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.· Expert Review of Anticancer...· 0 citations
Background
Identifying reliable predictors of mortality and survival in people living with HIV (PLWH) is essential for personalized risk stratification and treatment optimization. This study employed machine learning (ML) and explainable artificial intelligence (XAI) to identify key prognostic factors and develop predictive models for overall survival and mortality in a large PLWH cohort.
Methods
We analyzed data from 2139 patients from the AIDS Clinical Trials Group Study 175. For time-to-event analysis, we implemented Cox Proportional Hazards, Random Survival Forest, and Cox Elastic-Net models. For mortality prediction, we employed Elastic Net, Random Forest, and Bayesian Additive Regression Trees (BART). Models were trained on 70% of the data and validated on the remaining 30%. SHapley Additive exPlanations (SHAP) analysis was applied to the best-performing models for interpretability. Model performance was evaluated using C-index, AUC-ROC, accuracy, sensitivity, specificity, and calibration metrics with 95% confidence intervals (CI). No external validation was performed.
Results
The Cox Proportional Hazards model demonstrated the best survival prediction performance (C-index: 0.758, 95% CI: 0.723-0.784; 1-year AUC: 0.885, 95% CI: 0.849-0.934), while Elastic Net was optimal for mortality prediction (AUC: 0.751, 95% CI: 0.712-0.793; accuracy: 0.793, 95% CI: 0.758-0.825). CD4 count at 20 weeks consistently emerged as the most influential predictor across all models, with mean absolute SHAP values of 1.745 for survival and 0.129 for mortality. Treatment-related variables, including off-treatment status and specific antiretroviral therapy (ART) regimens, were also consistently important predictors. Symptomatic status showed strong negative contributions (81% for survival, 81% for mortality), while non-White race paradoxically demonstrated protective effects (73% positive contributions). BART demonstrated comparable performance (AUC: 0.743, 95% CI: 0.695-0.785) with excellent calibration (calibration slope: 0.895).
Conclusion
Machine learning models, particularly Elastic Net and Cox Proportional Hazards, effectively predict mortality and survival in PLWH, with immunological response, treatment-related factors, and clinical presentation emerging as the dominant predictors. These findings support the potential of ML and XAI for personalized risk stratification in HIV care, emphasizing the critical importance of optimizing ART regimens, ensuring treatment adherence, and addressing modifiable risk factors to improve long-term outcomes.
