CarDS-Plus ECG Platform: Development and Feasibility Evaluation of a Multiplatform Artificial Intelligence Toolkit for Portable and Wearable Device Electrocardiograms DOI Creative Commons
Sumukh Vasisht Shankar, Evangelos K. Oikonomou, Rohan Khera

et al.

medRxiv (Cold Spring Harbor Laboratory), Journal Year: 2023, Volume and Issue: unknown

Published: Oct. 3, 2023

In the rapidly evolving landscape of modern healthcare, integration wearable and portable technology provides a unique opportunity for personalized health monitoring in community. Devices like Apple Watch, FitBit, AliveCor KardiaMobile have revolutionized acquisition processing intricate data streams that were previously accessible only through devices available to healthcare providers. Amidst variety collected by these gadgets, single-lead electrocardiogram (ECG) recordings emerged as crucial source information cardiovascular health. Notably, there has been significant advances artificial intelligence capable interpreting 1-lead ECGs, facilitating clinical diagnosis well detection rare cardiac disorders. This design study describes development an innovative multi-platform system aimed at rapid deployment AI-based ECG solutions investigation care delivery. The examines various considerations, aligning them with specific applications, develops flows maximize efficiency research use. process encompasses reception ECGs from diverse devices, channeling this into centralized lake, real-time inference AI models interpretation. An evaluation platform demonstrates mean duration reporting results 33.0 35.7 seconds, after standard 30 second acquisition, allowing complete be completed 63.0 65.7 seconds. There no substantial differences across two commercially (Apple Watch KardiaMobile). These demonstrate succcessful translation principles fully integrated efficient strategy leveraging platforms interpretation AI-ECG algorithms. Such is critical translating discoveries impact deployment.

Language: Английский

Portable Bioelectronic System for Real-Time Motion Tracking in Virtual Reality: Integrating Movella Sensors with Vizard for Neurorehabilitation and Sports Applications DOI Creative Commons
Wangdo Kim

IntechOpen eBooks, Journal Year: 2025, Volume and Issue: unknown

Published: Jan. 9, 2025

This study presents a portable bioelectronic system designed for real-time motion tracking in virtual reality (VR) environments, with focus on applications neurorehabilitation and sports performance analysis. By integrating Movella wearable sensors the Vizard VR platform, offers cost-effective flexible solution capturing analyzing human motion. Leveraging Bluetooth Low Energy (BLE), it connects multiple Inertial Measurement Units (IMUs) to computer, enabling precise kinematic computations essential therapeutic exercises, biomechanical research, optimization sports. The integration of Python scripting within allows development interactive three-dimensional (3D) content that dynamically respond live data. In addition, incorporates Laban’s A Scale from Laban Movement Analysis (LMA) guide upper arm movement training, enhancing user engagement rehabilitation outcomes. Validation through experiments using soft exoskeletons demonstrated high accuracy reliability, making this robust tool telemedicine, healthcare, applications. open-source availability our code supports further innovation device technology personalized therapy.

Language: Английский

Citations

0
Consumer-grade wearable devices in arrhythmia diagnostics for clinicians: where we are and where we are going DOI
Eric Rytkin, И. В. Зотова, Rod Passman

et al.

Journal of Interventional Cardiac Electrophysiology, Journal Year: 2025, Volume and Issue: unknown

Published: Jan. 25, 2025

Language: Английский

Citations

0
Innovations in Quantitative Rapid Testing: Early Prediction of Health Risks DOI

Khaled S Alleilem,

Saad Almousa,

Mohammed Alissa

et al.

Current Problems in Cardiology, Journal Year: 2025, Volume and Issue: unknown, P. 103000 - 103000

Published: Feb. 1, 2025

Language: Английский

Citations

0
Reclassification of the conventional risk assessment for aging-related diseases by electrocardiogram-enabled biological age DOI Creative Commons
Chih‐Min Liu,

Ming‐Jen Kuo,

Chin-Yu Kuo

et al.

npj Aging, Journal Year: 2025, Volume and Issue: 11(1)

Published: Feb. 6, 2025

An artificial intelligence (AI)-enabled electrocardiogram (ECG) model has been developed in a healthy adult population to predict ECG biological age (ECG-BA). This ECG-BA exhibited robust correlation with chronological (CA) adults and additionally significantly enhanced the prediction of aging-related diseases' onset subclinical diseases. The showed particularly strong predictive power for cardiovascular non-cardiovascular diseases such as stroke, coronary artery disease, peripheral arterial occlusive myocardial infarction, Alzheimer's osteoarthritis, cancers. When combined CA, improved diagnostic accuracy risk classification by 21% over using CA alone, notably offering greatest improvements cancer prediction. net reclassification improvement reduced misclassification rates disease predictions. comprehensive study validates an effective supplement advancing precision assessments conditions suggesting broad implications enhancing preventive healthcare strategies, potentially leading better patient outcomes.

Language: Английский

Citations

0
Opportunities and challenges of noise interference suppression algorithms for dynamic ECG signals in wearable devices: A review DOI
J. Zhang, Yu Guo, Xinming Dong

et al.

