3298 - Predicting Chemoradiotherapy Induced Cardiotoxicity in Breast Cancer Patients Using Machine Learning Based Clinical, Imaging and Dosimetric Radiomics Features

M. Tavakoli¹, A. Talebi², A. Bitarafan-Rajabi³, A. Alizadeh-asl⁴, P. Seilani⁴, B. Khajetash⁵, G. Hajianfar⁶, and B. Ghavidel⁷; ¹Department of Radiation Oncology and Winship Cancer Institute, Emory University, Atlanta, GA, ²ran University of Medical Sciences, Tehran, Iran (Islamic Republic of), ³Iran University of Medical Sciences, Tehran, Iran (Islamic Republic of), ⁴Iran University of Medical Science, Tehran, Iran (Islamic Republic of), ⁵Medical Physics Department, Faculty of Medicine, Iran University of Medical Sciences, Tehran, Iran (Islamic Republic of), ⁶Geneva University Hospital, Geneva, Swaziland, ⁷Department of Radiation Oncology, Winship Cancer Institute of Emory University, Atlanta, GA

Purpose/Objective(s): Breast cancer is the leading cause of cancer death in worldwide. In order to enhance the chances of a favorable outcome for the survivors, it is essential to carefully balance the potential advantages of treatment methods with the risks of harm to healthy tissues, including the heart. There is currently a lack of comprehensive, data-driven evidence on effective risk stratification strategies. The aim of this study is to investigate whether prediction of cardiotoxicity could improve with machine learning methods using radiomics imaging and clinical features along with dosimetric parameters. Materials/

Methods: 50 left side breast cancer patients without history of cardiac disease were participated in this study. 2D and 3D echocardiography before and after 6 month of treatment completion was performed to evaluate cardiac toxicity. Cardiac dose volume histograms (DVH), demographic data, echocardiographic parameters and echocardiograph’s radiomics features were collected for all patients. Toxicity modelling performed with feature selection methods and five classifiers (K- Nearest Neighbor, Decision Tree, Neural Network, Random Forrest, and Support Vector Machine (SVM)) in 4 separated groups (DVH, DVH + Demographic, DVH + Demographic+ Clinical, DVH + Demographic + Clinical + ultrasound imaging). Prediction performance of models were validated by 5-fold cross validation and evaluated by AUCs.
Results: 58% of papulation showed cardiotoxicity after 6 months of treatment. Mean left ventricular Ejection Fraction and Global Longitudinal Strain were decreased significantly after treatment (P-Value < 0.001). After feature selection and prediction modelling using SVM, the DVH, DVH + Demographic, DVH + Demographic + Clinical, DVH + Demographic + Clinical + Radiomics models showed prediction performance (AUC) up to 70%, 75%, 85% and 95% respectively.
Conclusion: Incorporation of patient’s data, cardiac and dose descriptors combined with machine learning algorithms is beneficial for cardiac toxicity prediction after chemo-radiotherapy.