Machine learning approaches to predict early cardiac immune-related adverse events in patients receiving immune checkpoint inhibitors.
Machine learning models can now sort immunotherapy patients into low, medium, or high-risk groups for heart complications, enabling earlier monitoring and prevention.
ML models (gradient boosting, random forest, elastic net) trained on 61,117 ICI-treated patients predicted cardiac immune-related adverse events with AUC 0.71–0.72, effectively stratifying patients into low/medium/high-risk tiers with significantly different cardiac irAE rates. This record was retained from the prior triage attempt for PubMed pipeline handoff.
What the study was
- Study design
- retrospective database cohort + ML model development (n=61,117, TriNetX)
- Category
- ai_ml_clinical_diagnostics
- Maturity
- Validated
- Journal
- Support Care Cancer
Why it surfaced
Large database ML study (n=61,117) for prediction of rare but life-threatening cardiac irAEs in ICI patients — clinically important safety monitoring tool for the rapidly growing ICI-treated population. Open access publication; risk stratification applicable to routine clinical practice.
A plain-language summary of published research — not medical advice. Talk to a clinician about your own care.