ECG-based data-driven solutions for diagnosis and prognosis of cardiovascular diseases: A systematic review

A Soft Patch for Dynamic Myocardial Infarction Monitoring

Wearable electronics for cardiac monitoring have been widely developed in the field of routine vital sign monitoring and arrhythmia determination due to their convenience and continuity. However, there are very few reports on the demonstration of a stretchable multilead electrocardiogram (ECG) patch integrated with myocardial infarction (MI) location capability. Here, we first propose a wearable dynamic cardiac monitoring patch, which can acquire seven-lead ECG signals continuously. A novel stretchable bioelectrode is mounted on the patch, which is strain-insensitive in the 100% tensile strain range. Moreover, the bioelectrode maintains good adhesion to the skin at more than 0.4 N/cm. This soft and wireless multilead ECG patch is designed for long-term, all-round real-time cardiac monitoring. For MI classification, a machine learning model for MI identification and location is trained with accuracy (99.93%) and sensitivity (99.98%). In addition, we also propose a new framework for the automated annotation of MI abnormal segments, which simultaneously addresses the recognition of abnormal waveforms and the integration of interlead relationships. This study contributes to the realization of personalized medical monitoring and intervention as well as early warning for MI.

A Multimodal Sleep Foundation Model Developed with 500K Hours of Sleep Recordings for Disease Predictions

Sleep is a fundamental biological process with profound implications for physical and mental health, yet our understanding of its complex patterns and their relationships to a broad spectrum of diseases remains limited. While polysomnography (PSG), the gold standard for sleep analysis, captures rich multimodal physiological data, analyzing these measurements has been challenging due to limited flexibility across recording environments, poor generalizability across cohorts, and difficulty in leveraging information from multiple signals simultaneously. To address this gap, we curated over 585,000 hours of high-quality sleep recordings from approximately 65,000 participants across multiple cohorts and developed SleepFM, a multimodal sleep foundation model trained with a novel contrastive learning approach, designed to accommodate any PSG montage. SleepFM produces informative sleep embeddings that enable predictions of future diseases. We systematically demonstrate that SleepFM embeddings can predict 130 future diseases, as modeled by Phecodes, with C-Index and AUROC of at least 0.75 on held-out participants (Bonferroni-corrected p < 0.01). This includes accurate predictions for death (C-Index: 0.84 [95% CI: 0.81-0.87]), heart failure (C-Index: 0.80 [95% CI: 0.77-0.83]), chronic kidney disease (C-Index: 0.79 [95% CI: 0.77-0.81]), dementia (C-Index: 0.85 [95% CI: 0.82-0.87]), stroke (C-Index: 0.78 [95% CI: 0.76-0.81]), atrial fibrillation (C-Index: 0.78 [95% CI: 0.75-0.81]), and myocardial infarction (C-Index: 0.81 [95% CI: 0.78-0.84]). The model's generalizability was further validated through strong performance on the Sleep Heart Health Study (SHHS), a dataset unseen during pre-training. Additionally, SleepFM demonstrates strong performance on traditional sleep analysis tasks, achieving competitive results in both sleep staging (mean F1 scores: 0.70-0.78) and sleep apnea diagnosis (AUROC: 0.90-0.94). Beyond these standard applications, our analysis reveals that specific sleep stages and physiological signals carry distinct predictive power for different diseases. This work demonstrates how foundation models can leverage sleep polysomnography data to uncover the extensive relationship between sleep physiology and future disease risk.