A novel machine-learning model using nuclear features to predict upper tract urothelial carcinoma recurrence

Abstract

Upper-tract urothelial carcinoma (UTUC) is rare, constitutes < 5% of urothelial cancers, and, given its insidious clinical presentation, is typically diagnosed at advanced stages; post-radical nephroureterectomy recurrence remains challenging. Postoperative management is primarily guided by pathological factors, including T-stage and lymph-node status, which cannot accurately identify patients who would benefit from treatment intensification, particularly considering concerns regarding cisplatin-associated nephrotoxicity. Using an artificial intelligence (AI)-informed pathology model, we predicted postoperative recurrence using UTUC’s quantitative nuclear features. Among 222 patients with UTUC, support vector machine (SVM) and random forest (RF) models were trained using pT3 cases ( n = 68) comprising sufficient recurrence events. Patient-level model performance was evaluated and validated using an independent test cohort ( n = 50; pT1 = 12, pT2 = 11, pT3 = 22, and pT4 = 5). RF and SVM models achieved patient-level accuracies of 77.3% and 63.6%, respectively, in pT3 cases and overall accuracies of 80% and 68%, respectively, in the independent pT1–pT4 cohort. Model-derived risk stratification (1 point per model with predicted recurrence probability ≥ 0.5 and classifying patients into low, intermediate, and high-risk groups [0, 1, and 2 points, respectively]) significantly discriminated recurrence-free survival in the independent test cohort (pT1–pT4), distinguishing risk groups (low-risk: n = 7, intermediate-risk: n = 8, high-risk: n = 35; log-rank p = 0.01); the low-risk group had no recurrence.

Machine learning-based classification of renal cell carcinoma and upper tract urothelial carcinoma using preoperative hematological markers.
Kanrapee Nuwatkrisin, Chanita Panwoon, Kiartisak Senchan +2
Biomedical reports9 Oct 2026Peer-reviewedCC BY-NC-NDFull textGeneral medicineEurope PMCPMC
Durable Complete Response to Pembrolizumab for Postoperative Nodal Recurrence of Lynch Syndrome–Associated Upper Tract Urothelial Carcinoma: A Case Report
Kaya Atagi, Shinkuro Yamamoto, Nobutaka Shimizu +7
IJU case reports1 Nov 2026Peer-reviewedCC BYFull textSurgery & anaesthesiaEurope PMCPMC
Incorporating natural language processing-derived features from pathology reports into machine learning models to predict differentiated thyroid cancer recurrence
Denise T. Lee, Steven Yen, Grace Deng +6
Frontiers in Endocrinology21 Oct 2026Peer-reviewedCC BY 4.0Full textEndocrinology & metabolismCrossrefEurope PMCPMC
Incremental Predictive Value and Representation of Transcriptomic Features for Immunotherapy Response in Advanced Urothelial Carcinoma
G. Y. Han, H. Tai, F. Wang
medRxiv14 Sep 2026PreprintCC BYFull textOncologymedRxiv
Urinary DNA Methylation Profiling Identifies a Biologically Distinct Subgroup of Low-Grade Urothelial Carcinoma with High-Grade-Associated Features
Marc Andreu-Inglés, Alina-Iuliana Onoiu, Marc Grifoll-Escoda +6
International Journal of Molecular Sciences8 Oct 2026Peer-reviewedCC BY 4.0Full textSurgery & anaesthesiaCrossrefEurope PMC

Cite

BibTeX RIS

BibTeX

@article{muraoka2026novel,
  title = {{A novel machine-learning model using nuclear features to predict upper tract urothelial carcinoma recurrence}},
  author = {Ryu Muraoka and Akira Saito and Naoto Tokuyama and Shuya Matsubara and Bin Shen and Takuya Tsujino and Kazumasa Komura and Takeshi Hashimoto and Haruhito Azuma and Toshitaka Nagao and Masahiko Kuroda and Yoshio Ohno},
  journal = {Scientific Reports},
  year = {2026},
  month = oct,
  doi = {10.1038/s41598-026-72946-5},
  url = {https://www.nature.com/articles/s41598-026-72946-5},
  note = {CC BY 4.0},
}

RIS

TY  - JOUR
TI  - A novel machine-learning model using nuclear features to predict upper tract urothelial carcinoma recurrence
AU  - Ryu Muraoka
AU  - Akira Saito
AU  - Naoto Tokuyama
AU  - Shuya Matsubara
AU  - Bin Shen
AU  - Takuya Tsujino
AU  - Kazumasa Komura
AU  - Takeshi Hashimoto
AU  - Haruhito Azuma
AU  - Toshitaka Nagao
AU  - Masahiko Kuroda
AU  - Yoshio Ohno
PY  - 2026
DA  - 2026/10/05
JO  - Scientific Reports
DO  - 10.1038/s41598-026-72946-5
UR  - https://www.nature.com/articles/s41598-026-72946-5
AB  - Upper-tract urothelial carcinoma (UTUC) is rare, constitutes < 5% of urothelial cancers, and, given its insidious clinical presentation, is typically diagnosed at advanced stages; post-radical nephroureterectomy recurrence remains challenging. Postoperative management is primarily guided by pathological factors, including T-stage and lymph-node status, which cannot accurately identify patients who would benefit from treatment intensification, particularly considering concerns regarding cisplatin-associated nephrotoxicity. Using an artificial intelligence (AI)-informed pathology model, we predicted postoperative recurrence using UTUC’s quantitative nuclear features. Among 222 patients with UTUC, support vector machine (SVM) and random forest (RF) models were trained using pT3 cases ( n = 68) comprising sufficient recurrence events. Patient-level model performance was evaluated and validated using an independent test cohort ( n = 50; pT1 = 12, pT2 = 11, pT3 = 22, and pT4 = 5). RF and SVM models achieved patient-level accuracies of 77.3% and 63.6%, respectively, in pT3 cases and overall accuracies of 80% and 68%, respectively, in the independent pT1–pT4 cohort. Model-derived risk stratification (1 point per model with predicted recurrence probability ≥ 0.5 and classifying patients into low, intermediate, and high-risk groups [0, 1, and 2 points, respectively]) significantly discriminated recurrence-free survival in the independent test cohort (pT1–pT4), distinguishing risk groups (low-risk: n = 7, intermediate-risk: n = 8, high-risk: n = 35; log-rank p = 0.01); the low-risk group had no recurrence.
SN  - 2045-2322
ER  -

Abstract

Related

Cite