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...
Gespeichert in:
Veröffentlicht in: | Diagnostics (Basel) 2021-10, Vol.11 (10), p.1909, Article 1909 |
---|---|
Hauptverfasser: | , , , , , , , , , , , |
Format: | Artikel |
Sprache: | eng |
Schlagworte: | |
Online-Zugang: | Volltext |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
container_end_page | |
---|---|
container_issue | 10 |
container_start_page | 1909 |
container_title | Diagnostics (Basel) |
container_volume | 11 |
creator | 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 |
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. |
doi_str_mv | 10.3390/diagnostics11101909 |
format | Article |
fullrecord | <record><control><sourceid>proquest_pubme</sourceid><recordid>TN_cdi_pubmedcentral_primary_oai_pubmedcentral_nih_gov_8534707</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><doaj_id>oai_doaj_org_article_0cdbcb808b0a4a578b3d742bba3cf050</doaj_id><sourcerecordid>2584363437</sourcerecordid><originalsourceid>FETCH-LOGICAL-c476t-f6b41ee8dc40bd49f86c39be84794adaab1dd1174a863c41366ec272f3b701ac3</originalsourceid><addsrcrecordid>eNqNks1uEzEUhUcIRKvSJ2BjiQ0SGrDHnrGHBVKIgEakKlLKeuSfO4nDxE5tT1HegkfG01QVRSzwxpZ9znft61MULwl-S2mL3xkr187HZHUkhGDS4vZJcVphXpeMEfH0j_VJcR7jFufREiqq-nlxQlnD2wY3p8WvS6k31gFaggzOunX5UUYw6HoTAMpL79IGXY1J-x2gbwGM1cl6h6xDMz0mQIuoN7CzGq1S8D_gPZqhVaYMgOYQQAV_K6MeBxnK1R60lUM6oAsf9zbJIXtGc5hYKz_mOl99APmieNbLIcL5_XxWfP_86Xp-US6vvizms2WpGW9S2TeKEQBhNMPKsLYXjaatAsF4y6SRUhFjCOFMioZqRmjTgK541VPFMZGanhWLI9d4ue32we5kOHRe2u5uw4d1J0Nu7wAd1kZpJbBQWDJZc6Go4axSSlLd4xpn1ocjaz-qHRgNLgU5PII-PnF20639bSdqyjjmGfD6HhD8zQgxdTsbNQyDdODH2FX19C6KKc3SV39Jt34MLrfqTkUbyugEpEeVDj7GAP3DZQjupgB1_whQdr05un6C8n3UFpyGB2cOECcMi7aaskSyWvy_ep4_fErO3I8u0d-7_93P</addsrcrecordid><sourcetype>Open Website</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2584363437</pqid></control><display><type>article</type><title>Machine Learning-Based Three-Month Outcome Prediction in Acute Ischemic Stroke: A Single Cerebrovascular-Specialty Hospital Study in South Korea</title><source>DOAJ Directory of Open Access Journals</source><source>PubMed Central Open Access</source><source>MDPI - Multidisciplinary Digital Publishing Institute</source><source>Web of Science - Science Citation Index Expanded - 2021<img src="https://exlibris-pub.s3.amazonaws.com/fromwos-v2.jpg" /></source><source>EZB-FREE-00999 freely available EZB journals</source><source>PubMed Central</source><creator>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</creator><creatorcontrib>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</creatorcontrib><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.</description><identifier>ISSN: 2075-4418</identifier><identifier>EISSN: 2075-4418</identifier><identifier>DOI: 10.3390/diagnostics11101909</identifier><identifier>PMID: 34679606</identifier><language>eng</language><publisher>BASEL: Mdpi</publisher><subject>algorithm ; Algorithms ; Cardiac arrhythmia ; Cardiovascular disease ; Datasets ; Disability ; functional outcome ; General & Internal Medicine ; Hospitals ; ischemic stroke ; Life Sciences & Biomedicine ; Machine learning ; Medicine, General & Internal ; Patients ; prediction ; Science & Technology ; Stroke ; Variables ; Vein & artery diseases</subject><ispartof>Diagnostics (Basel), 2021-10, Vol.11 (10), p.1909, Article 1909</ispartof><rights>2021 by the authors. 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/). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.</rights><rights>2021 by the authors. 