Prediction of Parkinson’s Disease Depression Using LIME-Based Stacking Ensemble Model

Abstract

Depression symptoms are comparable to Parkinson’s disease symptoms, including attention deficit, fatigue, and sleep disruption, as well as symptoms of dementia such as apathy. As a result, it is difficult for Parkinson’s disease caregivers to diagnose depression early. We examined a LIME-based stacking ensemble model to predict the depression of patients with Parkinson’s disease. This study used the epidemiologic data of Parkinson’s disease dementia patients (EPD) from the Korea Disease Control and Prevention Agency’s National Biobank, which included 526 patients’ information. We used Logistic Regression (LR) as the meta-model, and five base models, including LightGBM (LGBM), K-nearest Neighbors (KNN), Random Forest (RF), Extra Trees (ET), and AdaBoost. After cleansing the data, the stacking ensemble model was trained using 261 participants’ data and 10 variables. According to the research, the best combination of the stacking ensemble model is ET + LGBM + RF + LR, a harmonious model. In order to achieve model prediction explainability, we also combined the stacking ensemble model with a LIME-based explainable model. This explainable stacking ensemble model can help identify the patients and start treatment on them early in a way that medical professionals can comprehend.