EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Wearable ECG-PPG Deep Learning Model for Cardiac Index-Based Noninvasive Cardiac Output Estimation in Cardiac Surgery Patients

Minwoo Kim iD, Min Dong Sung iD, Jimyeoung Jung, Sung Pil Cho iD, Junghwan Park iD, Sarah Soh iD, Hyun Chel Joo iD, Kyung Soo Chung iD

Sensors · 22.01.2026 · 26 (2) · 735

DOI: 10.3390/s26020735 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 22.01.2026. Verfasst von Minwoo Kim und 7 weiteren Autor:innen. Beteiligte Einrichtung: MEZOO Co., Ltd., 200, Gieopdosi-ro, Jijeong-myeon, Wonju-si 26354, Republic of Korea. Hauptthemen laut MEDLINE: Photoplethysmography, Wearable Electronic Devices, Deep Learning, Electrocardiography. Die Arbeit wurde bisher 7-mal zitiert (Crossref) und nennt 58 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: the Ministry of Health and Welfare, Republic of Korea, the Ministry of SMEs and Startups, Republic of Korea, Ministry of Health and Welfare, Republic of Korea.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Accurate cardiac output (CO) measurement is vital for hemodynamic management; however, it usually requires invasive monitoring, which limits its continuous and out-of-hospital use. Wearable sensors integrated with deep learning offer a noninvasive alternative. This study developed and validated a lightweight deep learning model using wearable electrocardiography (ECG) and photoplethysmography (PPG) signals to predict CO and examined whether cardiac index-based normalization (Cardiac Index (CI) = CO/body surface area) improves performance. Twenty-seven patients who underwent cardiac surgery and had pulmonary artery catheters were prospectively enrolled. Single-lead ECG (HiCardi+ chest patch) and finger PPG (WristOx2 3150) were recorded simultaneously and processed through an ECG–PPG fusion network with cross-modal interaction. Three models were trained as follows: (1) CI prediction, (2) direct CO prediction, and (3) indirect CO prediction. The total number of CO = predicted CI × body surface area. Reference values were derived from thermodilution. The CI model achieved the best performance, and the indirect CO model showed significant reductions in error/agreement metrics (MAE/RMSE/bias; p < 0.0001), while correlation-based metrics are reported descriptively without implying statistical significance. The Pearson correlation coefficient (PCC) and percentage error (PE) for the indirect CO estimates (PCC = 0.904; PE = 23.75%). The indirect CO estimates met the predefined PE < 30% agreement benchmark for method-comparison; this is not a universal clinical standard. These results demonstrate that wearable ECG–PPG fusion deep learning can achieve accurate, noninvasive CO estimation and that CI-based normalization enhances model agreement with pulmonary artery catheter measurements, supporting continuous catheter-free hemodynamic monitoring.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

PhotoplethysmographyWearable Electronic DevicesDeep LearningElectrocardiographyCardiac OutputCardiac Surgical ProceduresHumansFemaleMaleMiddle AgedAgedMonitoring, Physiologic

Stichwörter der Autor:innen

cardiac indexcardiac outputcardiac surgerydeep learningelectrocardiography (ECG)hemodynamic monitoringmultimodal fusionphotoplethysmography (PPG)wearable sensors

Autor:innen und Institutionen

  • MEZOO Co., Ltd., 200, Gieopdosi-ro, Jijeong-myeon, Wonju-si 26354, Republic of Korea.
  • Division of Pulmonology and Critical Care Medicine, Department of Internal Medicine, Institute for Innovation in Digital Healthcare, Yonsei University College of Medicine, Seoul 03722, Republic of Korea.
  • Anaesthesia and Pain Research Institute, Department of Anaesthesiology and Pain Medicine, Yonsei University College of Medicine, Seoul 03722, Republic of Korea.
  • Division of Cardiovascular Surgery, Department of Cardiovascular and Thoracic Surgery, Yonsei University College of Medicine, Seoul 03722, Republic of Korea.
  • Institute for Innovation in Digital Healthcare, Yonsei University College of Medicine, Seoul 03722, Republic of Korea.

ORCID-Profile: Minwoo Kim, Min Dong Sung, Sung Pil Cho, Junghwan Park, Sarah Soh, Hyun Chel Joo, Kyung Soo Chung

Förderung

  • the Ministry of Health and Welfare, Republic of Korea
  • the Ministry of SMEs and Startups, Republic of Korea
  • Ministry of Health and Welfare, Republic of Korea
  • Ministry of SMEs and Startups

Zitieren

APA

Kim, M., Sung, M. D., Jung, J., Cho, S. P., Park, J., Soh, S., Joo, H. C., & Chung, K. S. (2026). Wearable ECG-PPG Deep Learning Model for Cardiac Index-Based Noninvasive Cardiac Output Estimation in Cardiac Surgery Patients. Sensors, 26(2), 735. https://doi.org/10.3390/s26020735

Vancouver

Kim M, Sung MD, Jung J, Cho SP, Park J, Soh S, et al. Wearable ECG-PPG Deep Learning Model for Cardiac Index-Based Noninvasive Cardiac Output Estimation in Cardiac Surgery Patients. Sensors. 2026;26(2):735. doi:10.3390/s26020735

BibTeX
@article{Kim2026,
  author = {Kim, Minwoo and Sung, Min Dong and Jung, Jimyeoung and Cho, Sung Pil and Park, Junghwan and Soh, Sarah and Joo, Hyun Chel and Chung, Kyung Soo},
  title = {Wearable ECG-PPG Deep Learning Model for Cardiac Index-Based Noninvasive Cardiac Output Estimation in Cardiac Surgery Patients},
  journal = {Sensors},
  year = {2026},
  volume = {26},
  number = {2},
  pages = {735},
  doi = {10.3390/s26020735}
}
Kostenlos starten →