Machine learning models to predict pathological complete response after chemoradiotherapy in muscle-invasive bladder cancer: toward optimized indications for bladder preservation.
5 affiliations
- 1Department of Urology, Institute of Science Tokyo, Tokyo, Japan.
- 2Department of Medical Course, Faculty of Health and Medical Science, Teikyo Heisei University, Tokyo, Japan.
- 3Graduate School of Information Sciences, Teikyo Heisei University, Tokyo, Japan.
- 4Department of Radiological Technology, Kokura Memorial Hospital, Fukuoka, Japan.
- 5AI Laboratory, Tohoku University Hospital, Miyagi, Japan.
Abstract
After bladder-sparing chemoradiotherapy (CRT) for muscle-invasive bladder cancer (MIBC), residual microscopic disease may cause intravesical recurrence. This study aimed to develop machine learning models to predict pathological complete response (pCR) after CRT. We retrospectively analyzed 285 patients with cT2-4N0M0 MIBC who underwent CRT followed by partial or radical cystectomy. CRT response was determined from cystectomy specimens. Patients were randomly assigned to a training cohort (n = 228) and a test cohort (n = 57) using a fixed random seed. A total of 102 machine learning models were evaluated in the training cohort. The model with the highest area under the receiver operating characteristic curve (AUC) in the training-cohort was selected and then evaluated in the test cohort. The model incorporated clinical T stage, tumor size, multiplicity, hydronephrosis, bladder neck involvement (BNI), concomitant carcinoma in situ (CIS), variant histology, grade, and progression. Clinical T stages were T2/3/4 in 169/105/11 patients, respectively. Hydronephrosis was observed in 69 patients. Transurethral resection before CRT revealed multiplicity, BNI, and concomitant CIS in 108, 54, and 34 patients, respectively. Overall, 178/285 patients (62%) achieved pCR. WeightedEnsemble_L4 was selected as the final model and had a test-cohort AUC of 0.829 (95% confidence interval [CI], 0.706-0.932). The calibration slope was 0.856 (95% CI, 0.469-1.639), and the wide CI indicated uncertainty in calibration. Machine learning based on clinicopathologic variables estimated pCR after CRT. This may support decision-making regarding bladder preservation in patients with MIBC.
Related
- Fertility Preservation in Women with Endometriosis: Indications, Timing, Techniques, and Reproductive Outcomes
- Complete pathological response to neoadjuvant chemoradiotherapy in locally advanced rectal cancer and systemic oncologic benefit: a retrospective cohort study in Korea.
- Analysis of the Correlation Between Peripheral Blood Lymphocyte Subsets and Pathological Complete Response Rate in Rectal Cancer Patients Treated With Neoadjuvant Chemoradiotherapy
- Prediction Models for Pathological Response to Neoadjuvant Chemoradiotherapy in Locally Advanced Rectal Cancer: A Systematic Review and Meta-Analysis
- Pathological Response Depth and Pre-Treatment Risk Stratification After Neoadjuvant Chemoradiotherapy for Rectal Cancer.
BibTeX
@article{fujiwara2026machine,
title = {{Machine learning models to predict pathological complete response after chemoradiotherapy in muscle-invasive bladder cancer: toward optimized indications for bladder preservation.}},
author = {Motohiro Fujiwara and Hajime Tanaka and Daisuke Hirahara and Tatsunori Saho and Eichi Takaya and Shunya Matsumoto and Kasumi Yoshitomi and Masaki Kobayashi and Yuki Nakamura and Wei Chen and Yudai Ishikawa and Shohei Fukuda and Hiroshi Fukushima and Yuma Waseda and Soichiro Yoshida and Yasuhisa Fujii},
journal = {Clinical and translational radiation oncology},
year = {2026},
month = oct,
doi = {10.1016/j.ctro.2026.101320},
url = {https://europepmc.org/article/MED/42997524},
note = {CC BY},
}
RIS
TY - JOUR
TI - Machine learning models to predict pathological complete response after chemoradiotherapy in muscle-invasive bladder cancer: toward optimized indications for bladder preservation.
AU - Motohiro Fujiwara
AU - Hajime Tanaka
AU - Daisuke Hirahara
AU - Tatsunori Saho
AU - Eichi Takaya
AU - Shunya Matsumoto
AU - Kasumi Yoshitomi
AU - Masaki Kobayashi
AU - Yuki Nakamura
AU - Wei Chen
AU - Yudai Ishikawa
AU - Shohei Fukuda
AU - Hiroshi Fukushima
AU - Yuma Waseda
AU - Soichiro Yoshida
AU - Yasuhisa Fujii
PY - 2026
DA - 2026/10/13
JO - Clinical and translational radiation oncology
DO - 10.1016/j.ctro.2026.101320
UR - https://europepmc.org/article/MED/42997524
AB - After bladder-sparing chemoradiotherapy (CRT) for muscle-invasive bladder cancer (MIBC), residual microscopic disease may cause intravesical recurrence. This study aimed to develop machine learning models to predict pathological complete response (pCR) after CRT. We retrospectively analyzed 285 patients with cT2-4N0M0 MIBC who underwent CRT followed by partial or radical cystectomy. CRT response was determined from cystectomy specimens. Patients were randomly assigned to a training cohort (n = 228) and a test cohort (n = 57) using a fixed random seed. A total of 102 machine learning models were evaluated in the training cohort. The model with the highest area under the receiver operating characteristic curve (AUC) in the training-cohort was selected and then evaluated in the test cohort. The model incorporated clinical T stage, tumor size, multiplicity, hydronephrosis, bladder neck involvement (BNI), concomitant carcinoma in situ (CIS), variant histology, grade, and progression. Clinical T stages were T2/3/4 in 169/105/11 patients, respectively. Hydronephrosis was observed in 69 patients. Transurethral resection before CRT revealed multiplicity, BNI, and concomitant CIS in 108, 54, and 34 patients, respectively. Overall, 178/285 patients (62%) achieved pCR. WeightedEnsemble_L4 was selected as the final model and had a test-cohort AUC of 0.829 (95% confidence interval [CI], 0.706-0.932). The calibration slope was 0.856 (95% CI, 0.469-1.639), and the wide CI indicated uncertainty in calibration. Machine learning based on clinicopathologic variables estimated pCR after CRT. This may support decision-making regarding bladder preservation in patients with MIBC.
SN - 2405-6308
ER -