Luo Jing-Chao, Wang Huan, Tong Shang-Qing, Zhang Jia-Dong, Luo Ming-Hao, Zhao Qin-Yu, Zhang Yi-Jie, Zhang Ji-Yang, Gao Fei, Tu Guo-Wei, Luo Zhe
Department of Critical Care Medicine, Zhongshan Hospital, Fudan University, 200032 Shanghai, China.
Hybrid Imaging System Laboratory, Shanghai Engineering Research Center of Intelligent Vision and Imaging, School of Information Science and Technology, ShanghaiTech University, 201210 Shanghai, China.
Rev Cardiovasc Med. 2023 Jan 4;24(1):7. doi: 10.31083/j.rcm2401007. eCollection 2023 Jan.
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.
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.
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]).
Interpreting infrared thermography with deep learning enables accurate and non-invasive assessment of the severity of patients at risk of hypoperfusion.
低灌注是许多危重病的常见表现，可导致体表热分布异常。然而，热图像的解读具有挑战性。我们的目的是通过红外热成像结合深度学习方法，在前瞻性队列中评估有低灌注风险的危重病患者的死亡风险。
这项事后分析研究基于一个低灌注高风险队列。选择患者的腿部作为感兴趣区域。收集热图像和传统低灌注参数。尝试使用六种深度学习模型得出每位患者的死亡风险（范围：0至100%）。采用受试者操作特征曲线下面积（AUROC）评估预测准确性。
在由373名患者组成的队列中发生了55例医院死亡。传统低灌注（毛细血管再充盈时间和舒张压）和热（低温区比率和标准差）参数对医院死亡率显示出相似的预测准确性（AUROC分别为0.73和0.77）。深度学习方法，尤其是ResNet（18），可进一步提高准确性。当使用36%的临界值时，ResNet（18）的AUROC为0.94，敏感性为84%，特异性为91%。ResNet（18）在血压正常（13 [7至26]）、低血压（18 [8至32]）和休克（28 [14至62]）患者中的死亡风险呈显著上升趋势。
使用深度学习解读红外热成像能够准确且无创地评估有低灌注风险患者的严重程度。
