Interpreting Infrared Thermography with Deep Learning to Assess the Mortality Risk of Critically Ill Patients at Risk of Hypoperfusion

doi:10.31083/j.rcm2401007

	Interpreting Infrared Thermography with Deep Learning to Assess the Mortality Risk of Critically Ill Patients at Risk of Hypoperfusion
	Luo, Jing-chao 1; Wang, Huan 1; Tong, Shang-qing2 ; Zhang, Jia-dong2 ; Luo, Ming-hao 1,3; Zhao, Qin-yu 4; Zhang, Yi-jie 1; Zhang, Ji-yang 5; Gao, Fei2 ; Tu, Guo-wei 1; Luo, Zhe 1,6
	2023
发表期刊	REVIEWS IN CARDIOVASCULAR MEDICINE (IF:1.9[JCR-2023],2.2[5-Year])
ISSN	1530-6550
EISSN	2153-8174
卷号	24 期号:1
发表状态	已发表
DOI	10.31083/j.rcm2401007
摘要	Background: Hypoperfusion, a common manifestation of many critical illnesses, could lead to abnormalities in body surface thermal distribution. However, the interpretation of thermal images is difficult. Our aim was to assess the mortality risk of critically ill patients at risk of hypoperfusion in a prospective cohort by infrared thermography combined with deep learning methods. Methods: This post-hoc study was based on a cohort at high-risk of hypoperfusion. Patients' legs were selected as the region of interest. Thermal images and conventional hypoperfusion parameters were collected. Six deep learning models were attempted to derive the risk of mortality (range: 0 to 100%) for each patient. The area under the receiver operating characteristic curve (AUROC) was used to evaluate predictive accuracy. Results: Fifty-five hospital deaths occurred in a cohort consisting of 373 patients. The conventional hypoperfusion (capillary refill time and diastolic blood pressure) and thermal (low temperature area rate and standard deviation) parameters demonstrated similar predictive accuracies for hospital mortality (AUROC 0.73 and 0.77). The deep learning methods, especially the ResNet (18), could further improve the accuracy. The AUROC of ResNet (18) was 0.94 with a sensitivity of 84% and a specificity of 91% when using a cutoff of 36%. ResNet (18) presented a significantly increasing trend in the risk of mortality in patients with normotension (13 [7 to 26]), hypotension (18 [8 to 32]) and shock (28 [14 to 62]). Conclusions: Interpreting infrared thermography with deep learning enables accurate and non-invasive assessment of the severity of patients at risk of hypoperfusion.
关键词	deep learning infrared thermography hypoperfusion critically ill patients secondary analysis
URL	查看原文
收录类别	SCI ; SCOPUS
语种	英语
资助项目	Smart Medical Care of Zhongshan Hospital[2020ZHZS01] ; Science and Technology Commission of Shanghai Municipality[20DZ2261200] ; National Natural Science Foundation of China[82070085] ; Clinical Research Project of Zhongshan Hospital["2020ZSLC38","2020ZSLC27"] ; Project for Elite Backbone of Zhongshan Hospital[2021ZSGG06] ; Research Project of Shanghai Municipal Health Commission[20214Y0136]
WOS研究方向	Cardiovascular System & Cardiology
WOS类目	Cardiac & Cardiovascular Systems
WOS记录号	WOS:000931335500017
出版者	IMR PRESS
引用统计	正在获取...
文献类型	期刊论文
条目标识符	https://kms.shanghaitech.edu.cn/handle/2MSLDSTB/284212
专题	信息科学与技术学院_硕士生信息科学与技术学院_PI研究组_高飞组
通讯作者	Gao, Fei; Tu, Guo-wei; Luo, Zhe
作者单位	1.Fudan Univ, Zhongshan Hosp, Dept Crit Care Med, Shanghai 200032, Peoples R China 2.ShanghaiTech Univ, Shanghai Engn Res Ctr Intelligent Vis & Imaging, Sch Informat Sci & Technol, Hybrid Imaging Syst Lab, Shanghai 201210, Peoples R China 3.Fudan Univ, Shanghai Med Coll, Shanghai 200032, Peoples R China 4.Australian Natl Univ, Coll Engn & Comp Sci, Canberra, ACT 2601, Australia 5.Fudan Univ, Zhongshan Hosp, Dept Informat & Intelligence Dev, Shanghai 200032, Peoples R China 6.Fudan Univ, Zhongshan Hosp, Dept Crit Care Med, Xiamen Branch, Xiamen 361015, Fujian, Peoples R China
通讯作者单位	上海科技大学
推荐引用方式 GB/T 7714	Luo, Jing-chao,Wang, Huan,Tong, Shang-qing,et al. Interpreting Infrared Thermography with Deep Learning to Assess the Mortality Risk of Critically Ill Patients at Risk of Hypoperfusion[J]. REVIEWS IN CARDIOVASCULAR MEDICINE,2023,24(1).
APA	Luo, Jing-chao.,Wang, Huan.,Tong, Shang-qing.,Zhang, Jia-dong.,Luo, Ming-hao.,...&Luo, Zhe.(2023).Interpreting Infrared Thermography with Deep Learning to Assess the Mortality Risk of Critically Ill Patients at Risk of Hypoperfusion.REVIEWS IN CARDIOVASCULAR MEDICINE,24(1).
MLA	Luo, Jing-chao,et al."Interpreting Infrared Thermography with Deep Learning to Assess the Mortality Risk of Critically Ill Patients at Risk of Hypoperfusion".REVIEWS IN CARDIOVASCULAR MEDICINE 24.1(2023).