Osteoporosis Feature Selection and Risk Prediction Model by Machine Learning Using a Cross-Sectional Database
1
조회
0
다운로드
0
인용
0
참고문헌
초록
Background: The purpose of this study was to verify the accuracy and validity of using machine learning (ML) to select risk factors, to discriminate differences in feature selection by ML between men and women, and to develop predictive models for patients with osteoporosis in a big database. Methods: The data on 968 observed features from a total of 3,484 the Korea National Health and Nutrition Examination Survey participants were collected. To find preliminary features that were well-related to osteoporosis, logistic regression, random forest, gradient boosting, adaptive boosting, and support vector machine were used. Results: In osteoporosis feature selection by 5 ML models in this study, the most selected variables as risk factors in men and women were body mass index, monthly alcohol consumption, and dietary surveys. However, differences between men and women in osteoporosis feature selection by ML models were age, smoking, and blood glucose level. The receiver operating characteristic (ROC) analysis revealed that the area under the ROC curve for each ML model was not significantly different for either gender. Conclusions: ML performed a feature selection of osteoporosis, considering hidden differences between men and women. The present study considers the preprocessing of input data and the feature selection process as well as the ML technique to be important factors for the accuracy of the osteoporosis prediction model.
Abstract
Background: The purpose of this study was to verify the accuracy and validity of using machine learning (ML) to select risk factors, to discriminate differences in feature selection by ML between men and women, and to develop predictive models for patients with osteoporosis in a big database. Methods: The data on 968 observed features from a total of 3,484 the Korea National Health and Nutrition Examination Survey participants were collected. To find preliminary features that were well-related to osteoporosis, logistic regression, random forest, gradient boosting, adaptive boosting, and support vector machine were used. Results: In osteoporosis feature selection by 5 ML models in this study, the most selected variables as risk factors in men and women were body mass index, monthly alcohol consumption, and dietary surveys. However, differences between men and women in osteoporosis feature selection by ML models were age, smoking, and blood glucose level. The receiver operating characteristic (ROC) analysis revealed that the area under the ROC curve for each ML model was not significantly different for either gender. Conclusions: ML performed a feature selection of osteoporosis, considering hidden differences between men and women. The present study considers the preprocessing of input data and the feature selection process as well as the ML technique to be important factors for the accuracy of the osteoporosis prediction model.
참고문헌 (27)
- 차용한, "Introduction of the Cost-Effectiveness Studies of Fracture Liaison Service in Other Countries", 대한골대사학회지, 27(2), pp.79~83 (2020), 대한골대사학회
- 차용한, "Establishment of Fracture Liaison Service in Korea: Where Is It Stand and Where Is It Going?", 대한골대사학회지, 26(4), pp.207~211 (2019), 대한골대사학회
- LeBoff MS, "The clinician’s guide to prevention and treatment of osteoporosis", Osteoporos Int, 33, pp.2049~2102 (2022)[DOI]
- Cheng CT, "A scalable physician-level deep learning algorithm detects universal trauma on pelvic radiographs", Nat Commun, 12, pp.1066~ (2021)[DOI]
- Hyun-Soo Ok, "Alarm Services as a Useful Tool for Diagnosis and Management of Osteoporosis in Patients with Hip Fractures: A Prospective Observational Multicenter Study", 대한골대사학회지, 27(1), pp.65~70 (2020), 대한골대사학회
- Goecks J, "How machine learning will transform biomedicine", Cell, 181, pp.92~101 (2020)[DOI]
- Bohr A, "The rise of artificial intelligence in healthcare applications", Artif Intell Health, pp.25~60 (2020)[DOI]
- Basheer IA, "Artificial neural networks: fundamentals, computing, design, and application", J Microbiol Methods, 43, pp.3~31 (2000)[DOI]
- Patel JL, "Applications of artificial neural networks in medical science", Curr Clin Pharmacol, 2, pp.217~226 (2007)[DOI]
- Pandit A, "Machine learning in rheumatology approaches the clinic", Nat Rev Rheumatol, 16, pp.69~70 (2020)[DOI]
- Kokkotis C, "Machine learning in knee osteoarthritis : a review", Osteoarthr Cartil Open, 2, pp.100069~ (2020)[DOI]
- Jamshidi A, "Machine-learning-based patient-specific prediction models for knee osteoarthritis", Nat Rev Rheumatol, 15, pp.49~60 (2019)[DOI]
- de Vries BCS, "Comparing three machine learning approaches to design a risk assessment tool for future fractures : predicting a subsequent major osteoporotic fracture in fracture patients with osteopenia and osteoporosis", Osteoporos Int, 32, pp.437~449 (2021)[DOI]
- Kweon S, "Data resource profile : the Korea National Health and Nutrition Examination Survey(KNHANES)", Int J Epidemiol, 43, pp.69~77 (2014)[DOI]
- Maurel DB, "Alcohol and bone : review of dose effects and mechanisms", Osteoporos Int, 23, pp.1~16 (2012)[DOI]
- Cheraghi Z, "The effect of alcohol on osteoporosis : a systematic review and meta-analysis", Drug Alcohol Depend, 197, pp.197~202 (2019)[DOI]
- Bakker MH, "Are edentulousness, oral health problems and poor health-related quality of life associated with malnutrition in community-dwelling elderly (aged 75 years and over)? A cross-sectional study", Nutrients, 10, pp.1965~ (2018)[DOI]
- Bonjour JP, "Protein intake and bone health", Int J Vitam Nutr Res, 81, pp.134~142 (2011)[DOI]
- Huang W, "Association of geriatric nutritional risk index with the risk of osteoporosis in the elderly population in the NHANES", Front Endocrinol(Lausanne), 13, pp.965487~ (2022)[DOI]
- Rinonapoli G, "Osteoporosis in men : a review of an underestimated bone condition", Int J Mol Sci, 22, pp.2105~ (2021)[DOI]
- Kelsey JL, "Risk factors for osteoporosis and associated fractures", Public Health Rep, 104(Suppl), pp.14~20 (1989)
- Li H, "Smoking-induced risk of osteoporosis is partly mediated by cadmium from tobacco smoke : the MrOS Sweden study", J Bone Miner Res, 35, pp.1424~1429 (2020)[DOI]
- Vilaca T, "Osteoporosis in men", Lancet Diabetes Endocrinol, 10, pp.273~283 (2022)[DOI]
- Roth JA, "Introduction to machine learning in digital healthcare epidemiology", Infect Control Hosp Epidemiol, 39, pp.1457~1462 (2018)[DOI]
- Kwon Y, "Osteoporosis pre-screening using ensemble machine learning in postmenopausal Korean women", Healthcare(Basel), 10, pp.1107~ (2022)[DOI]
- Park HM, "Calcium from plant sources is beneficial to lowering the risk of osteoporosis in postmenopausal Korean women", Nutr Res, 31, pp.27~32 (2011)[DOI]
- Shim JG, "Application of machine learning approaches for osteoporosis risk prediction in postmenopausal women", Arch Osteoporos, 15, pp.169~ (2020)[DOI]