Table 6.
Selection of variables in machine learning and conventional methods for osteoporosis risk of hip, neck and lumbar
Variables | Machine learning method | Conventional method | ||||||
---|---|---|---|---|---|---|---|---|
SVM | RF | ANN | LR | OST | ORAI | SCORE | OSIRIS | |
Age | o | o | o | o | o | o | o | o |
Height | o | o | o | |||||
Weight | o | o | o | o | o | o | o | o |
Body mass index | o | o | o | |||||
Waist circumference | o | |||||||
Pregnancy | o | o | ||||||
Duration of menopause | o | o | ||||||
Duration of breastfeeding | o | o | o | o | ||||
Estrogen therapy | o | o | o | o | ||||
Hyperlipidemia | o | o | o | |||||
Hypertension | o | o | ||||||
Fracture history | o | o | o | |||||
Osteoarthritis | o | o | o | o | ||||
Rheumatoid arthritis | o | |||||||
Diabetes mellitus | o | o | o | o |
SVM support vector machines, RF random forests, ANN artificial neural networks, LR logistic regression, OST osteoporosis self-assessment tool, ORAI osteoporosis risk assessment instrument; SCORE simple calculated osteoporosis risk estimation, OSIRIS osteoporosis index of risk