Risk prediction of osteoporosis for postmenopausal women using machine learning methods

Abstract

Osteoporosis is a major public health concern worldwide. In particular, osteoporosis is common in postmenopausal women but is asymptomatic until a fracture occurs. A number of clinical decision tools for osteoporosis risk assessment have been developed to select postmenopausal women for the measurement of bone mineral density. We developed and validated machine learning models with the aim of more accurately identifying the risk of osteoporosis in postmenopausal women compared to the ability of conventional clinical decision tools.We collected medical records from Korean postmenopausal women based on the Korea National Health and Nutrition Examination Surveys (KNHANES V-1) conducted in 2010. The training data set was used to construct models based on popular machine learning algorithms such as support vector machines (SVM), random forests, artificial neural networks (ANN), and logistic regression (LR) based on simple surveys. The machine learning models were optimized using 10-fold cross validation and were compared to four conventional clinical decision tools: osteoporosis self-assessment tool (OST), osteoporosis risk assessment instrument (ORAI), simple calculated osteoporosis risk estimation (SCORE), and osteoporosis index of risk (OSIRIS). The internal validation set was used to assess the performance of the models for predicting osteoporosis risk using accuracy and area under the curve (AUC) of the receiver operating characteristic. External validation was also performed using the KNHANES V-2 conducted in 2011 to evaluate the models.SVM had significantly better AUC than ANN, LR, OST, ORAI, SCORE, and OSIRIS for the training set. The validation on the internal validation set showed that SVM predicted osteoporosis risk with an AUC of 0.827, accuracy of 76.7%, sensitivity of 77.8%, and specificity of 76.0% at total hip, femoral neck, or lumbar spine. In the

external validation, SVM predicted osteoporosis risk with an AUC of 0.833, accuracy of 76.5%, sensitivity of 70.3%, and specificity of 80.3% at any site. The significant factors selected by SVM were age, height, weight, body mass index, duration of menopause, duration of breast feeding, estrogen therapy, hyperlipidemia, hypertension, osteoarthritis, and diabetes mellitus.Considering various predictors associated with low bone density, the machine learning methods may be effective tools for identifying postmenopausal women at high risk for osteoporosis.