Journal of Multidisciplinary Healthcare (Sep 2021)
A Deep Learning Model to Predict Knee Osteoarthritis Based on Nonimage Longitudinal Medical Record
Abstract
Dina Nur Anggraini Ningrum,1– 3 Woon-Man Kung,4 I-Shiang Tzeng,4– 6 Sheng-Po Yuan,1,7 Chieh-Chen Wu,4 Chu-Ya Huang,8 Muhammad Solihuddin Muhtar,2 Phung-Anh Nguyen,2,9 Jack Yu-Chuan Li,1,2,10,11 Yao-Chin Wang12,13 1Graduate Institute of Biomedical Informatics, College of Medical Science and Technology, Taipei Medical University, Taipei, Taiwan; 2International Center for Health Information Technology (ICHIT), Taipei Medical University, Taipei, Taiwan; 3Public Health Department, Faculty of Sport Science, Universitas Negeri Semarang, Semarang City, Indonesia; 4Department of Exercise and Health Promotion, College of Kinesiology and Health, Chinese Culture University, Taipei, Taiwan; 5Department of Research, Taipei Tzu Chi Hospital, Buddhist Tzu Chi Medical Foundation, New Taipei City, Taiwan; 6Department of Statistics, National Taipei University, Taipei, Taiwan; 7Department of Otorhinolaryngology, Shuang-Ho Hospital, Taipei Medical University, New Taipei City, Taiwan; 8Taiwan College of Healthcare Executives, Taipei, Taiwan; 9Department of Healthcare Information and Management, Ming Chuan University, Taoyuan, Taiwan; 10Department of Dermatology, Wan Fang Hospital, Taipei Medical University, Taipei, Taiwan; 11TMU Research Center of Cancer Translational Medicine, Taipei Medical University, Taipei, Taiwan; 12Graduate Institute of Injury Prevention and Control, College of Public Health, Taipei Medical University, Taipei, Taiwan; 13Department of Emergency Medicine, Min-Sheng General Hospital, Taoyuan, TaiwanCorrespondence: Jack Yu-Chuan Li Email [email protected]; [email protected] Wang Email [email protected]: To develop deep learning model (Deep-KOA) that can predict the risk of knee osteoarthritis (KOA) within the next year by using the previous three years nonimage-based electronic medical record (EMR) data.Patients and Methods: We randomly selected information of two million patients from the Taiwan National Health Insurance Research Database (NHIRD) from January 1, 1999 to December 31, 2013. During the study period, 132,594 patients were diagnosed with KOA, while 1,068,464 patients without KOA were chosen randomly as control. We constructed a feature matrix by using the three-year history of sequential diagnoses, drug prescriptions, age, and sex. Deep learning methods of convolutional neural network (CNN) and artificial neural network (ANN) were used together to develop a risk prediction model. We used the area under the receiver operating characteristic (AUROC), sensitivity, specificity, and precision to evaluate the performance of Deep-KOA. Then, we explored the important features using stepwise feature selection.Results: This study included 132,594 KOA patients, 83,111 females (62.68%), 49,483 males (37.32%), mean age 64.2 years, and 1,068,464 non-KOA patients, 545,902 females (51.09%), 522,562 males (48.91%), mean age 51.00 years. The Deep-KOA achieved an overall AUROC, sensitivity, specificity, and precision of 0.97, 0.89, 0.93, and 0.80 respectively. The discriminative analysis of Deep-KOA showed important features from several diseases such as disorders of the eye and adnexa, acute respiratory infection, other metabolic and immunity disorders, and diseases of the musculoskeletal and connective tissue. Age and sex were not found as the most discriminative features, with AUROC of 0.9593 (− 0.76% loss) and 0.9644 (− 0.25% loss) respectively. Whereas medications including antacid, cough suppressant, and expectorants were identified as discriminative features.Conclusion: Deep-KOA was developed to predict the risk of KOA within one year earlier, which may provide clues for clinical decision support systems to target patients with high risk of KOA to get precision prevention program.Keywords: artificial intelligence, clinical decision support system, medical informatics application, precision medicine
