mlsanityData to 7 Oct 2026

GPT-PPG: A GPT-based Foundation Model for Photoplethysmography Signals

arXiv 2503.08015 ↗First posted 11 Mar 2025cs.LG eess.SPcited by 12

Not on the map. Why?

Abstract (arXiv)

This study introduces a novel application of a Generative Pre-trained Transformer (GPT) model tailored for photoplethysmography (PPG) signals, serving as a foundation model for various downstream tasks. Adapting the standard GPT architecture to suit the continuous characteristics of PPG signals, our approach demonstrates promising results. Our models are pre-trained on our extensive dataset that contains more than 200 million 30s PPG samples. We explored different supervised fine-tuning techniques to adapt our model to downstream tasks, resulting in performance comparable to or surpassing current state-of-the-art (SOTA) methods in tasks like atrial fibrillation detection. A standout feature of our GPT model is its inherent capability to perform generative tasks such as signal denoising effectively, without the need for further fine-tuning. This success is attributed to the generative nature of the GPT framework.

Key facts. Cited by 12 papers in the map (data through 7 Oct 2026). Builds on 27 of its 53 references that are in the map. First posted on arXiv 11 Mar 2025.

Builds on

27 of 53 references.

References · 27

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,084
  3. 2023Mamba: Linear-Time Sequence Modeling with Selective State Spacescited by 4,616
  4. 2021RoFormer: Enhanced Transformer with Rotary Position Embeddingcited by 4,581
  5. 2021Zero-Shot Text-to-Image Generationcited by 4,276
  6. 2020Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecastingcited by 2,141
  7. 2022A Time Series is Worth 64 Words: Long-term Forecasting with Transformerscited by 1,981
  8. 2021Autoformer: Decomposition Transformers with Auto-Correlation for Long-Term Series Forecastingcited by 1,654
  9. 2019Root Mean Square Layer Normalizationcited by 1,425
  10. 2024MOMENT: A Family of Open Time-series Foundation Modelscited by 453
  11. 2024LLM2Vec: Large Language Models Are Secretly Powerful Text Encoderscited by 396
  12. 2023TEMPO: Prompt-based Generative Pre-trained Transformer for Time Series Forecastingcited by 170
15 more
  1. 2023TimeGPT-1cited by 149
  2. 2023Large-scale Training of Foundation Models for Wearable Biosignalscited by 89
  3. 2024PaPaGei: Open Foundation Models for Optical Physiological Signalscited by 64
  4. 2023Frozen Language Model Helps ECG Zero-Shot Learningcited by 62
  5. 2014TROIKA: A General Framework for Heart Rate Monitoring Using Wrist-Type Photoplethysmographic Signals During Intensive Physical Exercisecited by 40
  6. 2023EarthPT: a time series foundation model for Earth Observationcited by 14
  7. 2020Estimating Blood Pressure from Photoplethysmogram Signal and Demographic Features using Machine Learning Techniquescited by 13
  8. 2022RRWaveNet: A Compact End-to-End Multi-Scale Residual CNN for Robust PPG Respiratory Rate Estimationcited by 8
  9. 2023BeliefPPG: Uncertainty-aware Heart Rate Estimation from PPG signals via Belief Propagationcited by 8
  10. 2021Log-Spectral Matching GAN: PPG-based Atrial Fibrillation Detection can be Enhanced by GAN-based Data Augmentation with Integration of Spectral Losscited by 7
  11. 2023Sparse learned kernels for interpretable and efficient medical time series processingcited by 6
  12. 2022Learning From Alarms: A Robust Learning Approach for Accurate Photoplethysmography-Based Atrial Fibrillation Detection using Eight Million Samples Labeled with Imprecise Arrhythmia Alarmscited by 4
  13. 2024SQUWA: Signal Quality Aware DNN Architecture for Enhanced Accuracy in Atrial Fibrillation Detection from Noisy PPG Signalscited by 4
  14. 2023SiamAF: Learning Shared Information from ECG and PPG Signals for Robust Atrial Fibrillation Detectioncited by 3
  15. 2023A Self-Supervised Algorithm for Denoising Photoplethysmography Signals for Heart Rate Estimation from Wearablescited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 6; 2026: 6.

12 papers.

  1. 2026SIGMA-PPG: Statistical-prior Informed Generative Masking Architecture for PPG Foundation Modelcited by 7
  2. 2025QualityFM: a Multimodal Physiological Signal Foundation Model with Self-Distillation for Signal Quality Challenges in Critically Ill Patientscited by 2
  3. 2025Estimating Clinical Lab Test Result Trajectories from PPG using Physiological Foundation Model and Patient-Aware State Space Model -- a UNIPHY+ Approachcited by 2
  4. 2025FairTune: A Bias-Aware Fine-Tuning Framework Towards Fair Heart Rate Prediction from PPGcited by 2
  5. 2025Wav2Arrest 2.0: Long-Horizon Cardiac Arrest Prediction with Time-to-Event Modeling, Identity-Invariance, and Pseudo-Lab Alignmentcited by 1
  6. 2025BioX-Bridge: Model Bridging for Unsupervised Cross-Modal Knowledge Transfer across Biosignalscited by 1
  7. 2026CAP: Towards PPG Universal Representation Learning with Patient-level Supervisioncited by 1
  8. 2025Generalist vs Specialist Time Series Foundation Models: Investigating Potential Emergent Behaviors in Assessing Human Health Using PPG Signalscited by 0
  9. 2026A Comprehensive Inference-Time Augmentation Framework in Physiological Signals: Application to PPG-Based AF Detectioncited by 0
  10. 2026Large language models in medical time series analysiscited by 0
  11. 2026PPG-LM: A Photoplethysmography-Language Model with Multi-Level Clinical Alignmentcited by 0
  12. 2026RAE-PPG: Duration-Grounded Retain-and-Extend Pretraining for PPG Foundation Modelscited by 0