Prediction of ECOG Performance Status of Lung Cancer Patients Using LIME-Based Machine Learning
Hung Viet Nguyen, Haewon Byeon
Abstract
The Eastern Cooperative Oncology Group (ECOG) performance status is a widely used method for evaluating the functional abilities of cancer patients and predicting their prognosis. It is essential for healthcare providers to frequently assess the ECOG performance status of lung cancer patients to ensure that it accurately reflects their current functional abilities and to modify their treatment plan accordingly. This study aimed to develop and evaluate an AdaBoost classification (ADB-C) model to predict a lung cancer patient’s performance status following treatment. According to the results, the ADB-C model has the highest “Area under the receiver operating characteristic curve” (ROC AUC) score at 0.7890 which outperformed other benchmark models including Logistic Regression, K-Nearest Neighbors, Decision Trees, Random Forest, XGBoost, and TabNet. In order to achieve model prediction explainability, we combined the ADB-C model with a LIME-based explainable model. This explainable ADB-C model may assist medical professionals in exploring effective cancer treatments that would not negatively impact the post-treatment performance status of a patient.