Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
September 14, 2026Expert Review of Anticancer Therapy

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

View Full Paper
Ask AI
Bookmark
Share

Authors

KSKannan SridharanMCMattia Alberto Di CivitaGSGowri Sivaramakrishnan

Discussion

Loading...

Member takes

Overview

Multicenter cohort study demonstrates machine learning models predict adverse events from enfortumab vedotin in urothelial carcinoma, suggesting potential for personalized risk assessment.

Key Points

  • To evaluate whether machine learning models integrated with explainable artificial intelligence (SHAP) can predict treatment-related toxicities in patients receiving enfortumab vedotin for advanced urothelial carcinoma.
  • Analyzed real-world clinical data from 542 patients across 51 centers in 24 countries.
  • Trained four machine learning algorithms on an 80% split and tested on 20% to predict six adverse outcomes, including grade 3-4 adverse events, using SHAP for model interpretability.
  • Random Forest yielded the highest overall performance with the best AUC for severe adverse events, diarrhea, and dose skipping, while XGBoost performed best for cutaneous toxicity and diabetes, and LASSO led for neuropathy.
  • Age was the most critical predictive variable overall, followed by prior immunotherapy and ECOG performance status, with liver and lung metastases differentially influencing specific toxicities.

Cite This Study

Sridharan et al. (2026) studied this question.

synapsesocial.com/papers/6aa7b3bf0926e14a848b2df9https://doi.org/10.1080/14737140.2026.2733827
View Full Paper
Ask AI
Bookmark
Share

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

  1. 1Machine learning-integrated explainable artificial intelligence for survival prediction in urothelial carcinoma with enfortumab vedotin: an exploratory real-world analysis2026
  2. 2Immunotherapy toxicity prediction in patients with melanoma using machine learning algorithms.2024
  3. 3Explainable machine learning to predict immunotherapy outcomes in metastatic renal cell carcinoma - Meet-URO 15-AI study2026
  4. 4Machine Learning Model for Predicting Severe Adverse Events in Oncology Patients Using the US Food and Drug Administration Adverse Event Reporting System2026
  5. 5Neutrophil-to-Lymphocyte Ratio and Performance Status Are Associated With Increased Risk of Skin Toxicity in Patients Receiving Enfortumab Vedotin With or Without Pembrolizumab for Metastatic Urothelial Carcinoma2026