Kwon O, et al. J Lipid Atheroscler. 2025 Sep;14(3):298-311. https://doi.org/10.12997/jla.2025.14.3.298

김기경, et al. J Korean Acad Nurs Adm. 2020 Mar;26(2):84-99. https://doi.org/10.11111/jkana.2020.26.2.84

Ahn J, et al. J Lipid Atheroscler. 2025 Jan;14(1):77-93. https://doi.org/10.12997/jla.2025.14.1.77

Kim S, et al. Korean J Adult Nurs. 2018 Aug;30(4):347-361. https://doi.org/10.7475/kjan.2018.30.4.347

Generative artificial intelligence (AI), particularly large language models (LLMs) such as ChatGPT, has rapidly advanced in capability and accessibility, creating novel paradigms for personalized healthcare. In exercise and sports medicine, where clinical decision-making necessitates the integration of complex physiological data, individualized programming, and patient-centered communication, generative AI offers transformative potential for workflow augmentation. This narrative review synthesizes current applications, strengths, and limitations across seven core domains: (1) personalized exercise prescription, (2) performance enhancement and training support, (3) clinical rehabilitation and disease management, (4) lifestyle modification, (5) education and communication, (6) injury prevention, and (7) data analytics. LLMs demonstrated the ability to generate structured exercise prescriptions and rehabilitation protocols with moderate to high guideline compliance across cardiac and musculoskeletal rehabilitation contexts, while patient education content achieved favorable readability and clinical relevance ratings. Furthermore, methodological advancements such as prompt engineering and wearable-integrated closed-loop systems have enhanced personalization and real-time adaptability. In the domain of patient communication, generative AI tools produced readable educational materials with high factual consistency, although challenges persist regarding comorbidity screening, individualized safety verification, and cultural-linguistic contextualization. Ultimately, generative AI is poised to function as a first-draft accelerator and productivity amplifier within exercise and sports medicine. However, mandatory expert oversight, rigorous clinical validation, and robust governance frameworks remain essential prerequisites for the safe and effective integration of this approach into frontline clinical practice.

Background/Objectives: Wearable electrocardiogram (ECG) monitoring has become increasingly important in detecting atrial fibrillation (AF) and subclinical arrhythmias by addressing diagnostic gaps inherent to intermittent or asymptomatic presentations. In contemporary clinical practice, two major types of wearable ECG monitors—patch-type and lead-type—are widely used, each with distinct advantages and limitations. This study aims to compare these modalities and evaluate their respective strengths and constraints in real-world settings. Methods: We retrospectively analyzed 639 consecutive outpatients (mean age 61.7 ± 14.5 years; 56.7% male) who underwent wearable ECG monitoring between March 2022 and October 2023. Patients were stratified into patch-type (n = 466; 72.9%) and lead-type (n = 173; 27.1%) groups. Baseline characteristics were comparable. Indications, monitoring duration, arrhythmia detection, and noise rates were assessed. Results: Baseline characteristics did not differ significantly between the two groups. Lead-type monitoring was often prescribed for symptomatic patients (87.9% vs. 75.8%; p = 0.001), Symptomatic patients were older than asymptomatic patients (p = 0.040), whereas the proportion of males was higher in the asymptomatic group (p < 0.001). AF detection rates were comparable between the two groups (24.0% vs. 24.9%; p = 0.911). Patch-type monitoring achieved significantly longer recording duration (p < 0.001) and higher pause event detection (p = 0.004), but at the cost of increased noise burden (p < 0.001). Conclusions: Both patch-type and lead-type wearable ECGs are clinical applicable for arrhythmia surveillance in real-world practice. While AF detection rates were similar, the patch-type monitoring provided more extended observation periods and enhanced pause detection, though accompanied by a higher noise burden. These findings suggest that device selection should be individualized based on patient symptoms, monitoring goals, and tolerability. This study provides practical insights for optimizing wearable ECG use in routine practice.