HETEROGENEOUS NETWORK ANALYSIS OF DISEASE CLINICAL TREATMENT MEASURES VIA MINING ELECTRONIC MEDICAL RECORD DATA

• 成果类型: Article
• 署名作者: Wang, Jiping; Li, Rong; Chang, Wei-Shan; Hsiao, Kai-Yuan; Shia, Ben-Chang; Ma, Shuangge
• 署名单位: Yale University; Fu Jen Catholic University; Fu Jen Catholic University
• 刊物名称: ANNALS OF APPLIED STATISTICS
• ISSN/ISSBN: 1932-6157
• DOI: 10.1214/24-AOAS1976
• 发表日期: 2025
• 页码: 637-654
• 关键词: readmission rates; health-care; mortality; models

摘要

The analysis of clinical treatment measures has been extensively conducted and can facilitate more effective resource management and assist in better understanding diseases. Most of the existing analyses have been focused on a single disease or many diseases combined. Partly motivated by the successes of gene-centric and phenotypic human disease network (HDN) research, there has been growing interest in network analysis of clinical treatment measures. However, existing studies have been limited by a lack of attention to heterogeneity and relevant covariates, ineffectiveness of methods, and low data quality. In this study our goal is to mine the Taiwan National Health Insurance Research Database (NHIRD), a large population-level electronic medical record (EMR) database, and construct HDNs for the number of outpatient visits and medical cost. Significantly advancing from existing literature, the proposed analysis accommodates heterogeneity and the effects of covariates. Additionally, the proposed method effectively accommodates zero inflation, Poisson distribution, high dimensionality, and network sparsity. Computational and theoretical properties are carefully examined. Simulation demonstrates the competitive performance of the proposed approach. In the analysis of NHIRD data, two and four subject groups are identified for outpatient visit and medical cost, respectively. The interconnections, hubs, and network modules are found to have sound implications.