A novel feature extraction method based on dynamic handwriting for Parkinson’s disease detection

• Published in: PloS one Vol. 20; no. 1; p. e0318021
• Main Authors: Lu, Huimin, Qi, Guolian, Wu, Dalong, Lin, Chenglin, Ma, Songzhe, Shi, Yingqi, Xue, Han
• Format: Journal Article
• Language: English
• Published: United States Public Library of Science 24.01.2025; Public Library of Science (PLoS)
• Subjects: Aged; Algorithms; Biology and Life Sciences; Biomechanical Phenomena; Datasets; Diagnosis; Disease detection; Engineering and Technology; Evaluation; Feature extraction; Fourier transforms; Global optimization; Handwriting; Health aspects; Humans; Information processing; Kinematics; Mathematical optimization; Medicine and Health Sciences; Methods; Movement disorders; Neural networks; Neurodegenerative diseases; Optimization algorithms; Parkinson Disease - diagnosis; Parkinson Disease - physiopathology; Parkinson's disease; Patients; Penmanship; Physical Sciences; Research and Analysis Methods; Signal processing; Statistical analysis; Wavelet transforms; Writing; China
• ISSN: 1932-6203; 1932-6203
• DOI: 10.1371/journal.pone.0318021

Parkinson’s disease (PD) is a common disease of the elderly. Given the easy accessibility of handwriting samples, many researchers have proposed handwriting-based detection methods for Parkinson’s disease. Extracting more discriminative features from handwriting is an important step. Although many features have been proposed in previous researches, the insight analysis of the combination of handwriting’s kinematic, pressure, and angle dynamic features is lacking. Moreover, most existing feature is incompletely represented, with feature information lost. Therefore, to solve the above problems, a new feature extraction approach for PD detection is proposed using handwriting. First, built on the kinematic, pressure, and angle dynamic features, we propose a moment feature by composed these three types of features, an overall representation of these three types of features information. Then, we proposed a feature extraction method to extract time-frequency-based statistical (TF-ST) features from dynamic handwriting features in terms of their temporal and frequency characteristics. Finally, we proposed an escape Coati Optimization Algorithm (eCOA) for global optimization to enhance classification performance. Self-constructed and public datasets are used to verify the proposed method’s effectiveness respectively. The experimental results showed an accuracy of 97.95% and 98.67%, a sensitivity of 98.15% (average) and 97.78%, a specificity of 99.17% (average) and 100%, and an AUC of 98.66% (average) and 98.89%. The code is available at https://github.com/dreamhcy/MLforPD .