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.

Authors

Institutions

Publication Details

Journal
Expert Review of Anticancer Therapy
Published
2026-09-12
DOI
https://doi.org/10.1080/14737140.2026.2733827
Primary Topic
Bladder and Urothelial Cancer Treatments
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

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

Linda Cerbone, Mattia Alberto Di Civita, Fabio Calabrò, Kannan Sridharan et al.
Expert Review of Anticancer Therapy
Bladder and Urothelial Cancer Treatments
article

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

Linda Cerbone, Mattia Alberto Di Civita, Fabio Calabrò, Kannan Sridharan, Andrea Malgeri, Gian Paolo Spinelli, Takafumi Yanagisawa, Jindřich Kopecký, Aristotelis Bamias, Takahiro Kimura, Tomáš Büchler, Daniele Santini, Luca Zacco, Gowri Sivaramakrishnan, Brigida Anna Maiorano, Jawaher Ansari, Se Hoon Park, Wataru Fukuokaya, Tarek Taha, Matteo Santoni
article en

Abstract

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.

Expert Review of Anticancer Therapy
Jikei University School of Medicine (JP), Royal Marsden NHS Foundation Trust (GB), Vita-Salute San Raffaele University (IT), National and Kapodistrian University of Athens (GR), University of St.Gallen (CH), Tawam Hospital (AE), University Hospital in Motol (CZ), European University of Rome (IT), National Cancer Institute (MY), Ospedale Sandro Pertini (IT), University Hospital Hradec Králové (CZ), Istituti di Ricovero e Cura a Carattere Scientifico (IT), Istituto di Ricovero e Cura a Carattere Scientifico San Raffaele (IT), Ospedale di Macerata, Arabian Gulf University (BH), Sungkyunkwan University (KR), Sapienza University of Rome (IT)
Openalex Percentile: Top 8%
Bladder and Urothelial Cancer Treatments
DOISourceOpenAlex
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.