Feasibility of Using Deep Learning to Detect Hypoxemia During Painless Gastrointestinal Endoscopy Based on Facial Images
Anesthesiology Research and Practice · 2026-01 · 2026 (1)
DOI: 10.1155/anrp/1829505 ↗Kurz gefasst
Fachartikel in der Zeitschrift Anesthesiology Research and Practice, online erschienen am 06.04.2026. Verfasst von Zhihu Yang und 10 weiteren Autor:innen. Die Arbeit nennt 43 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China.
Abstract (Originalsprache)
Objective
To develop and validate deep learning (DL) and machine learning (ML) models based on preoperative facial images and structured clinical data for predicting hypoxemia during adult painless gastrointestinal endoscopy, addressing the limitations of subjective and data‐intensive prediction methods.
Methods
A total of 424 patients aged 18–80 years from the East Campus of the First Affiliated Hospital of Zhengzhou University (training/validation set) and 60 patients from the West Campus (test set) between October 2022 and October 2023 were included. A ResNet‐50 DL architecture and five ML algorithms (LightGBM, XGBoost, Random Forest, Logistic Regression, were Naive Bayes) were trained. K‐fold cross‐validation, data augmentation, and class weighting were applied to address class imbalance. Model performance was assessed using AUC, precision–recall curves, calibration curves, confusion matrices, class activation maps, and accuracy.
Results
ResNet‐50 achieved the highest AUC of 0.8967 (95% CI: 0.8598–0.9402) and accuracy of 0.8500 (95% CI: 0.7333–0.9167), outperforming all ML models. LightGBM was the best ML performer (AUC: 0.8304; accuracy: 0.8176).
Conclusions
The proposed ResNet‐50 model enables accurate, objective, and noninvasive prediction of hypoxemia risk using only facial images, offering a rapid preoperative risk assessment tool. This approach may enhance patient safety and streamline anesthesia workflows in outpatient endoscopy. Trial Registration: Chinese Registry of Clinical Trials: ChiCTR2400082682
Förderung
- National Natural Science Foundation of China
Zitieren
APA
Yang, Z., Xing, F., Wang, Z., Qu, M., Yao, Y., Liu, Y., Jing, M., Xing, M., Chen, J., Cheng, D., & Xing, N. (2026). Feasibility of Using Deep Learning to Detect Hypoxemia During Painless Gastrointestinal Endoscopy Based on Facial Images. Anesthesiology Research and Practice, 2026(1). https://doi.org/10.1155/anrp/1829505
Vancouver
Yang Z, Xing F, Wang Z, Qu M, Yao Y, Liu Y, et al. Feasibility of Using Deep Learning to Detect Hypoxemia During Painless Gastrointestinal Endoscopy Based on Facial Images. Anesthesiology Research and Practice. 2026;2026(1). doi:10.1155/anrp/1829505
BibTeX
@article{Yang2026,
author = {Yang, Zhihu and Xing, Fei and Wang, Zhongyu and Qu, Mingcui and Yao, Yongchao and Liu, Yafei and Jing, Mingzhu and Xing, Mingquan and Chen, Jiaqi and Cheng, Dan and Xing, Na},
title = {Feasibility of Using Deep Learning to Detect Hypoxemia During Painless Gastrointestinal Endoscopy Based on Facial Images},
journal = {Anesthesiology Research and Practice},
year = {2026},
volume = {2026},
number = {1},
doi = {10.1155/anrp/1829505}
}
EUVIMED