文献类型：期刊文献

英文题名：Potential predictive value of CT radiomics features for treatment response in patients with COVID-19

作者：Huang, Gang[1];Hui, Zhongyi[2];Ren, Jialiang[3];Liu, Ruifang[4];Cui, Yaqiong[4];Ma, Ying[4];Han, Yalan[4];Zhao, Zehao[5];Lv, Suzhen[6];Zhou, Xing[1];Chen, Lijun[1];Bao, Shisan[7];Zhao, Lianping[1,8]

第一作者：Huang, Gang

通信作者：Zhao, LP[1]

机构：[1]Gansu Prov Hosp, Dept Radiol, Lanzhou, Gansu, Peoples R China;[2]Tianshui Combine Tradit Chinese & Western Med Hosp, Dept CT, Tianshui, Gansu, Peoples R China;[3]GE Healthcare China, Beijing, Peoples R China;[4]Gansu Univ Chinese Med, Clin Med Sch, Lanzhou, Gansu, Peoples R China;[5]First Hosp Tianshui, Ward Resp Med 2, Tianshui, Gansu, Peoples R China;[6]First Hosp Tianshui, Dept Radiol, Tianshui, Gansu, Peoples R China;[7]Univ Sydney, Sch Med Sci, Sydney, NSW, Australia;[8]Gansu Prov Hosp, Dept Radiol, Lanzhou 730000, Gansu, Peoples R China

第一机构：Gansu Prov Hosp, Dept Radiol, Lanzhou, Gansu, Peoples R China

通信机构：[1]corresponding author), Gansu Prov Hosp, Dept Radiol, Lanzhou 730000, Gansu, Peoples R China.

年份：2023

卷号：17

期号：5

起止页码：394

外文期刊名：CLINICAL RESPIRATORY JOURNAL

收录：;Scopus(收录号：2-s2.0-85150882533);WOS:【SCI-EXPANDED(收录号:WOS:000950972200001)】；

语种：英文

外文关键词：COVID-19; disease prognosis; radiomics; tomography; X-ray computed

摘要：IntroductionThis study aims to explore the predictive value of CT radiomics and clinical characteristics for treatment response in COVID-19 patients. MethodsData were collected from clinical/auxiliary examinations and follow-ups of COVID-19 patients. Whole lung radiomics feature extraction was performed at baseline chest CT. Radiomics, clinical, and combined features (nomogram) were evaluated for predicting treatment response. ResultsAmong 36 COVID-19 patients, mild, common, severe, and critical disease symptoms were found in 1, 21, 13, and 1 of them, respectively. Twenty-five (1 mild, 18 common, and 6 severe) patients showed a good response to treatment and 11 poor/fair responses. The clinical classification (p = 0.025) and serum creatinine (p = 0.010) on admission and small area emphasis (p = 0.036) from radiomics analysis significantly differed between the two groups. Predictive models were constructed based on the radiomics, clinical features, and nomogram showing an area under the curve of 0.651, 0.836, and 0.869, respectively. The nomogram achieved good calibration. ConclusionThis new, non-invasive, and low-cost prediction model that combines the radiomics and clinical features is useful for identifying COVID-19 patients who may not respond well to treatment.