Nailfold capillaroscopy and deep learning in diabetes
Journal of Diabetes · 2023-02 · 15 (2) · 145-151
DOI: 10.1111/1753-0407.13354 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Diabetes, online erschienen am 15.01.2023. Verfasst von Reema Shah und 6 weiteren Autor:innen. Beteiligte Einrichtung: Population Health Research Institute, McMaster University and Hamilton Health Sciences, Hamilton, Ontario, Canada. Hauptthemen laut MEDLINE: Diabetes Mellitus, Type 2, Deep Learning. Die Arbeit wurde bisher 26-mal zitiert (Crossref) und nennt 35 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Themen: Diabetes mellitus
Abstract (Originalsprache)
Objective
To determine whether nailfold capillary images, acquired using video capillaroscopy, can provide diagnostic information about diabetes and its complications. Research Design and Methods Nailfold video capillaroscopy was performed in 120 adult patients with and without type 1 or type 2 diabetes, and with and without cardiovascular disease. Nailfold images were analyzed using convolutional neural networks, a deep learning technique. Cross‐validation was used to develop and test the ability of models to predict five5 prespecified states (diabetes, high glycosylated hemoglobin, cardiovascular event, retinopathy, albuminuria, and hypertension). The performance of each model for a particular state was assessed by estimating areas under the receiver operating characteristics curves (AUROC) and precision recall curves (AUPR).
Results
A total of 5236 nailfold images were acquired from 120 participants (mean 44 images per participant) and were all available for analysis. Models were able to accurately identify the presence of diabetes, with AUROC 0.84 (95% confidence interval [CI] 0.76, 0.91) and AUPR 0.84 (95% CI 0.78, 0.93), respectively. Models were also able to predict a history of cardiovascular events in patients with diabetes, with AUROC 0.65 (95% CI 0.51, 0.78) and AUPR 0.72 (95% CI 0.62, 0.88) respectively.
Conclusions
This proof‐of‐concept study demonstrates the potential of machine learning for identifying people with microvascular capillary changes from diabetes based on nailfold images, and for possibly identifying those most likely to have diabetes‐related complications.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Population Health Research Institute, McMaster University and Hamilton Health Sciences, Hamilton, Ontario, Canada.
- Centre for Data Science and Digital Health, Hamilton Health Sciences, Hamilton, Ontario, Canada.
- Institute for Health Policy, Management and Evaluation, University of Toronto, Toronto, Ontario, Canada.
- Division of Cardiology, McMaster University, Hamilton, Ontario, Canada.
- Department of Statistical Sciences, University of Toronto, Toronto, Ontario, Canada.
- Cluster of Excellence Machine Learning, University of Tübingen, Tübingen, Germany.
ORCID-Profile: Reema Shah, Michael D Noseworthy, Hertzel C Gerstein
Zitieren
APA
Shah, R., Petch, J., Nelson, W., Roth, K., Noseworthy, M. D., Ghassemi, M., & Gerstein, H. C. (2023). Nailfold capillaroscopy and deep learning in diabetes. Journal of Diabetes, 15(2), 145-151. https://doi.org/10.1111/1753-0407.13354
Vancouver
Shah R, Petch J, Nelson W, Roth K, Noseworthy MD, Ghassemi M, et al. Nailfold capillaroscopy and deep learning in diabetes. Journal of Diabetes. 2023;15(2):145-151. doi:10.1111/1753-0407.13354
BibTeX
@article{Shah2023,
author = {Shah, Reema and Petch, Jeremy and Nelson, Walter and Roth, Karsten and Noseworthy, Michael D and Ghassemi, Marzyeh and Gerstein, Hertzel C},
title = {Nailfold capillaroscopy and deep learning in diabetes},
journal = {Journal of Diabetes},
year = {2023},
volume = {15},
number = {2},
pages = {145--151},
doi = {10.1111/1753-0407.13354}
}
EUVIMED