Cargando…

Machine Learning-Based Three-Month Outcome Prediction in Acute Ischemic Stroke: A Single Cerebrovascular-Specialty Hospital Study in South Korea

Background: Functional outcomes after acute ischemic stroke are of great concern to patients and their families, as well as physicians and surgeons who make the clinical decisions. We developed machine learning (ML)-based functional outcome prediction models in acute ischemic stroke. Methods: This r...

Descripción completa

Detalles Bibliográficos
Autores principales: Park, Dougho, Jeong, Eunhwan, Kim, Haejong, Pyun, Hae Wook, Kim, Haemin, Choi, Yeon-Ju, Kim, Youngsoo, Jin, Suntak, Hong, Daeyoung, Lee, Dong Woo, Lee, Su Yun, Kim, Mun-Chul
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2021
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8534707/
https://www.ncbi.nlm.nih.gov/pubmed/34679606
http://dx.doi.org/10.3390/diagnostics11101909
_version_ 1784587609363709952
author Park, Dougho
Jeong, Eunhwan
Kim, Haejong
Pyun, Hae Wook
Kim, Haemin
Choi, Yeon-Ju
Kim, Youngsoo
Jin, Suntak
Hong, Daeyoung
Lee, Dong Woo
Lee, Su Yun
Kim, Mun-Chul
author_facet Park, Dougho
Jeong, Eunhwan
Kim, Haejong
Pyun, Hae Wook
Kim, Haemin
Choi, Yeon-Ju
Kim, Youngsoo
Jin, Suntak
Hong, Daeyoung
Lee, Dong Woo
Lee, Su Yun
Kim, Mun-Chul
author_sort Park, Dougho
collection PubMed
description Background: Functional outcomes after acute ischemic stroke are of great concern to patients and their families, as well as physicians and surgeons who make the clinical decisions. We developed machine learning (ML)-based functional outcome prediction models in acute ischemic stroke. Methods: This retrospective study used a prospective cohort database. A total of 1066 patients with acute ischemic stroke between January 2019 and March 2021 were included. Variables such as demographic factors, stroke-related factors, laboratory findings, and comorbidities were utilized at the time of admission. Five ML algorithms were applied to predict a favorable functional outcome (modified Rankin Scale 0 or 1) at 3 months after stroke onset. Results: Regularized logistic regression showed the best performance with an area under the receiver operating characteristic curve (AUC) of 0.86. Support vector machines represented the second-highest AUC of 0.85 with the highest F1-score of 0.86, and finally, all ML models applied achieved an AUC > 0.8. The National Institute of Health Stroke Scale at admission and age were consistently the top two important variables for generalized logistic regression, random forest, and extreme gradient boosting models. Conclusions: ML-based functional outcome prediction models for acute ischemic stroke were validated and proven to be readily applicable and useful.
format Online
Article
Text
id pubmed-8534707
institution National Center for Biotechnology Information
language English
publishDate 2021
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-85347072021-10-23 Machine Learning-Based Three-Month Outcome Prediction in Acute Ischemic Stroke: A Single Cerebrovascular-Specialty Hospital Study in South Korea Park, Dougho Jeong, Eunhwan Kim, Haejong Pyun, Hae Wook Kim, Haemin Choi, Yeon-Ju Kim, Youngsoo Jin, Suntak Hong, Daeyoung Lee, Dong Woo Lee, Su Yun Kim, Mun-Chul Diagnostics (Basel) Article Background: Functional outcomes after acute ischemic stroke are of great concern to patients and their families, as well as physicians and surgeons who make the clinical decisions. We developed machine learning (ML)-based functional outcome prediction models in acute ischemic stroke. Methods: This retrospective study used a prospective cohort database. A total of 1066 patients with acute ischemic stroke between January 2019 and March 2021 were included. Variables such as demographic factors, stroke-related factors, laboratory findings, and comorbidities were utilized at the time of admission. Five ML algorithms were applied to predict a favorable functional outcome (modified