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