From the Journals

Machine Learning May Help Refine Fracture Risk Prediction

"Machine learning should be used to identify postmenopausal women at increased risk of fractures."

Share

A study published in Scientific Reports highlights the effectiveness of machine learning models in predicting osteoporotic fracture risk in postmenopausal women over 8 to 10 years. Conducted on 576 participants from two cohorts, the study found that Extreme Gradient Boosting achieved the highest predictive accuracy. Key predictors included history of fractures, parathormone levels, and lumbar spine T scores. The researchers emphasize that parathormone and vitamin D should be considered in fracture risk assessments, noting the limitations of the study due to its Spanish cohort and the binary modeling approach.

Original Source(s)

Machine Learning May Help Refine Fracture Risk Prediction

"Machine learning should be used to identify postmenopausal women at increased risk of fractures."

  • by Margery Weinstein

  • March 2, 2026

  • 3 min

Related Content

HDL Cholesterol's Vitamin D Dance: A Gender Twist

New research reveals that men's HDL cholesterol follows an inverted U-shaped relationship with vitamin D levels, while women maintain a consistently positive correlation.

USPSTF Releases Draft Osteoporosis Screening Guidelines

The USPSTF's draft recommendations reaffirm osteoporosis screening for older women, call for more research on screening men, and address health disparities.

FDA Approves First Once-Daily Oral Therapy for Acromegaly

Once-daily paltusotine offers an oral alternative to monthly injections for eligible adults.