ChatPPG.
Join free
First page or project page of “A Scoping Review of Deep Learning Methods for Photoplethysmography Data” (opens in a new tab)

PaperarXiv:2401.12783

A Scoping Review of Deep Learning Methods for Photoplethysmography Data

Venue listedDated Nov 2, 2026Added Nov 6, 2026

  • GH

Authors: Guangkun Nie; Jiabao Zhu; Gongzheng Tang; Deyun Zhang; Shijia Geng; Qinghao Zhao; Shenda Hong

Health Data Science

PDF (opens in a new tab) arXiv2401.12783 (opens in a new tab) Publisher (opens in a new tab) PubMed (opens in a new tab) Cite
Open codeCC BY (publisher/OA)
First page or project page of “A Scoping Review of Deep Learning Methods for Photoplethysmography Data” (opens in a new tab)

TL;DR

Scoping review of deep learning on contact PPG (2017-01-01 to 2025-12-31): 460 included papers across tasks/models/data. Task counts include BP 154, cardiovascular 106, mental health 31, glucose 31, signal processing 41, sleep 27, biometrics 27, respiratory/SpO2 26, ECG reconstruction 16, HAR 7. CNNs dominate (283).

  • Form factor: mixed

Abstract

Background: Photoplethysmography (PPG) is a non-invasive optical sensing technique widely used to capture hemodynamic information, with broad deployment in both clinical monitoring systems and wearable devices. In recent years, the integration of deep learning has substantially advanced PPG signal analysis and expanded its applications across healthcare and non-healthcare domains. Methods: We conducted a comprehensive literature search for studies applying deep learning to PPG data published between January 1, 2017 and December 31, 2025, using Google Scholar, PubMed, and Dimensions. The included studies were analyzed from three key perspectives: tasks, models, and data. Results: A total of 460 papers applying deep learning techniques to PPG signal analysis were included. These studies span a wide range of application domains, from traditional physiological monitoring tasks such as cardiovascular assessment to emerging applications including sleep analysis, cross-modality signal reconstruction, and biometric identification. Conclusions: Deep learning has significantly advanced PPG signal analysis by enabling more effective extraction of physiological information. Compared with traditional machine learning approaches reliant on handcrafted features, deep learning methods generally achieve improved performance and offer greater flexibility in model development. Nevertheless, several challenges remain, including limited availability of large-scale high-quality datasets, insufficient validation in real-world environments, and concerns over model interpretability, scalability, and computational efficiency. Addressing these challenges and exploring emerging research directions will be essential for further progress in deep learning-based PPG analysis.

Verbatim from arXiv (opens in a new tab) · arXiv metadata (abstracts are released under CC0)

Results on ChatPPG leaderboards

All leaderboards

No results from this paper on ChatPPG leaderboards yet. Browse the leaderboards.

Tasks & signals

Tasks

Signal qualitySleep stagingSpO₂

Signals

PPG

Devices

Empatica E4RespiBAN chest band

Keywords

Deep LearningScoping ReviewWearableSurveyHongSQISleepSpO₂

Datasets used

How it works

How Method works: Setup → Method → TargetSetup: Signals (PPG); Form factor (mixed). Method: Method. Target: Signal quality; Sleep staging; SpO₂.SetupSignals: PPGSignalsPPGForm factor: mixedForm factormixedMethodMethodTargetSignal qualitySignal qualitySleep stagingSleep stagingSpO₂O₂SpO₂

Cite this paper

Cite this paper with the fields recorded here. Check it against the publisher before submitting.

Nie, G., Zhu, J., Tang, G., Zhang, D., Geng, S., Zhao, Q., & Hong, S. (2026). A Scoping Review of Deep Learning Methods for Photoplethysmography Data. Health Data Science. https://doi.org/10.34133/hds.0474
Nie, Guangkun, Jiabao Zhu, Gongzheng Tang, Deyun Zhang, Shijia Geng, Qinghao Zhao, and Shenda Hong. 2026. "A Scoping Review of Deep Learning Methods for Photoplethysmography Data." Health Data Science. https://doi.org/10.34133/hds.0474.
Nie, G., Zhu, J., Tang, G., Zhang, D., Geng, S., Zhao, Q. and Hong, S. (2026) 'A Scoping Review of Deep Learning Methods for Photoplethysmography Data', Health Data Science. doi: 10.34133/hds.0474.
Nie, Guangkun, et al. "A Scoping Review of Deep Learning Methods for Photoplethysmography Data." Health Data Science, 2026. https://doi.org/10.34133/hds.0474.
G. Nie et al., "A Scoping Review of Deep Learning Methods for Photoplethysmography Data," Health Data Science, 2026, doi: 10.34133/hds.0474.
@article{nie2026scoping,
  title         = {{A Scoping Review of Deep Learning Methods for Photoplethysmography Data}},
  author        = {Nie, Guangkun and Zhu, Jiabao and Tang, Gongzheng and Zhang, Deyun and Geng, Shijia and Zhao, Qinghao and Hong, Shenda},
  year          = {2026},
  journal       = {Health Data Science},
  doi           = {10.34133/hds.0474},
  eprint        = {2401.12783},
  archivePrefix = {arXiv}
}

Added to the ChatPPG research hub

Same tasks, data and authors

Papers

Models