A novel ensemble of random forest for assisting diagnosis of Parkinson's disease on small handwritten dynamics dataset. (December 2020)

• Record Type: Journal Article
• Authors: Xu, Shoujiang; Pan, Zhigeng
• Is Part Of: International journal of medical informatics. Volume 144(2020)
• Publication Date: 2020-12
• Subjects: Parkinson's disease -- Ensemble learning -- Random forest -- Handwritten dynamics -- Sensor signals; Medical informatics -- Periodicals; Information science -- Periodicals; Computers -- Periodicals; Medical technology -- Periodicals; Medical Informatics -- Periodicals; Technology, Medical -- Periodicals; Computers; Information science; Medical informatics; Medical technology; Electronic journals; Periodicals; Electronic journals; 610.285
• DOI: 10.1016/j.ijmedinf.2020.104283
• Languages: English
• ISSNs: 1386-5056

Abstract

Highlights: Many motor symptoms of Parkinson's disease have been utilized to develop machine learning models. Micrographia is a typical motor symptom which can be measured by handwritten dynamics exams. Ensemble learning models based on different handwritten exams can improve the recognition performance. Computer-aided model based on handwritten dynamics is a potential way to diagnose Parkinson's disease. Abstract: Background: Parkinson's disease (PD) is a neurodegenerative disease of the elderly, which leads to patients' motor and non-motor disabilities and affects patients' quality of daily life. Timely and effective detection of PD is a key step to medical intervention. Recently, computer aided methods for PD detection have gained lots of attention in artificial intelligence domain. Methods: This paper proposed a novel ensemble learning model fusing Random Forest (RF) classifiers and Principal Component Analysis (PCA) technique to differentiate PD patients from healthy controls (HC). Six different RF models were separately constructed to generate the corresponding class probability vectors which represent an individual's category predictions on 6 different handwritten exams, and the final prediction result for an individual was obtained through voting strategy of all RF models. Stratified k-fold cross validation was performed to split the exam datasets and evaluate the classification performances. Results: Experimental results prove that our proposed ensemble model on six handwritten exams has achieved better classification performances than a single RF based method on a single handwritten exam. Our ensemble of RF model based on multiple handwritten exams has promising accuracy (89.4 %), specificity (93.7 %), sensitivity (84.5 %) and F1-score (87.7 %). Compared with Logistic Regression (LR) and Support Vector Machines (SVM), the ensemble model based on RF can achieve better classification results. Conclusion: A computer-assisted PD diagnosis model on small handwritten dynamics dataset is proposed, and it provides a potential way for assisting diagnosis of PD in clinical setting.