A novel machine learning-based radiomic model for diagnosing high bleeding risk esophageal varices in cirrhotic patients

doi:10.1007/s12072-021-10292-6

CORC > 自动化研究所 > 中国科学院自动化研究所 > 数字内容技术与服务研究中心 > 远程智能医疗

	A novel machine learning-based radiomic model for diagnosing high bleeding risk esophageal varices in cirrhotic patients
	Yan, Yijie 5; Li, Yue 4,5; Fan, Chunlei 5; Zhang, Yuening 5; Zhang, Shibin 5; Wang, Zhi 3; Huang, Tehui 3; Ding, Zhenjia 2; Hu, Keqin 1; Li, Lei 5
刊名	HEPATOLOGY INTERNATIONAL
	2022-04-01
卷号	16 期号:2 页码:423-432
关键词	Machine learning Radiomic model Esophageal varices Cirrhotic portal hypertension Computed tomography Endoscopy
ISSN号	1936-0533
DOI	10.1007/s12072-021-10292-6
通讯作者	Li, Lei(13699119545@163.com) ; Ding, Huiguo(dinghuiguo@ccmu.edu.cn)
英文摘要	Background and aim To develop and validate a novel machine learning-based radiomic model (RM) for diagnosing high bleeding risk esophageal varices (HREV) in patients with cirrhosis. Methods A total of 796 qualified participants were enrolled. In training cohort, 218 cirrhotic patients with mild esophageal varices (EV) and 240 with HREV RM were included to training and internal validation groups. Additionally, 159 and 340 cirrhotic patients with mild EV and HREV RM, respectively, were used for external validation. Interesting regions of liver, spleen, and esophagus were labeled on the portal venous-phase enhanced CT images. RM was assessed by area under the receiver operating characteristic curves (AUROC), sensitivity, specificity, calibration and decision curve analysis (DCA). Results The AUROCs for mild EV RM in training and internal validation were 0.943 and 0.732, sensitivity and specificity were 0.863, 0.773 and 0.763, 0.763, respectively. The AUROC, sensitivity, and specificity were 0.654, 0.773 and 0.632, respectively, in external validation. Interestingly, the AUROCs for HREV RM in training and internal validation were 0.983 and 0.834, sensitivity and specificity were 0.948, 0.916 and 0.977, 0.969, respectively. The related AUROC, sensitivity and specificity were 0.736, 0.690 and 0.762 in external validation. Calibration and DCA indicated RM had good performance. Compared with Baveno VI and its expanded criteria, HREV RM had a higher accuracy and net reclassification improvements that were as high as 49.0% and 32.8%. Conclusion The present study developed a novel non-invasive RM for diagnosing HREV in cirrhotic patients with high accuracy. However, this RM still needs to be validated by a large multi-center cohort.
资助项目	State Key Projects Specialized on Infectious Diseases[2017ZX10203202-004] ; Digestive Medical Coordinated Development Center of Beijing Hospitals Authority[XXZ0801] ; Sino-German Cooperation Group[GZ1517]
WOS关键词	BAVENO VI CRITERIA ; MANAGEMENT
WOS研究方向	Gastroenterology & Hepatology
语种	英语
出版者	SPRINGER
WOS记录号	WOS:000777385800001
资助机构	State Key Projects Specialized on Infectious Diseases ; Digestive Medical Coordinated Development Center of Beijing Hospitals Authority ; Sino-German Cooperation Group
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/48213]
专题	数字内容技术与服务研究中心_远程智能医疗
通讯作者	Li, Lei; Ding, Huiguo
作者单位	1.Univ Calif Irvine, Div Gastroenterol & Hepatol, Sch Med, Orange, CA 92668 USA 2.Chinese Acad Sci, Inst Automat, Beijing 100190, Peoples R China 3.Blot Info & Tech Beijing Co Ltd, Beijing 101200, Peoples R China 4.Harbin Med Univ, Dept Gastroenterol, Affiliated Hosp 4, Harbin 150001, Heilongjiang, Peoples R China 5.Capital Med Univ, Dept Gastroenterol & Hepatol, Beijing Youan Hosp, Beijing 100069, Peoples R China
推荐引用方式 GB/T 7714	Yan, Yijie,Li, Yue,Fan, Chunlei,et al. A novel machine learning-based radiomic model for diagnosing high bleeding risk esophageal varices in cirrhotic patients[J]. HEPATOLOGY INTERNATIONAL,2022,16(2):423-432.
APA	Yan, Yijie.,Li, Yue.,Fan, Chunlei.,Zhang, Yuening.,Zhang, Shibin.,...&Ding, Huiguo.(2022).A novel machine learning-based radiomic model for diagnosing high bleeding risk esophageal varices in cirrhotic patients.HEPATOLOGY INTERNATIONAL,16(2),423-432.
MLA	Yan, Yijie,et al."A novel machine learning-based radiomic model for diagnosing high bleeding risk esophageal varices in cirrhotic patients".HEPATOLOGY INTERNATIONAL 16.2(2022):423-432.