iCOVID: interpretable deep learning framework for early recovery-time prediction of COVID-19 patients

doi:10.1038/s41746-021-00496-3

	iCOVID: interpretable deep learning framework for early recovery-time prediction of COVID-19 patients
	Wang, Jun 1; Liu, Chen 2; Li, Jingwen 3; Yuan, Cheng 1; Zhang, Lichi 1; Jin, Cheng 4; Xu, Jianwei 1; Wang, Yaqi 5; Wen, Yaofeng 1; Lu, Hongbing 6; Li, Biao 7; Chen, Chang 8; Li, Xiangdong 9,10; Shen, Dinggang11,12 ; Qian, Dahong 1,7; Wang, Jian 2
	2021
发表期刊	NPJ DIGITAL MEDICINE (IF:12.4[JCR-2023],15.2[5-Year])
ISSN	2398-6352
卷号	4 期号:1
DOI	10.1038/s41746-021-00496-3
摘要	Most prior studies focused on developing models for the severity or mortality prediction of COVID-19 patients. However, effective models for recovery-time prediction are still lacking. Here, we present a deep learning solution named iCOVID that can successfully predict the recovery-time of COVID-19 patients based on predefined treatment schemes and heterogeneous multimodal patient information collected within 48 hours after admission. Meanwhile, an interpretable mechanism termed FSR is integrated into iCOVID to reveal the features greatly affecting the prediction of each patient. Data from a total of 3008 patients were collected from three hospitals in Wuhan, China, for large-scale verification. The experiments demonstrate that iCOVID can achieve a time-dependent concordance index of 74.9% (95% CI: 73.6-76.3%) and an average day error of 4.4 days (95% CI: 4.2-4.6 days). Our study reveals that treatment schemes, age, symptoms, comorbidities, and biomarkers are highly related to recovery-time predictions.
URL	查看原文
收录类别	SCIE ; EI
语种	英语
WOS研究方向	Health Care Sciences & Services ; Medical Informatics
WOS类目	Health Care Sciences & Services ; Medical Informatics
WOS记录号	WOS:000686640000001
出版者	NATURE PORTFOLIO
原始文献类型	Article
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/127984
专题	生物医学工程学院_PI研究组_沈定刚组
通讯作者	Wang, Jun; Li, Xiangdong; Shen, Dinggang; Qian, Dahong; Wang, Jian
作者单位	1.Shanghai Jiao Tong Univ, Sch Biomed Engn, Shanghai, Peoples R China; 2.Army Med Univ, Third Mil Med Univ, Southwest Hosp, Dept Radiol, Chongqing, Peoples R China; 3.Army Med Univ, Third Mil Med Univ, Southwest Hosp, Dept Gastroenterol, Chongqing, Peoples R China; 4.Stanford Univ, Dept Radiat Oncol, Sch Med, Stanford, CA 94305 USA; 5.Commun Univ Zhejiang, Coll Media, Hangzhou, Peoples R China; 6.Zhejiang Univ, Coll Comp Sci & Technol, Hangzhou, Peoples R China; 7.Ruijin Hosp, Dept Nucl Med, Shanghai, Peoples R China; 8.Tongji Univ, Shanghai Pulm Hosp, Sch Med, Dept Thorac Surg, Shanghai, Peoples R China; 9.PLA, Gen Hosp, Southern Theatre Command, Dept Radiol, Guangzhou, Peoples R China; 10.Huoshenshan Hosp, Dept Radiol, Wuhan, Peoples R China; 11.ShanghaiTech Univ, Sch Biomed Engn, Shanghai, Peoples R China; 12.Shanghai United Imaging Intelligence Co Ltd, Dept Res & Dev, Shanghai, Peoples R China
通讯作者单位	生物医学工程学院
推荐引用方式 GB/T 7714	Wang, Jun,Liu, Chen,Li, Jingwen,et al. iCOVID: interpretable deep learning framework for early recovery-time prediction of COVID-19 patients[J]. NPJ DIGITAL MEDICINE,2021,4(1).
APA	Wang, Jun.,Liu, Chen.,Li, Jingwen.,Yuan, Cheng.,Zhang, Lichi.,...&Wang, Jian.(2021).iCOVID: interpretable deep learning framework for early recovery-time prediction of COVID-19 patients.NPJ DIGITAL MEDICINE,4(1).
MLA	Wang, Jun,et al."iCOVID: interpretable deep learning framework for early recovery-time prediction of COVID-19 patients".NPJ DIGITAL MEDICINE 4.1(2021).