Preclinical Osteoporosis Screening Tool (POST): Development and validation of a machine learning-based model to predict osteoporosis risk in Hong Kong Chinese population
ABSTRACT
Background:
Identifying persons with a high risk of developing osteoporosis and preventing the occurrence of the first fracture is a healthcare priority. Most existing osteoporosis screening tools developed by traditional algorithms have high sensitivity but relatively low specificity.
Objective:
We aimed to develop a high-performance preclinical risk screening tool for osteoporosis by machine learning technology among Chinese population.
Methods:
Participants aged 45 years or above were enrolled from six clinics in three major districts of Hong Kong. The potential risk factors for osteoporosis were collected through a validated self-administered questionnaire. Bone mineral density was measured by the dual energy X-ray absorptiometry at the clinics, osteoporosis was defined as a T-score of -2.5 or lower. Four machine learning models including gradient boosting machine, support vector machine, naïve bayes, and logistic regression were constructed for the prediction of osteoporosis. The best-performing model was chosen as the final tool, named “Preclinical Osteoporosis Screening Tool (POST)”. Model performance was evaluated by area under the receiver operating characteristic curve (AUC) and other metrics.
Results:
Of 800 participants enrolled in this study, the prevalence of osteoporosis was 10.62%. The machine learning algorithm identified 15 significantly important predictors from the 113 potential risk factors. Seven variables were further selected based on their accessibility and convenience in daily self-assessment and healthcare practice, including age, gender, education level, decreased body height, body mass index, number of teeth lost, and the intake of vitamin D supplements, to construct the POST. The AUC of the POST was 0.86, the sensitivity, specificity and accuracy were all 0.83. The positive predictive value, negative predictive value and F1 score were 0.41, 0.98 and 0.56, respectively.
Conclusions:
The machine learning-based POST showed accurate discriminative capabilities for the prediction of osteoporosis and might be useful to guide population-based preclinical screening of osteoporosis and clinical decision-making. Clinical Trial: NA
Citation
Request queued. Please wait while the file is being generated. It may take some time.
Copyright
© The authors. All rights reserved. This is a privileged document currently under peer-review/community review (or an accepted/rejected manuscript). Authors have provided JMIR Publications with an exclusive license to publish this preprint on it's website for review and ahead-of-print citation purposes only. While the final peer-reviewed paper may be licensed under a cc-by license on publication, at this stage authors and publisher expressively prohibit redistribution of this draft paper other than for review purposes.