Page 8 - Read Online

Page 2 of 12 Hsu et al. Vessel Plus 2021;5:2 I http://dx.doi.org/10.20517/2574-1209.2020.45

selections, the input features decreased from 140 to 2-18 (including age of onset and NIHSS at admission) and from
262 to 2-8 (including NIHSS at discharge and mRS at discharge) at admission and discharge, respectively. With
only a few selected key clinical features, our models can provide better performance than those previously reported
in the literature.

Conclusion: This study proposed high performance prognostics outcome prediction models derived from a
population-based nationwide stroke registry even with reduced LR-selected clinical features. These key clinical
features can help physicians to better focus on stroke patients to triage for best outcome in acute settings.

Keywords: Stroke outcome, logistic regression, National Institutes of Health Stroke Scale, modified Rankin Scale,
population-based stroke registry

INTRODUCTION
Stroke is the second leading cause of death worldwide, affecting one in six adults, with an estimated
[1]
16.9 million cases of stroke in 2010 . Despite a 42% decrease in the number of strokes in high-income
countries over the past four decades, stroke incidence in low- and middle-income countries has more than
[1,2]
doubled . Moreover, stroke for people living in low- and middle-income countries occurs 15 years earlier
[1-3]
on average than those living in high-income countries . Given this disparity, continued effort to improve
stroke management remains a major health and socioeconomic challenge and priority worldwide.

Prediction of clinical outcome after stroke has been proposed and studied as one potential approach to
improve stroke care management . Specifically, the prediction of disability due to stroke can beneficially
[4]
assist clinicians in making decisions regarding what tests to order, choice of therapy, how to communicate
[5,6]
with the patient and family, as well as assist in reaching shared decisions . Modeling for such prediction
has been performed using different statistical techniques in conjunction with varying input information,
and the success of these models has been varied and cross-evaluated . What has been learned is that
[7,8]
some modeling techniques perform better than others and that the input information with questionable
quality selected to be included in modeling can influence prediction success, while the sample size of the
information can generate bias and limit model generalizability. As such, further work in this regard is
needed using high-quality input information with ample sample sizes to bring confidence to the prediction
models as having high predictive power for disability post-stroke to be used in real-world medical
practices.

This study aimed to identify prediction models for functional outcomes following stroke, to appraise these
models using current guidelines, and to determine the pooled accuracy of identified models using a well-
established national registry. The Taiwan Stroke Registry (TSR) is a national research database collecting
data from over 64 hospitals and medical centers across the nation with stroke patients occurring over a
12-year period [9,10] . Using this database, we sought to develop a multiparametric tool to estimate the
probability of achieving functional improvement and identify the important predictors at different key
time points for the stroke outcome prediction, aiming to help clinicians triage the stroke patients for best
outcomes.

METHODS
Patient data
[9]
Patients used in this study were from a nationwide prospective registry, the Taiwan Stroke Registry (TSR) ,
collected from 64 participating stroke centers with a confirmed diagnosis of acute cerebrovascular
[10]
disease , i.e., ischemic and hemorrhagic stroke excluding transient ischemic attack and subarachnoid