Multimodal AI refines EAU risk stratification in patients undergoing radiotherapy for prostate cancer
Abstract
The European Association of Urology (EAU) risk groups guide treatment decisions in prostate cancer using prostate-specific antigen (PSA), ISUP grade, and clinical stage, but do not incorporate histopathological image information. We evaluated a locked multimodal artificial intelligence (AI) model that integrates routinely available clinical variables (age, PSA, and ISUP grade) with deep-learning features extracted from diagnostic biopsy whole-slide images for predicting outcomes after radiotherapy (RT). The model was originally trained to predict biochemical recurrence (BCR) following radical prostatectomy and was applied without retraining to 353 patients from the population-based STHLM3 trial (ISRCTN84445406) treated with RT. Study endpoints included BCR (Phoenix definition), high-risk BCR (HR-BCR), and prostate cancer-specific mortality (PCSM). Model performance was assessed using Harrell’s C-index and cumulative incidence analyses and compared with EAU risk groups. The continuous AI score showed C-indices of 0.65 (95% CI 0.55–0.74) for BCR, 0.84 (0.72–0.95) for HR-BCR, and 0.81 (0.63–1.00) for PCSM, compared with 0.60, 0.82, and 0.80, respectively, for EAU risk groups. Although paired differences in C-index between AI and EAU were not statistically significant, adding the continuous AI score to EAU classification improved model fit for BCR, HR-BCR, and PCSM. Exploratory AI risk stratification classified 18.9% of EAU intermediate-risk patients as AI high-risk and 28.2% of EAU high-risk patients as AI low-risk. Within the EAU high-risk group, patients classified as AI low-risk ( n = 24) experienced no BCR events during 10 years of follow-up, compared with a 10-year cumulative incidence of 28.7% (95% CI 17.3–41.2%) among AI high-risk patients ( n = 61). These findings suggest that multimodal AI may refine EAU risk stratification by identifying distinct prognostic subgroups within established risk categories, although prospective validation is needed before its potential role in individualized treatment decision-making can be established.
Related
- Feasibility and safety of an F16 small-caliber catheter-based, irrigation-free protocol in BPH patients undergoing green laser enucleation of the prostate: a single-center retrospective cohort study
- Cost-effectiveness of adding enzalutamide vs standard non-steroidal antiandrogen drugs for patients with metastatic hormone-sensitive prostate cancer undergoing standard first-line therapy: a within-trial, secondary end-point analysis of the ENZAMET phase 3, international randomized trial (ANZUP 1304)
- Multimodal digital assessment of early recovery after chest tube omission in early-stage lung cancer patients undergoing wedge resection: a post hoc analysis of a prospective cohort
- Limosilactobacillus reuteri for oral mucositis in patients undergoing radiotherapy for malignant head and neck tumors: a randomized controlled trial.
- Effect of Jaw Exercise on Mouth Opening and Trismus in Head and Neck Cancer Patients Undergoing Radiotherapy: A Randomised Controlled Trial.
BibTeX
@article{camilloni2026multimodal,
title = {{Multimodal AI refines EAU risk stratification in patients undergoing radiotherapy for prostate cancer}},
author = {Andrea Camilloni and Chiara Micoli and Ugo Giovanni Falagario and Nita Mulliqi and Erik Everett Palm and Thorgerdur Palsdottir and Kelvin Szolnoky and Xiaoyi Ji and Sol Erika Boman and Andrea Discacciati and Lars Egevad and Henrik Grönberg and Kimmo Kartasalo and Tobias Nordström and Martin Eklund},
journal = {Scientific Reports},
year = {2026},
month = oct,
doi = {10.1038/s41598-026-76327-w},
url = {https://www.nature.com/articles/s41598-026-76327-w},
note = {CC BY 4.0},
}
RIS
TY - JOUR
TI - Multimodal AI refines EAU risk stratification in patients undergoing radiotherapy for prostate cancer
AU - Andrea Camilloni
AU - Chiara Micoli
AU - Ugo Giovanni Falagario
AU - Nita Mulliqi
AU - Erik Everett Palm
AU - Thorgerdur Palsdottir
AU - Kelvin Szolnoky
AU - Xiaoyi Ji
AU - Sol Erika Boman
AU - Andrea Discacciati
AU - Lars Egevad
AU - Henrik Grönberg
AU - Kimmo Kartasalo
AU - Tobias Nordström
AU - Martin Eklund
PY - 2026
DA - 2026/10/17
JO - Scientific Reports
DO - 10.1038/s41598-026-76327-w
UR - https://www.nature.com/articles/s41598-026-76327-w
AB - The European Association of Urology (EAU) risk groups guide treatment decisions in prostate cancer using prostate-specific antigen (PSA), ISUP grade, and clinical stage, but do not incorporate histopathological image information. We evaluated a locked multimodal artificial intelligence (AI) model that integrates routinely available clinical variables (age, PSA, and ISUP grade) with deep-learning features extracted from diagnostic biopsy whole-slide images for predicting outcomes after radiotherapy (RT). The model was originally trained to predict biochemical recurrence (BCR) following radical prostatectomy and was applied without retraining to 353 patients from the population-based STHLM3 trial (ISRCTN84445406) treated with RT. Study endpoints included BCR (Phoenix definition), high-risk BCR (HR-BCR), and prostate cancer-specific mortality (PCSM). Model performance was assessed using Harrell’s C-index and cumulative incidence analyses and compared with EAU risk groups. The continuous AI score showed C-indices of 0.65 (95% CI 0.55–0.74) for BCR, 0.84 (0.72–0.95) for HR-BCR, and 0.81 (0.63–1.00) for PCSM, compared with 0.60, 0.82, and 0.80, respectively, for EAU risk groups. Although paired differences in C-index between AI and EAU were not statistically significant, adding the continuous AI score to EAU classification improved model fit for BCR, HR-BCR, and PCSM. Exploratory AI risk stratification classified 18.9% of EAU intermediate-risk patients as AI high-risk and 28.2% of EAU high-risk patients as AI low-risk. Within the EAU high-risk group, patients classified as AI low-risk ( n = 24) experienced no BCR events during 10 years of follow-up, compared with a 10-year cumulative incidence of 28.7% (95% CI 17.3–41.2%) among AI high-risk patients ( n = 61). These findings suggest that multimodal AI may refine EAU risk stratification by identifying distinct prognostic subgroups within established risk categories, although prospective validation is needed before its potential role in individualized treatment decision-making can be established.
SN - 2045-2322
ER -