J Multidiscip Healthc. 2021 Sep 11;14:2477-2485. doi: 10.2147/JMDH.S325179. eCollection 2021.
A Deep Learning Model to Predict Knee Osteoarthritis Based on Nonimage Longitudinal Medical Record.
Journal of multidisciplinary healthcare
Dina Nur Anggraini Ningrum, Woon-Man Kung, I-Shiang Tzeng, Sheng-Po Yuan, Chieh-Chen Wu, Chu-Ya Huang, Muhammad Solihuddin Muhtar, Phung-Anh Nguyen, Jack Yu-Chuan Li, Yao-Chin Wang
Affiliations
Affiliations
- Graduate Institute of Biomedical Informatics, College of Medical Science and Technology, Taipei Medical University, Taipei, Taiwan.
- International Center for Health Information Technology (ICHIT), Taipei Medical University, Taipei, Taiwan.
- Public Health Department, Faculty of Sport Science, Universitas Negeri Semarang, Semarang City, Indonesia.
- Department of Exercise and Health Promotion, College of Kinesiology and Health, Chinese Culture University, Taipei, Taiwan.
- Department of Research, Taipei Tzu Chi Hospital, Buddhist Tzu Chi Medical Foundation, New Taipei City, Taiwan.
- Department of Statistics, National Taipei University, Taipei, Taiwan.
- Department of Otorhinolaryngology, Shuang-Ho Hospital, Taipei Medical University, New Taipei City, Taiwan.
- Taiwan College of Healthcare Executives, Taipei, Taiwan.
- Department of Healthcare Information and Management, Ming Chuan University, Taoyuan, Taiwan.
- Department of Dermatology, Wan Fang Hospital, Taipei Medical University, Taipei, Taiwan.
- TMU Research Center of Cancer Translational Medicine, Taipei Medical University, Taipei, Taiwan.
- Graduate Institute of Injury Prevention and Control, College of Public Health, Taipei Medical University, Taipei, Taiwan.
- Department of Emergency Medicine, Min-Sheng General Hospital, Taoyuan, Taiwan.
PMID: 34539180
PMCID: PMC8445097 DOI: 10.2147/JMDH.S325179
Abstract
PURPOSE: 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.
© 2021 Ningrum et al.
Keywords: artificial intelligence; clinical decision support system; medical informatics application; precision medicine
Conflict of interest statement
The authors report no conflicts of interest in this work.
References
- J Multidiscip Healthc. 2021 Apr 21;14:877-885 - PubMed
- Physiother Can. 2014 Winter;66(1):91-107 - PubMed
- Evid Based Complement Alternat Med. 2016;2016:7242478 - PubMed
- Nat Rev Rheumatol. 2016 Nov;12(11):632-644 - PubMed
- Rheum Dis Clin North Am. 2008 Aug;34(3):515-29 - PubMed
- Arthritis Rheum. 1998 Aug;41(8):1343-55 - PubMed
- J Am Med Inform Assoc. 2017 Jan;24(1):198-208 - PubMed
- BMJ Open. 2015 Mar 17;5(3):e007825 - PubMed
- J Med Econ. 2020 Apr;23(4):386-393 - PubMed
- Insights Imaging. 2018 Aug;9(4):611-629 - PubMed
- J Athl Train. 2017 Jun 2;52(6):497-506 - PubMed
- Osteoarthritis Cartilage. 2017 Dec;25(12):2014-2021 - PubMed
- Lancet. 2016 Oct 8;388(10053):1545-1602 - PubMed
- Stroke Vasc Neurol. 2017 Jun 21;2(4):230-243 - PubMed
- Magn Reson Med. 2013 Aug;70(2):568-75 - PubMed
- J Am Med Inform Assoc. 2015 Jul;22(4):896-9 - PubMed
- Clin Geriatr Med. 2010 Aug;26(3):355-69 - PubMed
- PLoS One. 2017 Apr 4;12(4):e0174944 - PubMed
- J Magn Reson Imaging. 2018 Jan;47(1):78-90 - PubMed
- BMC Musculoskelet Disord. 2020 Aug 10;21(1):531 - PubMed
- JAMA Dermatol. 2019 Nov 1;155(11):1277-1283 - PubMed
- Medicine (Baltimore). 2018 Aug;97(31):e11749 - PubMed
- Osteoarthritis Cartilage. 2015 Apr;23(4):507-15 - PubMed
- Sci Rep. 2019 Dec 27;9(1):20038 - PubMed
- Ann R Coll Surg Engl. 2004 Sep;86(5):334-8 - PubMed
- Plant Phenomics. 2020 Apr 9;2020:4152816 - PubMed
- Stud Health Technol Inform. 2019 Aug 21;264:438-441 - PubMed
- Rheumatology (Oxford). 2008 Jan;47(1):88-91 - PubMed
Publication Types