2021</rights><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>true</woscitedreferencessubscribed><woscitedreferencescount>14</woscitedreferencescount><woscitedreferencesoriginalsourcerecordid>wos000714089200001</woscitedreferencesoriginalsourcerecordid><citedby>FETCH-LOGICAL-c476t-f6b41ee8dc40bd49f86c39be84794adaab1dd1174a863c41366ec272f3b701ac3</citedby><cites>FETCH-LOGICAL-c476t-f6b41ee8dc40bd49f86c39be84794adaab1dd1174a863c41366ec272f3b701ac3</cites><orcidid>0000-0002-2232-065X ; 0000-0002-1288-470X</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktopdf>$$Uhttps://www.ncbi.nlm.nih.gov/pmc/articles/PMC8534707/pdf/$$EPDF$$P50$$Gpubmedcentral$$Hfree_for_read</linktopdf><linktohtml>$$Uhttps://www.ncbi.nlm.nih.gov/pmc/articles/PMC8534707/$$EHTML$$P50$$Gpubmedcentral$$Hfree_for_read</linktohtml><link.rule.ids>230,315,728,781,785,865,886,2103,2115,27929,27930,39263,53796,53798</link.rule.ids></links><search><creatorcontrib>Park, Dougho</creatorcontrib><creatorcontrib>Jeong, Eunhwan</creatorcontrib><creatorcontrib>Kim, Haejong</creatorcontrib><creatorcontrib>Pyun, Hae Wook</creatorcontrib><creatorcontrib>Kim, Haemin</creatorcontrib><creatorcontrib>Choi, Yeon-Ju</creatorcontrib><creatorcontrib>Kim, Youngsoo</creatorcontrib><creatorcontrib>Jin, Suntak</creatorcontrib><creatorcontrib>Hong, Daeyoung</creatorcontrib><creatorcontrib>Lee, Dong Woo</creatorcontrib><creatorcontrib>Lee, Su Yun</creatorcontrib><creatorcontrib>Kim, Mun-Chul</creatorcontrib><title>Machine Learning-Based Three-Month Outcome Prediction in Acute Ischemic Stroke: A Single Cerebrovascular-Specialty Hospital Study in South Korea</title><title>Diagnostics (Basel)</title><addtitle>DIAGNOSTICS</addtitle><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.</description><subject>algorithm</subject><subject>Algorithms</subject><subject>Cardiac arrhythmia</subject><subject>Cardiovascular disease</subject><subject>Datasets</subject><subject>Disability</subject><subject>functional outcome</subject><subject>General & Internal Medicine</subject><subject>Hospitals</subject><subject>ischemic stroke</subject><subject>Life Sciences & Biomedicine</subject><subject>Machine learning</subject><subject>Medicine, General & Internal</subject><subject>Patients</subject><subject>prediction</subject><subject>Science & Technology</subject><subject>Stroke</subject><subject>Variables</subject><subject>Vein & artery diseases</subject><issn>2075-4418</issn><issn>2075-4418</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2021</creationdate><recordtype>article</recordtype><sourceid>HGBXW</sourceid><sourceid>8G5</sourceid><sourceid>ABUWG</sourceid><sourceid>AFKRA</sourceid><sourceid>AZQEC</sourceid><sourceid>BENPR</sourceid><sourceid>CCPQU</sourceid><sourceid>DWQXO</sourceid><sourceid>GNUQQ</sourceid><sourceid>GUQSH</sourceid><sourceid>M2O</sourceid><sourceid>DOA</sourceid><recordid>eNqNks1uEzEUhUcIRKvSJ2BjiQ0SGrDHnrGHBVKIgEakKlLKeuSfO4nDxE5tT1HegkfG01QVRSzwxpZ9znft61MULwl-S2mL3xkr187HZHUkhGDS4vZJcVphXpeMEfH0j_VJcR7jFufREiqq-nlxQlnD2wY3p8WvS6k31gFaggzOunX5UUYw6HoTAMpL79IGXY1J-x2gbwGM1cl6h6xDMz0mQIuoN7CzGq1S8D_gPZqhVaYMgOYQQAV_K6MeBxnK1R60lUM6oAsf9zbJIXtGc5hYKz_mOl99APmieNbLIcL5_XxWfP_86Xp-US6vvizms2WpGW9S2TeKEQBhNMPKsLYXjaatAsF4y6SRUhFjCOFMioZqRmjTgK541VPFMZGanhWLI9d4ue32we5kOHRe2u5uw4d1J0Nu7wAd1kZpJbBQWDJZc6Go4axSSlLd4xpn1ocjaz-qHRgNLgU5PII-PnF20639bSdqyjjmGfD6HhD8zQgxdTsbNQyDdODH2FX19C6KKc3SV39Jt34MLrfqTkUbyugEpEeVDj7GAP3DZQjupgB1_whQdr05un6C8n3UFpyGB2cOECcMi7aaskSyWvy_ep4_fErO3I8u0d-7_93P</recordid><startdate>20211015</startdate><enddate>20211015</enddate><creator>Park, Dougho</creator><creator>Jeong, Eunhwan</creator><creator>Kim, Haejong</creator><creator>Pyun, Hae Wook</creator><creator>Kim, Haemin</creator><creator>Choi, Yeon-Ju</creator><creator>Kim, Youngsoo</creator><creator>Jin, Suntak</creator><creator>Hong, Daeyoung</creator><creator>Lee, Dong Woo</creator><creator>Lee, Su Yun</creator><creator>Kim, Mun-Chul</creator><general>Mdpi</general><general>MDPI AG</general><general>MDPI</general><scope>BLEPL</scope><scope>DTL</scope><scope>HGBXW</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>3V.