HYBRID RESAMPLING AND XGBOOST PREDICTION MODEL USING PATIENT'S INFORMATION AND DRAWING AS FEATURES FOR PARKINSON'S DISEASE DETECTION

Abstract

In the list of most commonly occurring neurodegenerative disorders, Parkinson’s disease ranks second while Alzheimer’s disease tops the list. It has no definite examination for an exact diagnosis. It has been observed that the handwriting of an individual suffering from Parkinson's disease deteriorates considerably. Therefore, many computer vision and micrography-based methods have been used by researchers to explore handwriting as a detection parameter. Yet, these methods suffer from two major drawbacks, i.e., the prediction model's biasedness due to the imbalance in the data and low rate of classification accuracy. The proposed technique is designed to alleviate prediction bias and low classification accuracy by use of hybrid resampling (Synthetic Minority Oversampling Technique and Wilson's Edited Nearest Neighbours) techniques and Extreme Gradient Boosting (XGBoost). Additionally, there is proof of innate neurological dissimilarities between men and women and the aged and the young. There is also a significant link of the dominant hand of the person and the side of the body where initial manifestation begins. Further, the gender, age, and handedness information have not been utilized for Parkinson’s disease detection. In this research work, a prediction method is developed incorporating age, gender, and dominant hand as features to identify Parkinson’s disease. The proposed hybrid resampling and XGBoost method's experimental results yield an accuracy of 98.24% highest so far when age is taken as a parameter along with nine statistical parameters (root mean square, largest value of radius difference between ET and HT, smallest value of radius difference between ET and HT, standard deviation of ET and HT radius difference, mean relative tremor, maximum ET, minimum HT, standard deviation of exam template values, number of instances where the HT and ET radius difference undergoes a change from negative value to positive value or vice versa) achieved on the HandPD dataset. 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. The proposed method results were compared with existing methods, and it is evident that the method outperforms its predecessors.