An explainable predictive machine learning model of osteopenia for perimenopausal women based on clinical data: a retrospective single-center study - Summary - MDSpire

An explainable predictive machine learning model of osteopenia for perimenopausal women based on clinical data: a retrospective single-center study

  • By

  • Xiaoling Zhuo

  • Huixian Zeng

  • Huoqiang Chen

  • Yunlin Wang

  • Zhenhua Feng

  • Quanhui Liang

  • May 29, 2026

  • 0 min

Share

Objective:

To develop a machine learning-based model for identifying individuals at risk of osteopenia in perimenopausal women using clinical data.

Key Findings:
  • 17 predictors of osteopenia were identified.
  • Random forest demonstrated the best performance with an AUC of 0.978 in training and 0.933 in validation datasets.
  • Key predictors included menopause, age, PINP, β-CTX, height, and eGFR.
  • A web-based calculator was developed for clinical use.
  • RF outperformed other models with an AUPR of 0.93 for the top six features.
Interpretation:

Limitations:
  • The study is based on a single center, which may limit generalizability.
  • The retrospective design may introduce bias.
Conclusion:

Original Source(s)

An explainable predictive machine learning model of osteopenia for perimenopausal women based on clinical data: a retrospective single-center study

  • by Xiaoling Zhuo, Huixian Zeng, Huoqiang Chen, Yunlin Wang, Zhenhua Feng, Quanhui Liang

  • May 29, 2026

Related Content

MAFLD is associated with lower bone mineral density in patients with type 2 diabetes: an exploratory cross-sectional analysis of a potential indirect association with HOMA-IR

Raman spectroscopic fingerprinting uncovers a multi-scale structural–mechanical–transcriptomic coupling landscape in osteoporosis

Medical Oddities: Ancient Practice Calms Modern BP

Ancient workouts, anxious ears, tea gains, limb regrowth, and furry tongues collide.