Explainable machine learning for osteoporosis detection in patients with osteopenia: model development and validation using routine clinical data from an Asian cohort - Takeaways - MDSpire
Coming Soon: Introducing MDSpire News. Learn more
Conexiant’s news site is now MDSpire News. Learn more

Development and Validation of an Explainable Machine Learning Model for Osteoporosis Identification in Osteopenic Patients Using Routine Clinical Data from an Asian Population

  • By

  • Xiuzhen Zhang

  • Li Zhao

  • Han Wu

  • Fengyi Yuan

  • Weiqing Wu

  • Yan Wu

  • Wei Wang

  • July 20, 2026

Share

  • 1

    A machine learning model was developed to distinguish osteoporosis from osteopenia using clinical data from 1,203 Asian adults with low bone mass.

  • 2

    The Linear Discriminant Analysis model achieved a mean cross-validated AUC of 0.738, indicating good performance in discriminating between the two conditions.

  • 3

    Key predictors for the model included waist-to-height ratio, body weight, serum uric acid, age, and alkaline phosphatase levels.

  • 4

    The model maintained robust performance with an AUC of 0.710 on an independent validation set, demonstrating its reliability.

  • 5

    This study highlights the potential of using routine clinical data for preliminary osteoporosis screening in resource-limited settings.

Original Source(s)

Related Content