EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

COVID-19 Detection Using Photoplethysmography and Neural Networks

Sara Lombardi iD, Piergiorgio Francia iD, Rossella Deodati, Italo Calamai iD, Marco Luchini, Rosario Spina, Leonardo Bocchi iD

Sensors · 25.02.2023 · 23 (5) · 2561

DOI: 10.3390/s23052561 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 25.02.2023. Verfasst von Sara Lombardi und 6 weiteren Autor:innen. Beteiligte Einrichtung: Department of Information Engineering, University of Florence, 50139 Florence, Italy. Hauptthemen laut MEDLINE: Photoplethysmography, COVID-19. Die Arbeit wurde bisher 7-mal zitiert (Crossref) und nennt 31 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Tuscany Region.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The early identification of microvascular changes in patients with Coronavirus Disease 2019 (COVID-19) may offer an important clinical opportunity. This study aimed to define a method, based on deep learning approaches, for the identification of COVID-19 patients from the analysis of the raw PPG signal, acquired with a pulse oximeter. To develop the method, we acquired the PPG signal of 93 COVID-19 patients and 90 healthy control subjects using a finger pulse oximeter. To select the good quality portions of the signal, we developed a template-matching method that excludes samples corrupted by noise or motion artefacts. These samples were subsequently used to develop a custom convolutional neural network model. The model accepts PPG signal segments as input and performs a binary classification between COVID-19 and control samples. The proposed model showed good performance in identifying COVID-19 patients, achieving 83.86% accuracy and 84.30% sensitivity (hold-out validation) on test data. The obtained results indicate that photoplethysmography may be a useful tool for microcirculation assessment and early recognition of SARS-CoV-2-induced microvascular changes. In addition, such a noninvasive and low-cost method is well suited for the development of a user-friendly system, potentially applicable even in resource-limited healthcare settings.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

PhotoplethysmographyCOVID-19HumansSARS-CoV-2OximetryOxygenNeural Networks, ComputerSignal Processing, Computer-AssistedHeart Rate

Stichwörter der Autor:innen

classificationconvolutional neural networkdeep learningmicrocirculationmodellingphotoplethysmogram

Substanzen

Oxygen

Autor:innen und Institutionen

  • Department of Information Engineering, University of Florence, 50139 Florence, Italy.
  • Ospedale San Giuseppe, 50053 Empoli, Italy.

ORCID-Profile: Sara Lombardi, Piergiorgio Francia, Italo Calamai, Leonardo Bocchi

Förderung

  • Tuscany Region

Zitieren

APA

Lombardi, S., Francia, P., Deodati, R., Calamai, I., Luchini, M., Spina, R., & Bocchi, L. (2023). COVID-19 Detection Using Photoplethysmography and Neural Networks. Sensors, 23(5), 2561. https://doi.org/10.3390/s23052561

Vancouver

Lombardi S, Francia P, Deodati R, Calamai I, Luchini M, Spina R, et al. COVID-19 Detection Using Photoplethysmography and Neural Networks. Sensors. 2023;23(5):2561. doi:10.3390/s23052561

BibTeX
@article{Lombardi2023,
  author = {Lombardi, Sara and Francia, Piergiorgio and Deodati, Rossella and Calamai, Italo and Luchini, Marco and Spina, Rosario and Bocchi, Leonardo},
  title = {COVID-19 Detection Using Photoplethysmography and Neural Networks},
  journal = {Sensors},
  year = {2023},
  volume = {23},
  number = {5},
  pages = {2561},
  doi = {10.3390/s23052561}
}
Kostenlos starten →