An early screening model of pulse detection technology for hepatic steatosis

作     者：Wenjie Wu Chunke Zhang Xiaotian Ma Rui Guo Jianjun Yan Yiqin Wang Haixia Yan Yeqing Zhang Wenjie Wu;Chunke Zhang;Xiaotian Ma;Rui Guo;Jianjun Yan;Yiqin Wang;Haixia Yan;Yeqing Zhang

作者机构：Department of Basic Medical ScienceShanghai University of Traditional Chinese MedicineShanghai 201203China Institute of Intelligent Perception and DiagnosisSchool of Mechanical and Power EngineeringEast China University of Science and TechnologyShanghai 200237China Department of Chinese Internal MedicineShanghai Municipal Hospital of Traditional Chinese MedicineShanghai University of Traditional Chinese MedicineShanghai 200071China 

出 版 物：《Intelligent Medicine》 (智慧医学（英文）)

年 卷 期：2023年第3卷第4期

页      面：280-286页

核心收录：

学科分类：1002[医学-临床医学] 1001[医学-基础医学(可授医学、理学学位)] 100201[医学-内科学(含：心血管病、血液病、呼吸系病、消化系病、内分泌与代谢病、肾病、风湿病、传染病)] 0812[工学-计算机科学与技术（可授工学、理学学位）] 10[医学] 

基　　金：This work was funded by the National Natural Science Foundation ofChina(Grant No.82074332) Shanghai Science and Technology Committee Funding(Grant No.19441901100) Shanghai Key Laboratory of Health Identification and Assessment(Grant No.21DZ2271000) 

主　　题：Pulse detection technology Time-domain method Hepatic steatosis Early screening Random forest 

摘      要：Background The increasing prevalence of hepatic steatosis presents a considerable challenge to public *** is a critical need for the development of novel preventive and screening strategies for this *** evaluated the potential applications of wrist pulse detection technology for the early detection of *** pulse time-domain features of a medical exam population with and without hepatic steatosis wereassessed to develop a screening model for this *** Participants were consecutively recruited from March 2021 to March 2022 in the medical examinationcenters of the Yueyang Hospital of Integrated Traditional Chinese and Western Medicine and the Shanghai Municipal Hospital of Traditional Chinese *** data from 255 participants,including general information(sex,age,and body mass index),and data related to glucose and blood lipids(fasting plasma glucose,triglyceride,total cholesterol,high-density lipoprotein,and low-density lipoprotein levels)were *** pulse signalswere acquired using a pulse detection device,and the pulse time-domain features,including t_(1),t_(4),t_(5),T,w_(1),w_(2),h_(2)/h_(1),h_(3)/h_(1),and h5/h_(1) were *** were assigned to hepatic steatosis and non-hepatic steatosisgroups according to their abdominal ultrasound examination *** clinical data and pulse time-domainfeatures were compared using chi-square and parametric or non-parametric statistical *** datasetswere used to construct screening models for hepatic steatosis based on the random forest *** datasetsfor modeling were defined as Dataset 1,containing blood glucose and lipid data and general information;Dataset2,containing time-domain features and general information;Dataset 3,containing time-domain features,bloodglucose and lipid data,and general *** evaluation metrics,accuracy,precision,recall,F1-score,andareas under the receiver operating characteristic curve(AUC