Skip to content

Author

T. Yanagisawa

2 papers indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Review Open access Aug 2026

Diet and risk of bladder cancer: a systematic review of epidemiological evidence.

PURPOSE Although tobacco use and occupational exposures are established risk factors for urothelial cancer (UC), the influence of dietary factors remains uncertain. We conducted a systematic review to synthesize evidence from prospective cohort studies examining associations between dietary exposures and UC incidence. METHODS A comprehensive literature search of MEDLINE, Embase, and Web of Science (May 2025) was performed to identify prospective studies evaluating dietary factors with UC incidence. The risk of bias was assessed using standard tools (CRD420251043101). RESULTS From 6253 records screened, 32 prospective cohort studies were included, encompassing 2 277 677 participants. Investigated exposures included fluid intake (four studies, n = 562 038), coffee (four, n = 1 013 624), milk (three, n = 613 141), tea (three, n = 532 949), alcohol (three, n = 694 585), fruits (three, n = 597 753), vegetables (three, n = 555 685), protein (two, n = 469 339), fibre (two, n = 466 577), and cruciferous vegetables (two, n = 1 071 313). Only one study specifically assessed upper tract urothelial carcinoma (n = 80 388). Two studies suggested a borderline inverse association between high fluid intake and bladder cancer (BC) risk (upper 95% confidence interval >0.95), whereas two others found no such association. Three of four coffee studies reported no significant association after adjustment for smoking; one reported a modest increased risk. Fruit and vegetable intake showed modest inverse associations with BC risk in three studies. Most included studies were at moderate risk of bias, and residual confounding-particularly by smoking-remains a concern. CONCLUSION Available evidence does not support a strong or consistent association between dietary factors and BC incidence. Although a healthy diet is beneficial for overall well-being, patients should be informed that dietary modifications alone are unlikely to meaningfully alter their BC risk.

Keiichiro Miyajima, Marcin Miszczyk, Navid Roessler et al. · 0 citations
#explainable ai Sep 2026

Machine learning integrated explainable artificial intelligence in predicting toxicities of enfortumab vedotin in urothelial carcinoma: an exploratory study.

BACKGROUND Enfortumab vedotin (EV) therapy for advanced urothelial carcinoma is limited by adverse events (AEs). Early identification of high-risk patients is needed. This proof-of-concept study evaluated whether machine learning (ML) with explainable AI (SHAP) could predict EV toxicities using real-world data. RESEARCH DESIGN AND METHODS Data from 542 patients (51 centers, 24 countries) were analyzed. Six outcomes were predicted including grade 3-4 AEs. Four ML algorithms were trained on an 80% split and tested on 20%. Performance was evaluated via standard metrics with SHAP for interpretability. RESULTS In this exploratory analyses, Random Forest achieved highest overall performance, yielding best AUC for diarrhea, severe AEs, and dose skipping. XGBoost led for cutaneous toxicity and diabetes; LASSO led for neuropathy (differences modest). Age was the most important associated variable, followed by prior immunotherapy and ECOG status. Liver metastases influenced diabetes and cutaneous toxicity; lung metastases impacted diarrhea, neuropathy, and skin toxicity. SHAP showed atezolizumab/nivolumab linked to lower cutaneous risk, and female sex to higher risk. CONCLUSION These preliminary, hypothesis-generating findings suggest ML may predict EV-related toxicities, but single train-test split, small event counts, and lack of external validation preclude clinical use. Prospective validation is essential.

K. Sridharan, Mattia Alberto Di Civita, G. Sivaramakrishnan et al. · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.