Parkinson's disease is the primary cause of global mortality connected to the brain. Timely identification and diagnosis of Parkinson's disease can significantly enhance the likelihood of patient survival. The utilisation of machine learning in the medical field for the identification of Parkinson's disease has been on the rise. However, the primary obstacle that persists is the lack of interpretability of these models. Explainable machine learning (XML) is an emerging methodology that seeks to offer clarity and comprehensibility for machine learning models. The entire experiment was conducted using the Parkinson dataset acquired from reliable public repository. The results of the predictive model, which include the SMOTE class balancing technique, are utilised to understand the key clinical variables that influenced the prediction of Parkinson's disease. This is achieved by the application of a machine learning explainable technique called SHAP (SHapley Additive exPlanation). The results demonstrate the strong ability of GBM to identify parkinson disease, with an accuracy of ...%, precision of ...%, recall of ...%, F-Measure of ...%, and an error rate of ...% (Undergoing implementation, not completed yet). These findings establish the effectiveness of our technique.
Partnerships
