AiCarePWP: Deep learning-based novel research for Freezing of Gait forecasting in Parkinson.

Autor: Ghayvat H; Department of Computer Science and Media Technology, Faculty of Technology, Linnaeus University, Växjö, 351 95, Sweden. Electronic address: hemant.ghayvat@lnu.se., Awais M; Department of Imaging Physics, The University of Texas, MD Anderson Cancer Center, Houston, 77030, TX, USA. Electronic address: m.awais0100@gmail.com., Geddam R; Computer Science Department, Institute of Technology, Nirma University, Ahmedabad, 382481, Gujarat, India. Electronic address: rebakah.geddam@nirmauni.ac.in., Khan MA; Scientific Researcher, Department of Electrical Engineering, Stanford University, 350, Jane Stanford Way, Stanford, CA 94305, USA. Electronic address: muhkhan@stanford.edu., Nkenyereye L; Department of Computer and Information Security, Sejong University, South Korea. Electronic address: nkenyele@sejong.ac.kr., Fortino G; Department of Informatics, Modeling, Electronics and Systems, University of Calabria, Italy. Electronic address: giancarlo.fortino@unical.it., Dev K; Department of Computer Science and ADAPT Centre, Munster Technological University, Bishopstown Cork, T12 P928, Ireland; Department of Electrical and Computer Engineering, Lebanese American University, Byblos, Lebanon; Department of Institute of Intelligent Systems, University of Johannesburg, Auckland Park, 2006, South Africa. Electronic address: Kapal.dev@ieee.org.
Jazyk: angličtina
Zdroj: Computer methods and programs in biomedicine [Comput Methods Programs Biomed] 2024 Sep; Vol. 254, pp. 108254. Date of Electronic Publication: 2024 Jun 07.
DOI: 10.1016/j.cmpb.2024.108254
Abstrakt: Background and Objectives: Episodes of Freezing of Gait (FoG) are among the most debilitating motor symptoms of Parkinson's Disease (PD), leading to falls and significantly impacting patients' quality of life. Accurate assessment of FoG by neurologists provides crucial insights into patients' conditions and disease symptoms. This proposed strategy involves utilizing a Weighted Fuzzy Logic Controller, Kalman Filter, and Kaiser-Meyer-Olkin test to detect the gait parameters while walking, resting, and standing phases. Parameters such as neuromodulation format, intensity, duration, frequency, and velocity are computed to pre-empt freezing episodes, thus aiding their prevention.
Method: The AiCarePWP is a wearable electronics device designed to identify instances when a patient is on the brink of experiencing a freezing episode and subsequently deliver a brief electrical impulse to the patient's shank muscles to stimulate movement. The AiCarePWP wearable device aims to identify impending freezing episodes in PD patients and deliver brief electrical impulses to stimulate movement. The study validates this innovative approach using plantar insoles with a 3D accelerometer and electrical stimulator, analysing data from the inertial measuring unit and plantar-pressure foot data to detect and predict FoG.
Results: Using a Convolutional Neural Network-based model, the study evaluated 47 gait features for their ability to differentiate resting, standing, and walking conditions. Variable selection was based on sensitivity, specificity, and overall accuracy, followed by Principal Component Analysis and Varimax rotation to extract and interpret factors. Factors with eigenvalues exceeding 1.0 were retained, and 37 features were retained.
Conclusion: This study validates CNN's effectiveness in detecting FoG during various activities. It introduces a novel cueing method using electrical stimulation, which improves gait function and reduces FoG incidence in PD patients. Trustworthy wearable devices, based on Artificial Intelligence of Things (AIoT) and Artificial Intelligence of Medical Things (AIoMT), have been developed to support such interventions.
Competing Interests: Declaration of competing interest We hereby acknowledge that disclosing any conflicts of interest promotes transparency and does not inherently suggest unethical conduct or bias in the execution of this study. Efforts have been made to effectively address any potential conflicts of interest encountered during the study process and to uphold the integrity and impartiality of our work. The study findings and conclusions outlined in this paper are derived from a meticulous application of scientific methodologies and substantiated by compelling empirical evidence.
(Copyright © 2024 Elsevier B.V. All rights reserved.)
Databáze: MEDLINE
Externí odkaz: