Baseline atrial volume indices and major adverse cardiac events following thoracic radiotherapy

Edmund M. Qiao¹John He²Katrina D. Silos³Jordan Gasho³Patrick Belen³Danielle Bitterman²Elizabeth McKenzie³Jennifer Steers³Christian Guthier²Anju Nohria²Michael T. Lu⁴Hugo J.W.L. Aerts²Andriana P. Nikolova³Raymond H. Mak^2*Katelyn M. Atkins^3*

• ¹University of California, San Diego, La Jolla, United States
• ²Brigham and Women's Hospital, Harvard Medical School, Boston, Massachusetts, United States
• ³Cedars Sinai Medical Center, Los Angeles, California, United States
• ⁴Massachusetts General Hospital, Harvard Medical School, Boston, Massachusetts, United States

Purpose: Patients receiving thoracic radiotherapy have increased risk of major adverse cardiac events (MACE) post-treatment. We utilized machine learning (ML) to discover novel predictors of MACE and validated on an external cohort.Methods: Multi-institutional retrospective study of 984 patients (n=803 non-small cell lung cancer (NSCLC), n=181 breast cancer) post-radiotherapy. Extreme gradient boosting was utilized to discover novel clinical, dosimetric, and anatomic features (CT-based cardiac substructure segmentations) associated with MACE in a cohort of locally advanced NSCLC patients. Fine-Gray regression was performed with non-cardiac death as a competing risk. External validation utilized independent cohorts of NSCLC or breast cancer.Results: In the discovery dataset (n=701), 70 patients developed MACE. ML modeling (training AUC: 0.68; testing AUC: 0.71) ranked right and left atrial volume indices (RAVI, LAVI) highly. Adjusting for baseline cardiovascular risk and known radiotherapy predictive factors, RAVI was associated with an increased risk of MACE (subdistribution hazard ratio [sHR]:1.02/unit, 95% confidence interval[CI]: 1.00-1.04; p=0.03). In the validation cohorts (n=102 NSCLC; n=181 breast), RAVI was associated with an increased risk of MACE (NSCLC: sHR 1.05, 95% CI:1.001-1.106, p=0.04; breast cancer: sHR 1.06, 95% CI:1.01-1.11, p=0.03). LAVI showed similar findings.Conclusions: ML modeling identified right and left atrial enlargement as novel radiographic predictors for increased risk of MACE following chest radiotherapy, which was validated in independent breast and lung cancer datasets. Given that echocardiography studies have demonstrated the prognostic utility of atrial volume indices across cardiovascular risk groups, these findings warrant further study to identify additional strategies for upfront cardiovascular risk profiling.