Key result
A novel GPT-based foundation model for photoplethysmography signals achieved performance comparable to or exceeding current state-of-the-art methods for atrial fibrillation detection.
Why the study?
The study was conducted to introduce a novel generative pre-trained transformer-based foundation model tailored to photoplethysmography signals to enable effective adaptation to various downstream biomedical tasks.
Does a GPT-based foundation model for PPG signals improve performance on downstream tasks like atrial fibrillation detection compared to state-of-the-art methods?
Does a GPT-based foundation model for PPG signals improve performance on downstream tasks like atrial fibrillation detection compared to state-of-the-art methods?
Answers are grounded in this paper and cite their sources.
A novel GPT-based foundation model for PPG signals demonstrates strong performance in predictive tasks like atrial fibrillation detection and generative tasks like signal denoising.
Objective . This study aims to introduce a novel generative pre-trained transformer (GPT)-based foundation model specifically tailored to photoplethysmography (PPG) signals, enabling effective adaptation to various downstream biomedical tasks. Approach . We adapted the standard GPT architecture to handle the continuous characteristics of PPG signals, leveraging extensive pre-training on a large dataset comprising over 200 million 30 s PPG samples, followed by supervised fine-tuning strategies for task-specific optimization. Main results . Our approach achieves performance comparable to or exceeding current state-of-the-art methods on various downstream tasks, notably atrial fibrillation detection, and demonstrates a unique generative capability, such as effective signal denoising, inherently available without additional fine-tuning. Significance . The successful adaptation of GPT to PPG signals underscores the potential of generative transformer frameworks as versatile foundation models in biomedical signal processing, highlighting their dual role in predictive and generative tasks.
No takes yet. Share an insight, caveat, or question.
Chen et al. (2025) studied Photoplethysmography (PPG) signal processing and atrial fibrillation detection. GPT-PPG (GPT-based foundation model) vs. Current state-of-the-art methods was evaluated on Performance on downstream biomedical tasks (notably atrial fibrillation detection) and signal denoising. A novel GPT-based foundation model for photoplethysmography signals achieved performance comparable to or exceeding current state-of-the-art methods for atrial fibrillation detection.
Synapse has enriched 10 related papers. Consider them for comparative context: