Predicting poor response to anti-osteoporosis therapy: a machine learning model integrating clinical and novel biomarker data - Takeaways - MDSpire

Predicting poor response to anti-osteoporosis therapy: a machine learning model integrating clinical and novel biomarker data

  • By

  • Yannan Bi

  • Maolin Zhang

  • Weiqiong Zhang

  • Jiahong Li

  • May 14, 2026

  • 0 min

Share

  • 1

    A predictive model integrating clinical features and novel biomarkers was developed to identify patients at high risk for inadequate osteoporosis treatment response.

  • 2

    The study analyzed data from 543 patients with primary osteoporosis, using machine learning models to predict treatment efficacy.

  • 3

    Eight independent predictors of poor treatment response were identified, including comorbid diabetes and specific serum biomarker levels.

  • 4

    The Random Forest model outperformed others, achieving an AUC of 0.856 in the training set and 0.825 in the validation set.

  • 5

    This model supports personalized treatment decisions, enhancing precision management in osteoporosis care.

Original Source(s)

Predicting poor response to anti-osteoporosis therapy: a machine learning model integrating clinical and novel biomarker data

  • by Yannan Bi, Maolin Zhang, Weiqiong Zhang, Jiahong Li

  • May 14, 2026

Related Content

Postop Pain Differs by Vitamin D Status

Patients with preoperative vitamin D deficiency had higher postoperative pain scores and opioid use after mastectomy, including more than triple the odds of moderate to severe pain within 24 hours of surgery.

Top 10 States for Physician-Owned Hospitals

These 10 states make it more practical for physicians to participate in hospital ownership by aligning statutory structure, corporate practice of medicine rules, and population trends.

Artificial Intelligence System for Detecting Multiple Diseases Through Retinal Imaging