文献类型：期刊文献

英文题名：A Just-in-Time Learning Based Monitoring and Classification Method for Hyper/Hypocalcemia Diagnosis

作者：Peng, Xin[1];Tang, Yang[1];He, Wangli[1];Du, Wenli[1];Qian, Feng[1]

机构：[1]East China Univ Sci & Technol, Key Lab Adv Control & Optimizat Chem Proc, Minist Educ, Shanghai 200237, Peoples R China

年份：2018

卷号：15

期号：3

起止页码：788

外文期刊名：IEEE-ACM TRANSACTIONS ON COMPUTATIONAL BIOLOGY AND BIOINFORMATICS

收录：;EI(收录号：20182405312341);WOS:【SCI-EXPANDED(收录号:WOS:000434295100010)】；

基金：This work was supported by the National Natural Science Foundation of China (61590923, 61333010, 61422303) and "Shu Guang" project supported by Shanghai Municipal Education Commission and Shanghai Education Development Foundation. The authors would like to thank the editor and the anonymous reviewers for their valuable suggestions. In addition, the authors would like to thank Prof. Babatunde Ogunnaike of the University of Delaware for his guide and suggestions, and Dr. Daniel Lees and Robert Lovelett of the University of Delaware for beneficial advice as well as language editing. Feng Qian and Wenli Du are the corresponding authors.

语种：英文

外文关键词：Calcium regulation; calcium-related pathologies; feature extraction; Just-in-Time modeling; mixture models; non-Gaussian process; online modeling; performance monitoring

摘要：This study focuses on the classification and pathological status monitoring of hyper/hypo-calcemia in the calciumregulatory system. By utilizing the Independent Component Analysis (ICA) mixture model, samples from healthy patients are collected, diagnosed, and subsequently classified according to their underlying behaviors, characteristics, and mechanisms. Then, a Just-in-Time Learning (JITL) has been employed in order to estimate the diseased status dynamically. In terms of JITL, for the purpose of the construction of an appropriate similarity index to identify relevant datasets, a novel similarity index based on the ICA mixture model is proposed in this paper to improve online model quality. The validity and effectiveness of the proposed approach have been demonstrated by applying it to the calciumregulatory systemunder various hypocalcemic and hypercalcemic diseased conditions.