Page 7 - Read Online

Hsu et al. Vessel Plus 2021;5:2 Vessel Plus
DOI: 10.20517/2574-1209.2020.45

Original Article Open Access

Comparison of outcome prediction models post-
stroke for a population-based registry with clinical

variables collected at admission vs. discharge

Kai-Cheng Hsu 1,2,3 , Ching-Heng Lin , Kory R. Johnson , Yang C. Fann , Chung Y. Hsu , Chon-Haw Tsai ,
5
6
4
5
3
Po-Lin Chen , Wei-Lun Chang , Po-Yen Yeh , Cheng-Yu Wei , Taiwan Stroke Registry Investigators #
8
9
7
10
1 School of Medicine, College of Medicine, China Medical University, Taichung, Taiwan.
2 Artificial Intelligence Center for Medical Diagnosis, China Medical University Hospital, Taichung, Taiwan.
3 Department of Neurology, China Medical University Hospital, Taichung, Taiwan
4 Center for Artificial Intelligence in Medicine, Chang Gung Memorial Hospital, Taoyuan, Taiwan.
5 Bioinformatics Section, National Institute of Neurological Disorder and Stroke, National Institutes of Health, Bethesda,
Maryland, USA.
6 Graduate Institute of Biomedical Sciences, China Medical University, Taichung, Taiwan.
7 Neurological Institute, Taichung Veterans General Hospital, Taichung, Taiwan.
8 Department of Neurology, Show Chwan Memorial Hospital, Changhua County, Taiwan.
9 Department of Neurology, St. Martin De Porres Hospital, Chiayi, Taiwan.
10 Department of Neurology, Chang Bing Show Chwan Memorial Hospital, Changhua County, Taiwan.
# Listed in Supplemental Appendix I.
Correspondence to: Dr. Yang C. Fann, Intramural IT & Bioinformatics Program, National Institute of Neurological Disorders and
Received: First Decision: Revised: Accepted: Published: x Stroke, National Institutes of Health 9000 Rockville Pike, Bethesda, MA 20892, USA. E-mail: fann@ninds.nih.gov
Science Editor: Copy Editor: Production Editor: Jing Yu How to cite this article: Hsu KC, Lin CH, Johnson KR, Fann YC, Hsu CY, Tsai CH, Chen PL, Chang WL, Yeh PY, Wei CY; Taiwan
Stroke Registry Investigators. Comparison of outcome prediction models post-stroke for a population-based registry with
clinical variables collected at admission vs. Discharge. Vessel Plus 2021;5:2. http://dx.doi.org/10.20517/2574-1209.2020.45

Received: 31 Aug 2020 First Decision: 19 Nov 2020 Revised: 29 Nov 2020 Accepted: 23 Dec 2020 Published: 15 Jan 2021
Academic Editor: Elisa Ciceri Copy Editor: Monica Wang Production Editor: Jing Yu

Abstract
Aim: The ability to predict outcomes can help clinicians to better triage and treat stroke patients. We aimed to
build prediction models using clinical data at admission and discharge to assess predictors highly relevant to stroke
outcomes.

Methods: A total of 37,094 patients from the Taiwan Stroke Registry (TSR) were enrolled to ascertain clinical
variables and predict their mRS outcomes at 90 days. The performances (i.e., the area under the curves (AUCs)) of
these independent predictors identified by logistic regression (LR) based on clinical variables were compared.

Results: Several outcome prediction models based on different patient subgroups were evaluated, and their AUCs
based on all clinical variables at admission and discharge were 0.85-0.88 and 0.92-0.96, respectively. After feature
© The Author(s) 2021. Open Access This article is licensed under a Creative Commons Attribution 4.0
International License (https://creativecommons.org/licenses/by/4.0/), which permits unrestricted use,
sharing, adaptation, distribution and reproduction in any medium or format, for any purpose, even commercially, as long
as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license,
and indicate if changes were made.

www.vpjournal.net