Artificial Intelligence Assisted Prediction of Late Onset Cardiomyopathy Among Childhood Cancer Survivors

Abstract

Listen

Translate article

Objective: Early identification of childhood cancer survivors at high risk for treatment-related cardiomyopathy may improve outcomes by enabling intervention prior to development of heart failure. We implemented artificial intelligence methods using the Children’s Oncology Group (COG) guideline-recommended baseline electrocardiography (ECG) to predict cardiomyopathy. Materials and Methods: Seven artificial intelligence and signal processing methods were applied to 10-second 12-lead ECGs obtained on 1,217 adult survivors of childhood cancer prospectively followed in the St. Jude Lifetime Cohort (SJLIFE) study. Clinical and echocardiographic assessment of cardiac function was performed at initial and follow-up SJLIFE visits. Cardiomyopathy was defined as ejection fraction <50% or absolute drop from the baseline ≥10%. Genetic algorithm was used for feature selection and extreme gradient boosting (XGboost) was applied to predict cardiomyopathy during the follow-up period. Model performance was evaluated by five-fold stratified cross validation. Results: The median age at baseline SJLIFE evaluation was 31·7 years (range 18·4-66·4), and the time between baseline and follow-up evaluations was 5·2 years (0·5-9·5). Two-thirds (67·1%) of subjects were exposed to chest radiation and 76·6% to anthracycline chemotherapy. One hundred seventeen (9·6%) subjects developed cardiomyopathy during follow-up. In the model based solely on ECG features, the cross-validation AUC was 0·87 (CI 0·83-0·90), while the model based on clinical features had an AUC of 0·69 (CI 0·64-0·74). In the model based on ECG and clinical features, the cross-validation AUC was 0·89 (CI 0·86-0·91), with sensitivity 78% and specificity 81%. Conclusion: Artificial intelligence using ECG data may assist in the identification of childhood cancer survivors at increased risk for developing cardiomyopathy. Funding Statement: This study was supported by the National Cancer Institute (U01 CA195547, M. Hudson and L. Robison, Principal Investigators). Support to St. Jude Children’s Research Hospital was also provided by the Cancer Center Support (CORE) grant (CA21765, C. Roberts, Principal Investigator) and the American Lebanese Syrian Associated Charities (ALSAC). Declaration of Interests: The authors declare no competing interests. Ethics Approval Statement: The study was approved by the Institutional Review Board and all survivors provided informed consent prior to participation.