeraj Sharma; Andrew Nicolaides; Jasjit S Suri Journal: Ann Transl Med Date: 2021-07
Authors: Yizhao Ni; Kathleen Alwell; Charles J Moomaw; Daniel Woo; Opeolu Adeoye; Matthew L Flaherty; Simona Ferioli; Jason Mackey; Felipe De Los Rios La Rosa; Sharyl Martini; Pooja Khatri; Dawn Kleindorfer; Brett M Kissela Journal: PLoS One Date: 2018-02-14 Impact factor: 3.240
Authors: Yiqing Zhao; Sunyang Fu; Suzette J Bielinski; Paul A Decker; Alanna M Chamberlain; Veronique L Roger; Hongfang Liu; Nicholas B Larson Journal: J Med Internet Res Date: 2021-03-08 Impact factor: 5.428