AUTHOR=Galaz Zoltan , Drotar Peter , Mekyska Jiri , Gazda Matej , Mucha Jan , Zvoncak Vojtech , Smekal Zdenek , Faundez-Zanuy Marcos , Castrillon Reinel , Orozco-Arroyave Juan Rafael , Rapcsak Steven , Kincses Tamas , Brabenec Lubos , Rektorova Irena 

TITLE=Comparison of CNN-Learned vs. Handcrafted Features for Detection of Parkinson's Disease Dysgraphia in a Multilingual Dataset

JOURNAL=Frontiers in Neuroinformatics

VOLUME=Volume 16 - 2022

YEAR=2022

URL=https://www.frontiersin.org/journals/neuroinformatics/articles/10.3389/fninf.2022.877139

DOI=10.3389/fninf.2022.877139

ISSN=1662-5196

ABSTRACT=Parkinson's disease dysgraphia (PDYS), one of the earliest signs of Parkinson's disease (PD), has been researched as a promising biomarker of PD and as the target of a noninvasive and inexpensive approach to monitoring the progress of the disease. However, although several approaches to supportive PDYS diagnosis have been proposed (mainly based on handcrafted features extracted from online handwriting or the utilization of deep neural networks), it remains unclear which approach provides the highest discrimination power and how these approaches can be transferred between different datasets and languages. This study aims to compare classification performance based on two types of features: features automatically extracted by a pretrained convolutional neural network (CNN) and handcrafted features designed by human experts. Both approaches are evaluated on a multilingual dataset collected from 143 PD patients and 151 healthy controls in the Czech Republic, United States, Colombia, and Hungary. Models based on logistic regression and gradient boosting were trained in several scenarios, including the leave-one-language-out methodology. We found that the handcrafted features slightly outperformed the CNN-extracted features in all considered evaluation scenarios for the sentence writing task. However, in the case of the spiral drawing task, features extracted by a CNN provided competitive results.