Development of Machine Learning Models for Prediction of Osteoporosis from Clinical Health Examination Data
Open Access
- 18 July 2021
- journal article
- research article
- Published by MDPI AG in International Journal of Environmental Research and Public Health
- Vol. 18 (14) , 7635
Abstract
Osteoporosis is treatable but often overlooked in clinical practice. We aimed to construct prediction models with machine learning algorithms to serve as screening tools for osteoporosis in adults over fifty years old. Additionally, we also compared the performance of newly developed models with traditional prediction models. Data were acquired from community-dwelling participants enrolled in health checkup programs at a medical center in Taiwan. A total of 3053 men and 2929 women were included. Models were constructed for men and women separately with artificial neural network (ANN), support vector machine (SVM), random forest (RF), k-nearest neighbor (KNN), and logistic regression (LoR) to predict the presence of osteoporosis. Area under receiver operating characteristic curve (AUROC) was used to compare the performance of the models. We achieved AUROC of 0.837, 0.840, 0.843, 0.821, 0.827 in men, and 0.781, 0.807, 0.811, 0.767, 0.772 in women, for ANN, SVM, RF, KNN, and LoR models, respectively. The ANN, SVM, RF, and LoR models in men, and the ANN, SVM, and RF models in women performed significantly better than the traditional Osteoporosis Self-Assessment Tool for Asians (OSTA) model. We have demonstrated that machine learning algorithms improve the performance of screening for osteoporosis. By incorporating the models in clinical practice, patients could potentially benefit from earlier diagnosis and treatment of osteoporosis.Keywords
This publication has 39 references indexed in Scilit:
- Prevalence and trends in low femur bone density among older US adults: NHANES 2005–2006 compared with NHANES IIIJournal of Bone and Mineral Research, 2020
- Machine Learning in MedicineCirculation, 2015
- Bone Health and OsteoporosisEndocrinology and Metabolism Clinics of North America, 2015
- Osteoporosis risk prediction using machine learning and conventional methods2013
- Weighted Youden index and its two-independent-sample comparison based on weighted sensitivity and specificityChinese Medical Journal, 2013
- The Relationship Among Hypertension, Antihypertensive Medications, and Osteoporosis: A Narrative ReviewCalcified Tissue International, 2012
- Summary ROC curve based on a weighted Youden index for selecting an optimal cutpoint in meta‐analysis of diagnostic accuracyStatistics in Medicine, 2010
- Youden Index and the optimal threshold for markers with mass at zeroStatistics in Medicine, 2007
- Osteoporosis Prevention, Diagnosis, and TherapyJAMA, 2001
- Basic principles of ROC analysisSeminars in Nuclear Medicine, 1978