Application of Photoplethysmography Combined with Deep Learning in Postoperative Monitoring of Flaps

ObjectivePhotoelectric volumetric tracing (PPG) exhibits high sensitivity and specificity in flap monitoring. Deep learning (DL) is capable of automatically and robustly extracting features from raw data. In this study, we propose combining PPG with 1D convolutional neural networks (1D-CNN) to preli...

Full description

Saved in:
Bibliographic Details
Main Authors: Jing YANG, Xinlei YANG, Yuwei GAO, Chunlei ZHANG, Di WANG, Tao SONG
Format: Article
Language:zho
Published: Editorial Office of Chinese Journal of Medical Instrumentation 2024-07-01
Series:Zhongguo yiliao qixie zazhi
Subjects:
Online Access:https://zgylqxzz.xml-journal.net/article/doi/10.12455/j.issn.1671-7104.230624
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846163565017300992
author Jing YANG
Xinlei YANG
Yuwei GAO
Chunlei ZHANG
Di WANG
Tao SONG
author_facet Jing YANG
Xinlei YANG
Yuwei GAO
Chunlei ZHANG
Di WANG
Tao SONG
author_sort Jing YANG
collection DOAJ
description ObjectivePhotoelectric volumetric tracing (PPG) exhibits high sensitivity and specificity in flap monitoring. Deep learning (DL) is capable of automatically and robustly extracting features from raw data. In this study, we propose combining PPG with 1D convolutional neural networks (1D-CNN) to preliminarily explore the method’s ability to distinguish the degree of embolism and to localize the embolic site in skin flap arteries. MethodsData were collected under normal conditions and various embolic scenarios by creating vascular emboli in a dermatome artery model and a rabbit dermatome model. These datasets were then trained, validated, and tested using 1D-CNN. ResultsAs the degree of arterial embolization increased, the PPG amplitude upstream of the embolization site progressively increased, while the downstream amplitude progressively decreased, and the gap between the upstream and downstream amplitudes at the embolization site progressively widened. 1D-CNN was evaluated in the skin flap arterial model and rabbit skin flap model, achieving average accuracies of 98.36% and 95.90%, respectively. ConclusionThe combined monitoring approach of DL and PPG can effectively identify the degree of embolism and locate the embolic site within the skin flap artery.
format Article
id doaj-art-912e96d7b235437c9f4863dcdd3f1b83
institution Kabale University
issn 1671-7104
language zho
publishDate 2024-07-01
publisher Editorial Office of Chinese Journal of Medical Instrumentation
record_format Article
series Zhongguo yiliao qixie zazhi
spelling doaj-art-912e96d7b235437c9f4863dcdd3f1b832024-11-19T06:09:14ZzhoEditorial Office of Chinese Journal of Medical InstrumentationZhongguo yiliao qixie zazhi1671-71042024-07-0148441942510.12455/j.issn.1671-7104.2306242023-0624Application of Photoplethysmography Combined with Deep Learning in Postoperative Monitoring of FlapsJing YANG0Xinlei YANG1Yuwei GAO2Chunlei ZHANG3Di WANG4Tao SONG5School of Stomatology, Harbin Medical University, Harbin, 150000The First Affiliated Hospital of Harbin Medical University, Harbin, 150000Stomatological Hospital of Harbin Medical University, Harbin, 150000School of Stomatology, Harbin Medical University, Harbin, 150000School of Stomatology, Harbin Medical University, Harbin, 150000Stomatological Hospital of Harbin Medical University, Harbin, 150000ObjectivePhotoelectric volumetric tracing (PPG) exhibits high sensitivity and specificity in flap monitoring. Deep learning (DL) is capable of automatically and robustly extracting features from raw data. In this study, we propose combining PPG with 1D convolutional neural networks (1D-CNN) to preliminarily explore the method’s ability to distinguish the degree of embolism and to localize the embolic site in skin flap arteries. MethodsData were collected under normal conditions and various embolic scenarios by creating vascular emboli in a dermatome artery model and a rabbit dermatome model. These datasets were then trained, validated, and tested using 1D-CNN. ResultsAs the degree of arterial embolization increased, the PPG amplitude upstream of the embolization site progressively increased, while the downstream amplitude progressively decreased, and the gap between the upstream and downstream amplitudes at the embolization site progressively widened. 1D-CNN was evaluated in the skin flap arterial model and rabbit skin flap model, achieving average accuracies of 98.36% and 95.90%, respectively. ConclusionThe combined monitoring approach of DL and PPG can effectively identify the degree of embolism and locate the embolic site within the skin flap artery.https://zgylqxzz.xml-journal.net/article/doi/10.12455/j.issn.1671-7104.230624photoplethysmographydeep learningflap
spellingShingle Jing YANG
Xinlei YANG
Yuwei GAO
Chunlei ZHANG
Di WANG
Tao SONG
Application of Photoplethysmography Combined with Deep Learning in Postoperative Monitoring of Flaps
Zhongguo yiliao qixie zazhi
photoplethysmography
deep learning
flap
title Application of Photoplethysmography Combined with Deep Learning in Postoperative Monitoring of Flaps
title_full Application of Photoplethysmography Combined with Deep Learning in Postoperative Monitoring of Flaps
title_fullStr Application of Photoplethysmography Combined with Deep Learning in Postoperative Monitoring of Flaps
title_full_unstemmed Application of Photoplethysmography Combined with Deep Learning in Postoperative Monitoring of Flaps
title_short Application of Photoplethysmography Combined with Deep Learning in Postoperative Monitoring of Flaps
title_sort application of photoplethysmography combined with deep learning in postoperative monitoring of flaps
topic photoplethysmography
deep learning
flap
url https://zgylqxzz.xml-journal.net/article/doi/10.12455/j.issn.1671-7104.230624
work_keys_str_mv AT jingyang applicationofphotoplethysmographycombinedwithdeeplearninginpostoperativemonitoringofflaps
AT xinleiyang applicationofphotoplethysmographycombinedwithdeeplearninginpostoperativemonitoringofflaps
AT yuweigao applicationofphotoplethysmographycombinedwithdeeplearninginpostoperativemonitoringofflaps
AT chunleizhang applicationofphotoplethysmographycombinedwithdeeplearninginpostoperativemonitoringofflaps
AT diwang applicationofphotoplethysmographycombinedwithdeeplearninginpostoperativemonitoringofflaps
AT taosong applicationofphotoplethysmographycombinedwithdeeplearninginpostoperativemonitoringofflaps