Rankin Scale 0 or 1) at 3 months after stroke onset. Results: Regularized logistic regression showed the best performance with an area under the receiver operating characteristic curve (AUC) of 0.86. Support vector machines represented the second-highest AUC of 0.85 with the highest F1-score of 0.86, and finally, all ML models applied achieved an AUC > 0.8. The National Institute of Health Stroke Scale at admission and age were consistently the top two important variables for generalized logistic regression, random forest, and extreme gradient boosting models. Conclusions: ML-based functional outcome prediction models for acute ischemic stroke were validated and proven to be readily applicable and useful. MDPI 2021-10-15 /pmc/articles/PMC8534707/ /pubmed/34679606 http://dx.doi.org/10.3390/diagnostics11101909 Text en © 2021 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Park, Dougho
Jeong, Eunhwan
Kim, Haejong
Pyun, Hae Wook
Kim, Haemin
Choi, Yeon-Ju
Kim, Youngsoo
Jin, Suntak
Hong, Daeyoung
Lee, Dong Woo
Lee, Su Yun
Kim, Mun-Chul
Machine Learning-Based Three-Month Outcome Prediction in Acute Ischemic Stroke: A Single Cerebrovascular-Specialty Hospital Study in South Korea
title Machine Learning-Based Three-Month Outcome Prediction in Acute Ischemic Stroke: A Single Cerebrovascular-Specialty Hospital Study in South Korea
title_full Machine Learning-Based Three-Month Outcome Prediction in Acute Ischemic Stroke: A Single Cerebrovascular-Specialty Hospital Study in South Korea
title_fullStr Machine Learning-Based Three-Month Outcome Prediction in Acute Ischemic Stroke: A Single Cerebrovascular-Specialty Hospital Study in South Korea
title_full_unstemmed Machine Learning-Based Three-Month Outcome Prediction in Acute Ischemic Stroke: A Single Cerebrovascular-Specialty Hospital Study in South Korea
title_short Machine Learning-Based Three-Month Outcome Prediction in Acute Ischemic Stroke: A Single Cerebrovascular-Specialty Hospital Study in South Korea
title_sort machine learning-based three-month outcome prediction in acute ischemic stroke: a single cerebrovascular-specialty hospital study in south korea
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8534707/
https://www.ncbi.nlm.nih.gov/pubmed/34679606
http://dx.doi.org/10.3390/diagnostics11101909
work_keys_str_mv AT parkdougho machinelearningbasedthreemonthoutcomepredictioninacuteischemicstrokeasinglecerebrovascularspecialtyhospitalstudyinsouthkorea
AT jeongeunhwan machinelearningbasedthreemonthoutcomepredictioninacuteischemicstrokeasinglecerebrovascularspecialtyhospitalstudyinsouthkorea
AT kimhaejong machinelearningbasedthreemonthoutcomepredictioninacuteischemicstrokeasinglecerebrovascularspecialtyhospitalstudyinsouthkorea
AT pyunhaewook machinelearningbasedthreemonthoutcomepredictioninacuteischemicstrokeasinglecerebrovascularspecialtyhospitalstudyinsouthkorea
AT kimhaemin machinelearningbasedthreemonthoutcomepredictioninacuteischemicstrokeasinglecerebrovascularspecialtyhospitalstudyinsouthkorea
AT choiyeonju machinelearningbasedthreemonthoutcomepredictioninacuteischemicstrokeasinglecerebrovascularspecialtyhospitalstudyinsouthkorea
AT kimyoungsoo machinelearningbasedthreemonthoutcomepredictioninacuteischemicstrokeasinglecerebrovascularspecialtyhospitalstudyinsouthkorea
AT jinsuntak machinelearningbasedthreemonthoutcomepredictioninacuteischemicstrokeasinglecerebrovascularspecialtyhospitalstudyinsouthkorea
AT hongdaeyoung machinelearningbasedthreemonthoutcomepredictioninacuteischemicstrokeasinglecerebrovascularspecialtyhospitalstudyinsouthkorea
AT leedongwoo machinelearningbasedthreemonthoutcomepredictioninacuteischemicstrokeasinglecerebrovascularspecialtyhospitalstudyinsouthkorea
AT leesuyun machinelearningbasedthreemonthoutcomepredictioninacuteischemicstrokeasinglecerebrovascularspecialtyhospitalstudyinsouthkorea
AT kimmunchul machinelearningbasedthreemonthoutcomepredictioninacuteischemicstrokeasinglecerebrovascularspecialtyhospitalstudyinsouthkorea