Developing a stroke severity index based on administrative data was feasible using data mining techniques

NCU Institutional Repository > 管理學院 > 資訊管理學系 > 期刊論文 > Item 987654321/106586

請使用永久網址來引用或連結此文件: https://ir.lib.ncu.edu.tw/handle/987654321/106586

題名:	Developing a stroke severity index based on administrative data was feasible using data mining techniques
作者:	胡雅涵;Sung, Sheng-Feng;Hsieh, Cheng-Yang;Kao Yang, Yea-Huei;Lin, Huey-Juan;Chen, Chih-Hung;Chen, Yu-Wei;Hu, Ya-Han
貢獻者:	管理學院資訊管理學系
關鍵詞:	Acute ischemic stroke;Administrative Claims, Healthcare;Administrative data;Aged;Cardiovascular disease;Clinical medicine;Correlation coefficient;Data Mining;Databases, Factual;Disease severity;Epidemiology;Feasibility Studies;Female;Health care;Health insurance;Hospitalization;Hospitals;Humans;Intensive care;Internal Medicine;Intubation;Laboratories;Male;Medical imaging;Medical research;Models, Statistical;Mortality;Outcomes research;Patients;Prediction model;Prediction models;Severity of Illness Index;Standard deviation;Stroke;Stroke - diagnosis;Studies;Suctioning
日期:	2015-11-01
上傳時間:	2026-04-23 13:30:21 (UTC+8)
出版者:	United States: Elsevier Inc
摘要:	摘要： Case-mix adjustment is difficult for stroke outcome studies using administrative data. However, relevant prescription, laboratory, procedure, and service claims might be surrogates for stroke severity. This study proposes a method for developing a stroke severity index (SSI) by using administrative data. We identified 3,577 patients with acute ischemic stroke from a hospital-based registry and analyzed claims data with plenty of features. Stroke severity was measured using the National Institutes of Health Stroke Scale (NIHSS). We used two data mining methods and conventional multiple linear regression (MLR) to develop prediction models, comparing the model performance according to the Pearson correlation coefficient between the SSI and the NIHSS. We validated these models in four independent cohorts by using hospital-based registry data linked to a nationwide administrative database. We identified seven predictive features and developed three models. The k-nearest neighbor model (correlation coefficient, 0.743; 95% confidence interval: 0.737, 0.749) performed slightly better than the MLR model (0.742; 0.736, 0.747), followed by the regression tree model (0.737; 0.731, 0.742). In the validation cohorts, the correlation coefficients were between 0.677 and 0.725 for all three models. The claims-based SSI enables adjusting for disease severity in stroke studies using administrative data. 其他題名： J Clin Epidemiol 出版者： United States: Elsevier Inc 出版日期： 2015-11-01 出處： Journal of clinical epidemiology, 2015-11, Vol.68 (11), p.1292-1300 資源來源： Healthcare Administration Database (Proquest) 版權： 2015 Elsevier Inc. 版權： Elsevier Inc. 版權： Copyright © 2015 Elsevier Inc. All rights reserved. 版權： Copyright Elsevier Limited Nov 2015 識別號： ISSN: 0895-4356 識別號： ISSN: 1878-5921 識別號： EISSN: 1878-5921 識別號： DOI: 10.1016/j.jclinepi.2015.01.009 識別號： PMID: 25700940
顯示於類別:	[資訊管理學系] 期刊論文

文件中的檔案:

檔案	描述	大小	格式	瀏覽次數
index.html		0Kb	HTML	19	檢視/開啟

在NCUIR中所有的資料項目都受到原著作權保護.

社群 sharing

資料載入中.....