Measurement, Journal Year: 2025, Volume and Issue: unknown, P. 117067 - 117067

Published: Feb. 1, 2025

Language: Английский

Citations

0
Sudden cardiac arrest prediction via deep learning electrocardiogram analysis DOI Creative Commons
Matt T. Oberdier, Luca Neri, Alessandro Orro

et al.

European Heart Journal - Digital Health, Journal Year: 2025, Volume and Issue: unknown

Published: Feb. 25, 2025

Sudden cardiac arrest (SCA) is a commonly fatal event that often occurs without prior indications. To improve outcomes and enable preventative strategies, the electrocardiogram (ECG) in conjunction with deep learning was explored as potential screening tool. A publicly available data set containing 10 s of 12-lead ECGs from individuals who did not have an SCA, information about time ECG to arrest, age sex utilized for analysis individually predict SCA or using convolution neural network models. The base model included sex, within 1 day sampled windows 720 ms around R-waves 221 1046 controls had area under receiver operating characteristic curve 0.77. With sensitivity at 95%, specificity 31%, which clinically applicable. Gradient-weighted class activation mapping showed mostly relied on QRS complex make predictions. However, models recorded between month year demonstrated predictive capabilities. Deep processing are promising means this method explains differences SCAs due sex. Model performance improved when were nearer SCAs, although up value. prediction more dependent upon compared other segments.

Language: Английский

Citations

0
Plantar Pressure Analysis and the Ankle Instability Index: Quantifying “Giving Away” in Functional Ankle Instability DOI

Xiaojiang Yang,

Zhongyang Lv,

Ziying Sun

et al.

Foot & Ankle International, Journal Year: 2025, Volume and Issue: unknown

Published: March 18, 2025

Background: Individuals with functional ankle instability (FAI) typically present abnormal plantar pressure distribution, while “giving away” is the most significant symptom. This study aims to explore relationship between and deviation of center (COP) trajectory during stance, which could potentially serve as an objective parameter for quantifying giving away identifying FAI. Methods: A total 243 participants (20.3±1.1 years) were categorized into FAI group Coper based on stability status presence away. Plantar analysis was conducted measure maximum medial-lateral COP forefoot contact phase foot flat phase, defined Ankle Instability Index (AII). The difference in AII 2 groups assessed using independent-sample t test. self-reported explored, a discriminant function performed determine optimal cut-off value FAI, subsequently diagnostic accuracy explored. Results: observed (FAI: 18.06±4.82, Coper: 9.13±3.82, P < .001), correlation found scores Cumberland Tool (CAIT) Identification Functional (IdFAI) ( r = −0.927 0.976, respectively, .001). exhibited robust area under receiver operating characteristic curve 0.931. threshold 11.4, yielding overall 91.99%. Conclusion: findings revealed severity AII, effective status. Level Evidence: III, retrospective case-control.

Language: Английский

Citations

0
Wear the Future of Healthcare: Revolutionizing Healthcare with AI-Driven Wearables for Enhanced Health and Wellness DOI
Jack Ng Kok Wah

SSRN Electronic Journal, Journal Year: 2025, Volume and Issue: unknown

Published: Jan. 1, 2025

Language: Английский

Citations

0
Adoption barriers and facilitators of wearable health devices with AI integration: a patient-centred perspective DOI Creative Commons
Haitham Alzghaibi

Frontiers in Medicine, Journal Year: 2025, Volume and Issue: 12

Published: April 3, 2025

Wearable devices that incorporate artificial intelligence (AI) have revolutionised healthcare through continuous monitoring, early detection, and tailored management of chronic diseases. This cross-sectional study analysed patients' perceptions, trust, awareness AI-driven wearable health technologies, emphasising the identification primary facilitators barriers to adoption. A total 455 participants, comprising individuals with conditions, were recruited convenience stratified sampling methods. Data collected via an online questionnaire included demographic questions, Likert-scale items, multiple-choice questions evaluate particular AI features functionalities devices. The findings indicated predominantly positive most participants concurring improve proactive care, facilitate remote consultations, deliver precise insights. Concerns regarding technical failures, data accuracy, potential reduction human interaction significant. No notable differences identified; however, conditions expressed more favourable perceptions. research emphasises necessity user education, reliability, professional oversight for successful integration AI-powered wearables in

Language: Английский

Citations

0
Artificial Intelligence in Cardiac Emergencies: A Review DOI Creative Commons
Chandrasekhar Krishnamurti, Salehe I. Mrutu

Indian Journal of Clinical Cardiology, Journal Year: 2025, Volume and Issue: unknown

Published: April 3, 2025

Sudden cardiac arrest is a major public health problem as it accounts for nearly 1,000 deaths per day worldwide. An estimated 80% of these occur outside hospitals, with less than 20% survival out-of-hospital victims and around 30% in-hospital victims. Delays in recognizing sudden initiating high-quality cardiopulmonary resuscitation result significant neurological problems like post-anoxic coma vegetative states. Human expertise integrated artificial intelligence will contribute to dramatic improvement outcomes by aiding emergency physicians making critical decisions the management prognostication patient outcomes.

Language: Английский

Citations

0