</scope><scope>7XB</scope><scope>8FK</scope><scope>8G5</scope><scope>ABUWG</scope><scope>AFKRA</scope><scope>AZQEC</scope><scope>BENPR</scope><scope>CCPQU</scope><scope>DWQXO</scope><scope>GNUQQ</scope><scope>GUQSH</scope><scope>M2O</scope><scope>MBDVC</scope><scope>PIMPY</scope><scope>PQEST</scope><scope>PQQKQ</scope><scope>PQUKI</scope><scope>PRINS</scope><scope>Q9U</scope><scope>7X8</scope><scope>5PM</scope><scope>DOA</scope><orcidid>https://orcid.org/0000-0002-2232-065X</orcidid><orcidid>https://orcid.org/0000-0002-1288-470X</orcidid></search><sort><creationdate>20211015</creationdate><title>Machine Learning-Based Three-Month Outcome Prediction in Acute Ischemic Stroke: A Single Cerebrovascular-Specialty Hospital Study in South Korea</title><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></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c476t-f6b41ee8dc40bd49f86c39be84794adaab1dd1174a863c41366ec272f3b701ac3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2021</creationdate><topic>algorithm</topic><topic>Algorithms</topic><topic>Cardiac arrhythmia</topic><topic>Cardiovascular disease</topic><topic>Datasets</topic><topic>Disability</topic><topic>functional outcome</topic><topic>General & Internal Medicine</topic><topic>Hospitals</topic><topic>ischemic stroke</topic><topic>Life Sciences & Biomedicine</topic><topic>Machine learning</topic><topic>Medicine, General & Internal</topic><topic>Patients</topic><topic>prediction</topic><topic>Science & Technology</topic><topic>Stroke</topic><topic>Variables</topic><topic>Vein & artery diseases</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Park, Dougho</creatorcontrib><creatorcontrib>Jeong, Eunhwan</creatorcontrib><creatorcontrib>Kim, Haejong</creatorcontrib><creatorcontrib>Pyun, Hae Wook</creatorcontrib><creatorcontrib>Kim, Haemin</creatorcontrib><creatorcontrib>Choi, Yeon-Ju</creatorcontrib><creatorcontrib>Kim, Youngsoo</creatorcontrib><creatorcontrib>Jin, Suntak</creatorcontrib><creatorcontrib>Hong, Daeyoung</creatorcontrib><creatorcontrib>Lee, Dong Woo</creatorcontrib><creatorcontrib>Lee, Su Yun</creatorcontrib><creatorcontrib>Kim, Mun-Chul</creatorcontrib><collection>Web of Science Core Collection</collection><collection>Science Citation Index Expanded</collection><collection>Web of Science - Science Citation Index Expanded - 2021</collection><collection>CrossRef</collection><collection>ProQuest Central (Corporate)</collection><collection>ProQuest Central (purchase pre-March 2016)</collection><collection>ProQuest Central (Alumni) (purchase pre-March 2016)</collection><collection>Research Library (Alumni Edition)</collection><collection>ProQuest Central (Alumni Edition)</collection><collection>ProQuest Central UK/Ireland</collection><collection>ProQuest Central Essentials</collection><collection>ProQuest Central</collection><collection>ProQuest One Community College</collection><collection>ProQuest Central Korea</collection><collection>ProQuest Central Student</collection><collection>Research Library Prep</collection><collection>Research