Hahm Cho Rom, Lee Young Kyung, Oh Dong Hyun, Ahn Mi Young, Choi Jae-Phil, Kang Na Ree, Oh Jungkyun, Choi Hanzo, Kim Suhyun
Department of Internal Medicine, Seoul Medical Center, Seoul, Republic of Korea.
Department of Radiology, Seoul Medical Center, Seoul, Republic of Korea.
Tuberc Respir Dis (Seoul). 2021 Apr;84(2):115-124. doi: 10.4046/trd.2020.0139. Epub 2021 Jan 5.
This study aimed to determine the parameters for worsening oxygenation in non-severe coronavirus disease 2019 (COVID-19) pneumonia.
This retrospective cohort study included cases of confirmed COVID-19 pneumonia in a public hospital in South Korea. The worsening oxygenation group was defined as that with SpO2 ≤94% or received oxygen or mechanical ventilation (MV) throughout the clinical course versus the non-worsening oxygenation group that did not experience any respiratory event. Parameters were compared, and the extent of viral pneumonia from an initial chest computed tomography (CT) was calculated using artificial intelligence (AI) and measured visually by a radiologist.
We included 136 patients, with 32 (23.5%) patients in the worsening oxygenation group; of whom, two needed MV and one died. Initial vital signs and duration of symptoms showed no difference between the two groups; however, univariate logistic regression analysis revealed that a variety of parameters on admission were associated with an increased risk of a desaturation event. A subset of patients was studied to eliminate potential bias, that ferritin ≥280 μg/L (p=0.029), lactate dehydrogenase ≥240 U/L (p=0.029), pneumonia volume (p=0.021), and extent (p=0.030) by AI, and visual severity scores (p=0.042) were the predictive parameters for worsening oxygenation in a sex-, age-, and comorbid illness-matched case-control study using propensity score (n=52).
Our study suggests that initial CT evaluated by AI or visual severity scoring as well as serum markers of inflammation on admission are significantly associated with worsening oxygenation in this COVID-19 pneumonia cohort.
本研究旨在确定非重症2019冠状病毒病（COVID-19）肺炎患者氧合恶化的参数。
这项回顾性队列研究纳入了韩国一家公立医院确诊的COVID-19肺炎病例。氧合恶化组定义为在整个临床过程中SpO2≤94%或接受吸氧或机械通气（MV）的患者，而非氧合未恶化组则未经历任何呼吸事件。对参数进行比较，并使用人工智能（AI）计算初始胸部计算机断层扫描（CT）的病毒性肺炎范围，同时由放射科医生进行视觉测量。
我们纳入了136例患者，其中32例（23.5%）属于氧合恶化组；其中，2例需要机械通气，1例死亡。两组患者的初始生命体征和症状持续时间无差异；然而，单因素逻辑回归分析显示，入院时的多种参数与去饱和事件风险增加相关。为消除潜在偏倚，对一部分患者进行了研究，在一项使用倾向评分的性别、年龄和合并症匹配的病例对照研究（n=52）中，铁蛋白≥280μg/L（p=0.029）、乳酸脱氢酶≥240U/L（p=0.029）、肺炎体积（p=0.021）、AI测量的范围（p=0.030）以及视觉严重程度评分（p=0.042）是氧合恶化的预测参数。
我们的研究表明，在这个COVID-19肺炎队列中，通过AI或视觉严重程度评分评估的初始CT以及入院时的炎症血清标志物与氧合恶化显著相关。
