Computer-Aided Diagnosis of Parkinson’s Disease Using Enhanced Probabilistic Neural Network

• Published in: Journal of medical systems Vol. 39; no. 11; pp. 179 - 12
• Main Authors: Hirschauer, Thomas J., Adeli, Hojjat, Buford, John A.
• Format: Journal Article
• Language: English
• Published: New York Springer US 01.11.2015; Springer Nature B.V
• Subjects: Accuracy; Algorithms; CAI; Classification; Computer assisted instruction; Diagnosis; Diagnosis, Computer-Assisted - methods; Diagnosis, Differential; False Positive Reactions; Health Informatics; Health Sciences; Humans; Medical diagnosis; Medicine; Medicine & Public Health; Neural networks; Neural Networks (Computer); Parkinson Disease - diagnosis; Parkinson's disease; Patient Facing Systems; Physical Examination; Probabilistic methods; Probability theory; ROC Curve; Statistics for Life Sciences; Support Vector Machine; Support vector machines; Enhanced probabilistic neural networks; Computer-aided diagnosis; Parkinson’s disease
• ISSN: 0148-5598; 1573-689X
• DOI: 10.1007/s10916-015-0353-9

Early and accurate diagnosis of Parkinson’s disease (PD) remains challenging. Neuropathological studies using brain bank specimens have estimated that a large percentages of clinical diagnoses of PD may be incorrect especially in the early stages. In this paper, a comprehensive computer model is presented for the diagnosis of PD based on motor, non-motor, and neuroimaging features using the recently-developed enhanced probabilistic neural network (EPNN). The model is tested for differentiating PD patients from those with scans without evidence of dopaminergic deficit (SWEDDs) using the Parkinson’s Progression Markers Initiative (PPMI) database, an observational, multi-center study designed to identify PD biomarkers for diagnosis and disease progression. The results are compared to four other commonly-used machine learning algorithms: the probabilistic neural network (PNN), support vector machine (SVM), k-nearest neighbors (k-NN) algorithm, and classification tree (CT). The EPNN had the highest classification accuracy at 92.5 % followed by the PNN (91.6 %), k-NN (90.8 %) and CT (90.2 %). The EPNN exhibited an accuracy of 98.6 % when classifying healthy control (HC) versus PD, higher than any previous studies.