Machine learning approaches to predict early cardiac immune-related adverse events in patients receiving immune checkpoint inhibitors
Authors:
Open Access
- 29 July 2026
- journal article
- research article
- Published by Springer Nature in Supportive Care in Cancer
- Vol. 34 (8) , 809
Abstract
Purpose: Immune checkpoint inhibitor (ICI)–induced cardiac immune-related adverse events (cardiac irAEs) are rare yet serious complications. Clinical assessment tools to identify at-risk patients would allow for more effective prevention strategies, thus improving clinical outcomes. We constructed various machine learning (ML) models to predict these events among patients receiving ICI therapy. Methods: A cohort of patients receiving ICI therapy from 2010 to 2023 was identified from the TriNetX database. Cardiac irAEs were defined as the occurrence of relevant diagnosis codes within 90 days of ICI initiation, with corresponding hospital visits. We created ML models to predict these events, including elastic net logistic regression and multiple tree-based approaches (gradient boosted trees and random forest). We evaluated model performance with different performance measures and utilized assigned risk scores to stratify risk of cardiac irAEs into low, medium, and high-risk tiers. Results: We identified 61,117 patients receiving ICI therapy, with nearly 2% of patients experiencing cardiac irAEs. Model performance on testing data was comparable with all approaches (AUC = 0.71–0.72, balanced accuracy = 65–66%). Each model emphasized distinct features to make classifications, as observed with feature importance and SHAP values. Comparing cardiac irAE rates among assigned risk strata, patients identified as high risk were significantly more likely to experience cardiac irAEs compared to lower tiers. Conclusion: Our preliminary exploration of ML methods demonstrated the potential for risk assessment tools to predict rare cardiac irAEs in patients receiving ICI therapy. Follow-up studies can implement time series approaches to harness longitudinal data that incorporates real-time labs, new diagnoses, and new therapy, to refine predictions further.Keywords
This publication has 53 references indexed in Scilit:
- Early detection of myocarditis caused by immune checkpoint inhibitor therapy with nivolumab and ipilimumab for advanced recurrent renal cell carcinomaCancer Immunology, Immunotherapy, 2025
- The effect of resampling techniques on the performances of machine learning clinical risk prediction models in the setting of severe class imbalance: development and internal validation in a retrospective cohortDiscover Artificial Intelligence, 2024
- A two-stage ensemble learning based prediction and grading model for PD-1/PD-L1 inhibitor-related cardiac adverse events: A multicenter retrospective studyComputer Methods and Programs in Biomedicine, 2024
- Early identification of severe immune checkpoint inhibitor associated myocarditis: From an electrocardiographic perspectiveCancer Medicine, 2024
- Risk Factors for Immune Checkpoint Inhibitor–Mediated Cardiovascular ToxicitiesCurrent Oncology Reports, 2023
- Immune checkpoint inhibitors: immune-related adverse events, healthcare utilization, and costs among commercial and Medicare Advantage patientsSupportive Care in Cancer, 2022
- The Impact of Adverse Events on Health Care Resource Utilization, Costs, and Mortality Among Patients Treated with Immune Checkpoint InhibitorsThe Oncologist, 2021
- Machine Learning vs. Conventional Statistical Models for Predicting Heart Failure Readmission and MortalityESC Heart Failure, 2020
- Explaining prediction models and individual predictions with feature contributionsKnowledge and Information Systems, 2013
- Micronutrients in Chronic Heart FailureCurrent Heart Failure Reports, 2012