The Pathologist
  • Explore Pathology

    Explore

    • Latest
    • Insights
    • Case Studies
    • Opinion & Personal Narratives
    • Research & Innovations
    • Product Profiles

    Featured Topics

    • Molecular Pathology
    • Infectious Disease
    • Digital Pathology

    Issues

    • Latest Issue
    • Archive
  • Subspecialties
    • Oncology
    • Histology
    • Cytology
    • Hematology
    • Endocrinology
    • Neurology
    • Microbiology & Immunology
    • Forensics
    • Pathologists' Assistants
  • Training & Education

    Career Development

    • Professional Development
    • Career Pathways
    • Workforce Trends

    Educational Resources

    • Guidelines & Recommendations
    • App Notes
    • eBooks

    Events

    • Webinars
    • Live Events
  • Events
    • Live Events
    • Webinars
  • Profiles & Community

    People & Profiles

    • Power List
    • Voices in the Community
    • Authors & Contributors
  • Multimedia
    • Video
    • Pathology Captures
Subscribe
Subscribe

False

The Pathologist / Issues / 2026 / November / AI Improves Kidney Stone Identification
Biochemistry and molecular biology Bioinformatics Software and hardware Technology and innovation

AI Improves Kidney Stone Identification

New model predicts kidney stone composition from urine tests, potentially informing treatment when stones are unavailable for analysis

11/20/2026 News 2 min read
  • Full Article
  • Summary
  • Takeaways
  • Listen
  • Report
  • Scorecard
  • Quiz
  • Poll

Share

Clinical Report: AI Improves Kidney Stone Identification

Overview

A Mayo Clinic-developed AI model predicted kidney stone composition with 73% accuracy in an independent dataset, compared with 33% for urinary supersaturation calculations alone. The researchers state that the model may provide additional information when a stone is unavailable for direct analysis, but should supplement—not replace—direct stone analysis and established clinical assessment.

Background

Kidney stones affect approximately 1 in 11 Americans during their lifetime, and recurrence is frequent. Identifying stone composition is important to long-term management, but stones are not always recovered for laboratory analysis. Clinicians may then estimate composition using laboratory measurements and other clinical information. Urinary supersaturation is routinely used to assess crystal-formation tendency, but the source reports that these calculations alone provide limited information about the composition of an existing stone.

Data Highlights

MeasureFinding
Model development cohort13,000 patients with stone analysis and 24-hour urine testing within 90 days, September 2015–March 2024
Independent evaluation dataset1,653 patients
AI model accuracy73%
Urinary supersaturation calculation accuracy33%
Predicted categoriesPredominantly calcium oxalate, predominantly calcium phosphate, uric acid, and other compositions

Key Findings

  • The model combined patient age, sex, and urinary measurements to predict four stone-composition categories.
  • In the independent dataset, the model correctly classified 73% of stones, versus 33% with urinary supersaturation calculations alone; the difference was statistically significant.
  • The model maintained superior performance across different age and sex groups.
  • Direct laboratory analysis remains the most reliable method for establishing stone composition, according to the article.
  • The researchers emphasize that AI predictions should supplement, not replace, direct stone analysis and established clinical assessments.
  • The article states that further evaluation of clinical implementation is needed to determine whether predictions improve treatment decisions and reduce recurrence.

Clinical Implications

When a stone is unavailable for direct analysis, the model may offer additional diagnostic information from patient characteristics and urine tests already collected in routine care. The researchers caution that its predictions are supplementary and that further evaluation is needed to establish effects on treatment decisions and recurrence.

Conclusion

In an independent evaluation, the AI model outperformed urinary supersaturation calculations alone for predicting kidney stone composition. Its role in clinical implementation remains to be evaluated, and it is not presented as a replacement for direct stone analysis.

Related Resources & Content

  1. Mayo Clinic Proceedings, Year not provided — A Validated Artificial Intelligence Model Versus Urinary Supersaturation Alone for Predicting Kidney Stone Composition
  2. European Association of Urology, 2026 — EAU Guidelines on Urolithiasis: Analysis of stone composition
  3. American Urological Association, 2026 — Medical Management of Kidney Stones: AUA Guideline, Part I
  4. American Urological Association, 2026 — Medical Management of Kidney Stones: AUA Guideline, Part II
  5. MDSpire News — AI Aids Rapid Kidney Stone Detection
  6. npj Digital Medicine — Clinical validation of an AI-assisted system for real-time kidney stone detection during flexible ureteroscopic surgery
  7. World Journal of Urology — Methodology of peri-operative imaging data reporting for stone disease: a systematic review toward the development of a novel checklist—iSTAR
  8. ASCO Publications — Using automated machine learning to detect kidney anomalies.
  9. AI Aids Rapid Kidney Stone Detection
  10. Clinical validation of an AI-assisted system for real-time kidney stone detection during flexible ureteroscopic surgery
  11. Methodology of peri-operative imaging data reporting for stone disease: a systematic review toward the development of a novel checklist—iSTAR
  12. 3.3.2.b **Analysis of stone composition**
  13. Guidelines - EAU Guidelines on Urolithiasis - Uroweb
  14. Medical Management of Kidney Stones: AUA Guideline (2026) Part I: Evaluation of Patients With Kidney Stones and Dietary Management of Patients With Calcium Stones
  15. Medical Management of Kidney Stones: AUA Guideline (2026) Part II: Treatment and Follow-up of Kidney Stones
  16. A Validated Artificial Intelligence Model Versus Urinary Supersaturation Alone for Predicting Kidney Stone Composition.
  17. Determination of urinary stone composition using computed tomography using artificial intelligence

This content is an AI-generated, fully rewritten summary based on a published scholarly article. It does not reproduce the original text and is not a substitute for the original publication. Readers are encouraged to consult the source for full context, data, and methodology.

Newsletters

Receive the latest pathologist news, personalities, education, and career development – weekly to your inbox.

Newsletter Signup Image

Explore More in Pathology

Dive deeper into the world of pathology. Explore the latest articles, case studies, expert insights, and groundbreaking research.

False

Advertisement

Recommended

False

Affiliations:

Specialties:

Areas of Expertise:

Contributions:

False

The Pathologist
Subscribe

About

  • About Us
  • Work at Conexiant Europe
  • Terms and Conditions
  • Privacy Policy
  • Your Privacy Choices
  • Advertise With Us
  • Contact Us

Copyright © 2026 Texere Publishing Limited (trading as Conexiant), with registered number 08113419 whose registered office is at Booths No. 1, Booths Park, Chelford Road, Knutsford, England, WA16 8GS.