Machine Learning May Help Refine Fracture Risk Prediction - Takeaways - MDSpire
Coming Soon: Introducing MDSpire News. Learn more
Conexiant’s news site is now MDSpire News. Learn more

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

Share

  • 1

    Machine learning models accurately predicted osteoporotic fracture risk in postmenopausal women over 8 to 10 years.

  • 2

    The study involved 576 postmenopausal women, with significant fracture occurrences in both osteoporosis and general population cohorts.

  • 3

    Extreme Gradient Boosting showed the best predictive performance, achieving an AUC of 0.88 in both cohorts.

  • 4

    Key predictors of fracture risk included previous fractures, parathormone levels, lumbar spine T score, and vitamin D levels.

  • 5

    The study highlights limitations in generalizability and fracture timing, emphasizing the need for improved risk assessment models.

Original Source(s)

Machine Learning May Help Refine Fracture Risk Prediction

  • by Margery Weinstein

  • March 2, 2026

Related Content

Osteoimmuno-brain axis: a bridge connecting osteoporosis and cognitive decline and its clinical significance in dementia and Alzheimer’s disease

Screening and validation of ZFYVE27 as a potential diagnostic biomarker for osteoporosis via integrative bioinformatics and machine learning approaches

Simplified Bone Age Method May Aid Review

Single-bone approach showed close agreement with Greulich-Pyle assessments in adolescents, particularly among experienced raters