AI Improves Kidney Stone Identification - Takeaways - MDSpire
Coming Soon: Introducing MDSpire News. Learn more
Conexiant’s news site is now MDSpire News. Learn more

AI Improves Kidney Stone Identification

  • November 20, 2026

  • 2 min

Share

  • 1

    A Mayo Clinic AI model predicted kidney stone composition using patient age, sex, and urinary measurements.

  • 2

    The model was developed using data from 13,000 patients who had stone analysis and 24-hour urine testing within 90 days.

  • 3

    In an independent dataset of 1,653 patients, the model correctly classified 73% of stones, compared with 33% using urinary supersaturation calculations alone.

  • 4

    The model predicted four categories: predominantly calcium oxalate, predominantly calcium phosphate, uric acid, and other compositions.

  • 5

    Researchers said AI predictions should supplement, not replace, direct stone analysis and established clinical assessments; clinical implementation requires further evaluation.

Original Source(s)

Related Content