A novel cepstral-based technique for automatic cognitive load estimation

Sarcopenia Diagnostic Technique Based on Artificial Intelligence Using Bio-signal of Neuromuscular System: A Proof-of-Concept Study

In this paper, we propose an artificial intelligence (AI)-based sarcopenia diagnostic technique for stroke patients utilizing bio-signals from the neuromuscular system. Handgrip, skeletal muscle mass index, and gait speed are prerequisite components for sarcopenia diagnoses. However, measurement of these parameters is often challenging for most hemiplegic stroke patients. For these reasons, there is an imperative need to develop a sarcopenia diagnostic technique that requires minimal volitional participation but nevertheless still assesses the muscle changes related to sarcopenia. The proposed AI diagnostic technique collects motor unit responses from stroke patients in a resting state via stimulated muscle contraction signals (SMCSs) recorded from surface electromyography while applying electrical stimulation to the muscle. For this study, we extracted features from SMCS collected from stroke patients and trained our AI model for sarcopenia diagnosis. We validated the performance of the trained AI models for each gender against other diagnostic parameters. The accuracy of the AI sarcopenia model was 96%, and 95% for male and females, respectively. Through these results, we were able to provide preliminary proof that SMCS could be a potential surrogate biomarker to reflect sarcopenia in stroke patients.

A novel method based on matching pursuit decomposition of gait signals for Parkinson's disease, Amyotrophic lateral sclerosis and Huntington's disease detection

BACKGROUND AND OBJECTIVE

An accurate detection of neurodegenerative diseases (NDDs) definitely improves the life of patients and has attracted growing attention.

METHODS

In this paper, a general automatic method for detection of Parkinson's disease (PD), Amyotrophic lateral sclerosis (ALS) and Huntington's disease (HD) has been proposed based on the localized time-frequency information of gait signals. The new main part of the detection method is to obtain a small set of sparse coefficients for the local representation of gait signals with appropriate time and frequency resolution. For this purpose, a hybrid feature set based on sparse matching pursuit decomposition and two sets of nonlinear and linear features has been developed. Then, principal components of the proposed feature have been analyzed using a sparse coding classifier. Results The proposed approach has achieved high average accuracy rates of 93%, 94%, and 97% for PD, ALS, and HD detection, respectively.

CONCLUSIONS

The obtained results have indicated that combination of time and frequency information of the gait signals through adaptive localized window length in MP makes it more efficient in comparison with the existing time, frequency or other time-frequency gait parameters. The great potential of nonlinear sparse features for PD and HD detection and linear ones for ALS detection has also been shown.