BackgroundWearable textile electrodes for the detection of biopotentials are a promising tool for the monitoring and early diagnosis of chronic diseases. We present a comparative study of the electrical characteristics of four textile electrodes manufactured from common fabrics treated with a conductive polymer, a commercial fabric, and disposable Ag/AgCl electrodes. These characteristics will allow identifying the performance of the materials when used as ECG electrodes. The electrodes were subjected to different electrical tests, and complemented with conductivity calculations and microscopic images to determine their feasibility in the detection of ECG signals.MethodsWe evaluated four electrical characteristics: contact impedance, electrode polarization, noise, and long-term performance. We analyzed PEDOT:PSS treated fabrics based on cotton, cotton–polyester, lycra and polyester; also a commercial fabric made of silver-plated nylon Shielde® Med-Tex P130, and commercial Ag/AgCl electrodes. We calculated conductivity from the surface resistance and, analyzed their surface at a microscopic level. Rwizard was used in the statistical analysis.ResultsThe results showed that textile electrodes treated with PEDOT:PSS are suitable for the detection of ECG signals. The error detecting features of the ECG signal was lower than 2% and the electrodes kept working properly after 36 h of continuous use. Even though the contact impedance and the polarization level in textile electrodes were greater than in commercial electrodes, these parameters did not affect the acquisition of the ECG signals. Fabrics conductivity calculations were consistent to the contact impedance.

In this paper we evaluate the suitability of handwriting patterns as potential biomarkers to model Parkinson's disease (PD). Although the study of PD is attracting the interest of many researchers around the world, databases to evaluate handwriting patterns are scarce and knowledge about patterns associated to PD is limited and biased to the existing datasets. This paper introduces a database with a total of 935 handwriting tasks collected from 55 PD patients and 94 healthy controls (45 young and 49 old). Three feature sets are extracted from the signals: neuromotor, kinematic, and nonlinear dynamic. Different classifiers are used to discriminate between PD and healthy subjects: support vector machines, knearest neighbors, and a multilayer perceptron. The proposed features and classifiers enable to detect PD with accuracies between 81% and 97%. Additionally, new insights are presented on the utility of the studied features for monitoring and detecting PD.

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 (HF) 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 HF 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. The subjects performed the spiral drawing task (SDT; a language-independent task) and the sentence writing task (SWT; a language-dependent task). Models based on logistic regression and gradient boosting were trained in several scenarios, specifically single language (SL), leave one language out (LOLO), and all languages combined (ALC). We found that the HF slightly outperformed the CNN-extracted features in all considered evaluation scenarios for the SWT. In detail, the following balanced accuracy (BACC) scores were achieved: SL—0.65 (HF), 0.58 (CNN); LOLO—0.65 (HF), 0.57 (CNN); and ALC—0.69 (HF), 0.66 (CNN). However, in the case of the SDT, features extracted by a CNN provided competitive results: SL—0.66 (HF), 0.62 (CNN); LOLO—0.56 (HF), 0.54 (CNN); and ALC—0.60 (HF), 0.60 (CNN). In summary, regarding the SWT, the HF outperformed the CNN-extracted features over 6% (mean BACC of 0.66 for HF, and 0.60 for CNN). In the case of the SDT, both feature sets provided almost identical classification performance (mean BACC of 0.60 for HF, and 0.58 for CNN).