SMOTE and ENN based XGBoost prediction model for Parkinson’s disease detection

It is always desirable that the diagnosis of Parkinson’s be highly accurate. This can help reduce the severity of the disorder by timely treatment. It is often seen that handwriting of the patient diminishes as it becomes difficult to grip the pen/pencil due to muscle rigidity. There is proof of innate neurological dissimilarities between men and women and the aged and the young. There also lies a significant link between dominant hand of the person and the side of the body where initial manifestation of the disease. In this research work, a prediction method is developed incorporating age, gender and dominant hand as features to identify Parkinson’s disease. The HandPD dataset used here is inherently imbalanced. This gives rise to the issue of prediction model biasedness. The true nature of such a model is not quite revealed by the conventional accuracy alone. Thus, balanced accuracy is used to evaluate true efficiency. The technique proposed here alleviates model bias using hybrid resampling and extreme gradient boosting. It also computes balanced accuracy as a performance parameter. The conventional accuracy is 98.24% (meanders) and 95.37% (spirals) when age is used along with nine statistical parameters extracted from the dataset. It becomes 97.02% (meanders) and 97.12% (spirals) when age, gender and handedness information are utilised. Further, post balancing the training set, the balanced accuracy and conventional accuracy tend to become approximately same.