Library</collection><collection>Research Library (Corporate)</collection><collection>Access via ProQuest (Open Access)</collection><collection>ProQuest One Academic Eastern Edition (DO NOT USE)</collection><collection>ProQuest One Academic</collection><collection>ProQuest One Academic UKI Edition</collection><collection>ProQuest Central China</collection><collection>ProQuest Central Basic</collection><collection>MEDLINE - Academic</collection><collection>PubMed Central (Full Participant titles)</collection><collection>DOAJ Directory of Open Access Journals</collection><jtitle>Diagnostics (Basel)</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Park, Dougho</au><au>Jeong, Eunhwan</au><au>Kim, Haejong</au><au>Pyun, Hae Wook</au><au>Kim, Haemin</au><au>Choi, Yeon-Ju</au><au>Kim, Youngsoo</au><au>Jin, Suntak</au><au>Hong, Daeyoung</au><au>Lee, Dong Woo</au><au>Lee, Su Yun</au><au>Kim, Mun-Chul</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Machine Learning-Based Three-Month Outcome Prediction in Acute Ischemic Stroke: A Single Cerebrovascular-Specialty Hospital Study in South Korea</atitle><jtitle>Diagnostics (Basel)</jtitle><stitle>DIAGNOSTICS</stitle><date>2021-10-15</date><risdate>2021</risdate><volume>11</volume><issue>10</issue><spage>1909</spage><pages>1909-</pages><artnum>1909</artnum><issn>2075-4418</issn><eissn>2075-4418</eissn><abstract>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.</abstract><cop>BASEL</cop><pub>Mdpi</pub><pmid>34679606</pmid><doi>10.3390/diagnostics11101909</doi><tpages>12</tpages><orcidid>https://orcid.org/0000-0002-2232-065X</orcidid><orcidid>https://orcid.org/0000-0002-1288-470X</orcidid><oa>free_for_read</oa></addata></record> |
fulltext | fulltext |
identifier | ISSN: 2075-4418 |
ispartof | Diagnostics (Basel), 2021-10, Vol.11 (10), p.1909, Article 1909 |
issn | 2075-4418 2075-4418 |
language | eng |
recordid | cdi_pubmedcentral_primary_oai_pubmedcentral_nih_gov_8534707 |
source | DOAJ Directory of Open Access Journals; PubMed Central Open Access; MDPI - Multidisciplinary Digital Publishing Institute; Web of Science - Science Citation Index Expanded - 2021<img src="https://exlibris-pub.s3.amazonaws.com/fromwos-v2.jpg" />; EZB-FREE-00999 freely available EZB journals; PubMed Central |
subjects | algorithm Algorithms Cardiac arrhythmia Cardiovascular disease Datasets Disability functional outcome General & Internal Medicine Hospitals ischemic stroke Life Sciences & Biomedicine Machine learning Medicine, General & Internal Patients prediction Science & Technology Stroke Variables Vein & artery diseases |
title | Machine Learning-Based Three-Month Outcome Prediction in Acute Ischemic Stroke: A Single Cerebrovascular-Specialty Hospital Study in South Korea |
url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-15T00%3A49%3A06IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_pubme&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Machine%20Learning-Based%20Three-Month%20Outcome%20Prediction%20in%20Acute%20Ischemic%20Stroke:%20A%20Single%20Cerebrovascular-Specialty%20Hospital%20Study%20in%20South%20Korea&rft.jtitle=Diagnostics%20(Basel)&rft.au=Park,%20Dougho&rft.date=2021-10-15&rft.volume=11&rft.issue=10&rft.spage=1909&rft.pages=1909-&rft.artnum=1909&rft.issn=2075-4418&rft.eissn=2075-4418&rft_id=info:doi/10.3390/diagnostics11101909&rft_dat=%3Cproquest_pubme%3E2584363437%3C/proquest_pubme%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2584363437&rft_id=info:pmid/34679606&rft_doaj_id=oai_doaj_org_article_0cdbcb808b0a4a578b3d742bba3cf050&rfr_iscdi=true |