Search

Wearable electrocardiogram (ECG) devices such as smartwatches and ambulatory monitors generate large-scale continuous cardiac data suitable for arrhythmia detection in real-world settings. However, the development of supervised machine learning models is limited by the scarcity of expert-annotated ECG data, class imbalance due to rare arrhythmias, and privacy constraints that restrict data sharing. These challenges make it difficult for traditional deep learning approaches to scale effectively in clinical applications.This work proposes a self-supervised contrastive learning framework that leverages large volumes of unlabeled wearable ECG data to learn meaningful cardiac representations. Using ECG-specific data augmentations, the model is trained to maximize agreement between different views of the same signal while distinguishing between different segments. A deep encoder produces latent embeddings, which are optimized through a contrastive loss, and later adapted for arrhythmia classification using a lightweight classifier with minimal labeled data.The proposed approach reduces dependence on expert annotations, improves generalization across devices and populations, and supports privacy-preserving training. Overall, it offers a scalable and efficient pathway for wearable-based arrhythmia detection, potentially enabling earlier diagnosis and broader deployment of cardiac AI systems in resource-limited healthcare settings.

Chest X-ray report generation is time-consuming and contributes to radiologist workload and burnout, motivating the need for AI systems that can reduce cognitive burden while preserving clinical accuracy. Although encoder-decoder models can generate reports from images, they often suffer from hallucinations, producing findings that are not present or missing real abnormalities due to lack of explicit grounding in evidence, making them unreliable for clinical use. To address this, we propose a cross-modal retrieval framework that generates reports by retrieving and assembling clinically validated sentences from existing radiology reports rather than generating text from scratch. The system uses contrastive learning to align chest X-ray image patches with report sentences in a shared embedding space, enabling retrieval of the most relevant clinical descriptions. A patch encoder extracts visual features, a sentence encoder represents report text, and a retrieval module identifies semantically matching sentences, which are then composed into a coherent final report. Because all outputs are sourced from real clinical reports, the method substantially reduces hallucinations while improving factual reliability and interpretability. This retrieval-based approach offers a scalable and safer alternative to generative models and can be evaluated on datasets such as MIMIC-CXR and CheXpert for clinical accuracy and retrieval performance.