Deep Learning-Driven Single-Lead ECG Classification: A Rapid Approach for Comprehensive Cardiac Diagnostics

Diagnostics, Journal Year: 2025, Volume and Issue: 15(3), P. 384 - 384

Published: Feb. 6, 2025

Background/Objectives: This study aims to address the critical need for accessible, early, and accurate cardiac di-agnostics, especially in resource-limited or remote settings. By shifting focus from traditional multi-lead ECG analysis single-lead data, this research explores potential of advanced deep learning models classifying conditions, including Nor-mal, Abnormal, Previous Myocardial Infarction (PMI), (MI). Methods: Five state-of-the-art architectures—Inception, DenseNet201, MobileNetV2, NASNetLarge, VGG16—were systematically evaluated on individual leads. Key performance metrics, such as model accuracy, inference time, size, were analyzed determine optimal configurations practical applications. Results: VGG16 emerged most model, achieving an F1-score 98.11% lead V4 with a prediction time 4.2 ms size 528 MB, making it suitable high-precision clinical compact 13.4 offered balanced performance, 97.24% faster 3.2 ms, positioning ideal candidate real-time monitoring telehealth Conclusions: bridges gap diagnostics by demonstrating feasibility lightweight, scalable, using models. The findings pave way deploying portable diagnostic tools across diverse settings, enhancing accessibility efficiency care globally.

Language: Английский

Transformer and Attention-Based Architectures for Segmentation of Coronary Arterial Walls in Intravascular Ultrasound: A Narrative Review

Diagnostics, Journal Year: 2025, Volume and Issue: 15(7), P. 848 - 848

Published: March 26, 2025

Background: The leading global cause of death is coronary artery disease (CAD), necessitating early and precise diagnosis. Intravascular ultrasound (IVUS) a sophisticated imaging technique that provides detailed visualization arteries. However, the methods for segmenting walls in IVUS scan into internal wall structures quantifying plaque are still evolving. This study explores use transformers attention-based models to improve diagnostic accuracy segmentation scans. Thus, objective explore application transformer scans assess their inherent biases artificial intelligence systems improving accuracy. Methods: By employing Preferred Reporting Items Systematic Reviews Meta-Analyses (PRISMA) framework, we pinpointed examined top strategies using transformer-based techniques, assessing traits, scientific soundness, clinical relevancy. Coronary thickness determined by boundaries (inner: lumen-intima outer: media-adventitia) through cross-sectional Additionally, it first investigate deep learning (DL) associated with segmentation. Finally, incorporates explainable AI (XAI) concepts DL structure Findings: Because its capacity automatically extract features at numerous scales encoders, rebuild segmented pictures via decoders, fuse variations skip connections, UNet model stands out as an efficient Conclusions: investigation underscores deficiency incentives embracing XAI pruned (PAI) models, no attaining bias-free configuration. Shifting from theoretical practical usage crucial bolstering evaluation deployment.

Language: Английский

An Artificial Intelligence-Based Non-Invasive Approach for Cardiovascular Disease Risk Stratification in Obstructive Sleep Apnea Patients: A Narrative Review

Reviews in Cardiovascular Medicine, Journal Year: 2024, Volume and Issue: 25(12)

Published: Dec. 28, 2024

Obstructive sleep apnea (OSA) is a severe condition associated with numerous cardiovascular complications, including heart failure. The complex biological and morphological relationship between OSA atherosclerotic disease (ASCVD) poses challenges in predicting adverse outcomes. While artificial intelligence (AI) has shown potential for (CVD) stroke risks other conditions, there lack of detailed, bias-free, compressed AI models ASCVD risk stratification patients. This study aimed to address this gap by proposing three hypotheses: (i) strong exists ASCVD/stroke, (ii) deep learning (DL) can stratify ASCVD/stroke patients using surrogate carotid imaging, (iii) as covariate factors improve CVD stratification.

Language: Английский