PaPaGei: Open Foundation Models for Optical Physiological Signals

This repository contains PPG foundation models trained using the VitalDB, MIMIC-III, and MESA datasets. Note that data must be obtained from the respective data owners following appropriate procedures.

For details and usage, please visit: https://github.com/Nokia-Bell-Labs/papagei-foundation-model

VitalDB:

The VitalDB dataset is under the Creative Commons Attribution 4.0 International Public License.

Lee, H., & Jung, C. (2022). VitalDB, a high-fidelity multi-parameter vital signs database in surgical patients (version 1.0.0). PhysioNet. https://doi.org/10.13026/czw8-9p62.

Lee, HC., Park, Y., Yoon, S.B. et al. VitalDB, a high-fidelity multi-parameter vital signs database in surgical patients. Sci Data 9, 279 (2022)

Goldberger, A., Amaral, L., Glass, L., Hausdorff, J., Ivanov, P. C., Mark, R., ... & Stanley, H. E. (2000). PhysioBank, PhysioToolkit, and PhysioNet: Components of a new research resource for complex physiologic signals. Circulation [Online]. 101 (23), pp. e215–e220.

MIMIC-III:

Contains information from MIMIC-III Waveform Database Matched Subset in our analysis, which is made available here under the Open Database License (ODbL).

Moody, B., Moody, G., Villarroel, M., Clifford, G. D., & Silva, I. (2020). MIMIC-III Waveform Database Matched Subset (version 1.0). PhysioNet. https://doi.org/10.13026/c2294b.

Johnson, A. E. W., Pollard, T. J., Shen, L., Lehman, L. H., Feng, M., Ghassemi, M., Moody, B., Szolovits, P., Celi, L. A., & Mark, R. G. (2016). MIMIC-III, a freely accessible critical care database. Scientific Data, 3, 160035.

Goldberger, A., Amaral, L., Glass, L., Hausdorff, J., Ivanov, P. C., Mark, R., ... & Stanley, H. E. (2000). PhysioBank, PhysioToolkit, and PhysioNet: Components of a new research resource for complex physiologic signals. Circulation [Online]. 101 (23), pp. e215–e220.

The Multi-Ethnic Study of Atherosclerosis (MESA) Sleep Ancillary study:

Zhang GQ, Cui L, Mueller R, Tao S, Kim M, Rueschman M, Mariani S, Mobley D, Redline S. The National Sleep Research Resource: towards a sleep data commons. J Am Med Inform Assoc. 2018 Oct 1;25(10):1351-1358. doi: 10.1093/jamia/ocy064. PMID: 29860441; PMCID: PMC6188513.

Chen X, Wang R, Zee P, Lutsey PL, Javaheri S, Alcántara C, Jackson CL, Williams MA, Redline S. Racial/Ethnic Differences in Sleep Disturbances: The Multi-Ethnic Study of Atherosclerosis (MESA). Sleep. 2015 Jun 1;38(6):877-88. doi: 10.5665/sleep.4732. PMID: 25409106; PMCID: PMC4434554.

The Multi-Ethnic Study of Atherosclerosis (MESA) Sleep Ancillary study was funded by NIH-NHLBI Association of Sleep Disorders with Cardiovascular Health Across Ethnic Groups (RO1 HL098433). MESA is supported by NHLBI funded contracts HHSN268201500003I, N01-HC-95159, N01-HC-95160, N01-HC-95161, N01-HC-95162, N01-HC-95163, N01-HC-95164, N01-HC-95165, N01-HC-95166, N01-HC-95167, N01-HC-95168 and N01-HC-95169 from the National Heart, Lung, and Blood Institute, and by cooperative agreements UL1-TR-000040, UL1-TR-001079, and UL1-TR-001420 funded by NCATS. The National Sleep Research Resource was supported by the National Heart, Lung, and Blood Institute (R24 HL114473, 75N92019R002).

Ethics Statement

Our research on PaPaGei, utilizing publicly available PPG datasets, adheres to data privacy regulations and promotes transparency through open-source releases. We acknowledge potential biases in the training data and have evaluated performance across diverse datasets, particularly regarding skin tone variations. While PaPaGei offers significant potential for improving non-invasive health monitoring, we recognize the need to address potential misuse. Examples of misuse could include unauthorized health monitoring, discriminatory practices in insurance or employment, unfair credit scoring, or exploiting personal health data for targeted marketing. We strongly advocate responsible use solely for beneficial healthcare applications. Our study followed established research ethics guidelines, and we declare no conflicts of interest. We encourage ongoing interdisciplinary dialogue to address potential risks and ensure responsible development and deployment of such technologies, recognizing the broader societal impacts of AI in healthcare. We remain committed to ethical AI advancement and welcome further discussion on the critical issues, including the development of governance frameworks to prevent misuse and protect data privacy.