Authors
Eric B Lantz, Patrick Vanderboom, Kevin Koo, Paul J Jannetto, John C Lieske, Jeff Meeusen, Patrick L Day
Published in
Mayo Clinic proceedings. Nov 12, 2026. Epub Nov 12, 2026.
Abstract
To develop and validate an artificial intelligence (AI) model that can identify kidney stone composition more accurately than the EQUIL2 urine supersaturation (SS) algorithm.
Patients with both a 24-hour urine SS panel and a kidney stone composition analysis conducted within 90 days of each other between September 24, 2015, and March 15, 2024, were identified (n=13,000 unique patients). Kidney stones were classified as either majority calcium oxalate (CaOx), majority calcium phosphate (CaP), uric acid, or other. A model was developed to predict kidney stone classification using demographic characteristics plus urinary SS panel results. This model was subsequently validated on a held-out data set of paired measurements collected between March 16, 2024, and March 15, 2025 (n=1653). The urinary SS for CaOx, hydroxyapatite (CaP), brushite (CaP), and uric acid were calculated using EQUIL2 according to routine clinical practice and expressed using the delta Gibbs free energy scale.
The AI model was significantly more accurate in the validation data set for identifying stone composition compared with SS alone (accuracy, 0.73 vs 0.33; P<.01). Additionally, the model outperformed SS alone in the validation data set for correctly identifying kidney stone composition in all analyses stratified into clinically relevant subgroups by age and sex.
In all kidney stone categories and within various subgroups, the AI model outperformed the EQUIL2-calculated SS as well as previously published AI models in the correct prediction of CaOx, CaP, and uric acid kidney stones when using the 24-hour urine SS panel.
PMID:
43018532
Bibliographic data and abstract were imported from PubMed on 12 Nov 2026.
Read full publication at:
Please sign in
to see all details.
Advertisement
Stats
- Recommendations n/a n/a positive of 0 vote(s)
- Views 2
- Comments 0