Comparison of Machine Learning Methods for Predicting Outcomes After In-Hospital Cardiac Arrest
Prognostication of neurologic status among survivors of in-hospital cardiac arrests remains a challenging task for physicians. Although models such as the Cardiac Arrest Survival Post-Resuscitation In-hospital score are useful for predicting neurologic outcomes, they were developed using traditional...
Saved in:
| Published in: | Critical care medicine Vol. 50; no. 2; p. e162 |
|---|---|
| Main Authors: | , , , , , |
| Format: | Journal Article |
| Language: | English |
| Published: |
United States
01.02.2022
|
| Subjects: | |
| ISSN: | 1530-0293, 1530-0293 |
| Online Access: | Get more information |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Abstract | Prognostication of neurologic status among survivors of in-hospital cardiac arrests remains a challenging task for physicians. Although models such as the Cardiac Arrest Survival Post-Resuscitation In-hospital score are useful for predicting neurologic outcomes, they were developed using traditional statistical techniques. In this study, we derive and compare the performance of several machine learning models with each other and with the Cardiac Arrest Survival Post-Resuscitation In-hospital score for predicting the likelihood of favorable neurologic outcomes among survivors of resuscitation.
Analysis of the Get With The Guidelines-Resuscitation registry.
Seven-hundred fifty-five hospitals participating in Get With The Guidelines-Resuscitation from January 1, 2001, to January 28, 2017.
Adult in-hospital cardiac arrest survivors.
None.
Of 117,674 patients in our cohort, 28,409 (24%) had a favorable neurologic outcome, as defined as survival with a Cerebral Performance Category score of less than or equal to 2 at discharge. Using patient characteristics, pre-existing conditions, prearrest interventions, and periarrest variables, we constructed logistic regression, support vector machines, random forests, gradient boosted machines, and neural network machine learning models to predict favorable neurologic outcome. Events prior to October 20, 2009, were used for model derivation, and all subsequent events were used for validation. The gradient boosted machine predicted favorable neurologic status at discharge significantly better than the Cardiac Arrest Survival Post-Resuscitation In-hospital score (C-statistic: 0.81 vs 0.73; p < 0.001) and outperformed all other machine learning models in terms of discrimination, calibration, and accuracy measures. Variables that were consistently most important for prediction across all models were duration of arrest, initial cardiac arrest rhythm, admission Cerebral Performance Category score, and age.
The gradient boosted machine algorithm was the most accurate for predicting favorable neurologic outcomes in in-hospital cardiac arrest survivors. Our results highlight the utility of machine learning for predicting neurologic outcomes in resuscitated patients. |
|---|---|
| AbstractList | Prognostication of neurologic status among survivors of in-hospital cardiac arrests remains a challenging task for physicians. Although models such as the Cardiac Arrest Survival Post-Resuscitation In-hospital score are useful for predicting neurologic outcomes, they were developed using traditional statistical techniques. In this study, we derive and compare the performance of several machine learning models with each other and with the Cardiac Arrest Survival Post-Resuscitation In-hospital score for predicting the likelihood of favorable neurologic outcomes among survivors of resuscitation.OBJECTIVESPrognostication of neurologic status among survivors of in-hospital cardiac arrests remains a challenging task for physicians. Although models such as the Cardiac Arrest Survival Post-Resuscitation In-hospital score are useful for predicting neurologic outcomes, they were developed using traditional statistical techniques. In this study, we derive and compare the performance of several machine learning models with each other and with the Cardiac Arrest Survival Post-Resuscitation In-hospital score for predicting the likelihood of favorable neurologic outcomes among survivors of resuscitation.Analysis of the Get With The Guidelines-Resuscitation registry.DESIGNAnalysis of the Get With The Guidelines-Resuscitation registry.Seven-hundred fifty-five hospitals participating in Get With The Guidelines-Resuscitation from January 1, 2001, to January 28, 2017.SETTINGSeven-hundred fifty-five hospitals participating in Get With The Guidelines-Resuscitation from January 1, 2001, to January 28, 2017.Adult in-hospital cardiac arrest survivors.PATIENTSAdult in-hospital cardiac arrest survivors.None.INTERVENTIONSNone.Of 117,674 patients in our cohort, 28,409 (24%) had a favorable neurologic outcome, as defined as survival with a Cerebral Performance Category score of less than or equal to 2 at discharge. Using patient characteristics, pre-existing conditions, prearrest interventions, and periarrest variables, we constructed logistic regression, support vector machines, random forests, gradient boosted machines, and neural network machine learning models to predict favorable neurologic outcome. Events prior to October 20, 2009, were used for model derivation, and all subsequent events were used for validation. The gradient boosted machine predicted favorable neurologic status at discharge significantly better than the Cardiac Arrest Survival Post-Resuscitation In-hospital score (C-statistic: 0.81 vs 0.73; p < 0.001) and outperformed all other machine learning models in terms of discrimination, calibration, and accuracy measures. Variables that were consistently most important for prediction across all models were duration of arrest, initial cardiac arrest rhythm, admission Cerebral Performance Category score, and age.MEASUREMENTS AND MAIN RESULTSOf 117,674 patients in our cohort, 28,409 (24%) had a favorable neurologic outcome, as defined as survival with a Cerebral Performance Category score of less than or equal to 2 at discharge. Using patient characteristics, pre-existing conditions, prearrest interventions, and periarrest variables, we constructed logistic regression, support vector machines, random forests, gradient boosted machines, and neural network machine learning models to predict favorable neurologic outcome. Events prior to October 20, 2009, were used for model derivation, and all subsequent events were used for validation. The gradient boosted machine predicted favorable neurologic status at discharge significantly better than the Cardiac Arrest Survival Post-Resuscitation In-hospital score (C-statistic: 0.81 vs 0.73; p < 0.001) and outperformed all other machine learning models in terms of discrimination, calibration, and accuracy measures. Variables that were consistently most important for prediction across all models were duration of arrest, initial cardiac arrest rhythm, admission Cerebral Performance Category score, and age.The gradient boosted machine algorithm was the most accurate for predicting favorable neurologic outcomes in in-hospital cardiac arrest survivors. Our results highlight the utility of machine learning for predicting neurologic outcomes in resuscitated patients.CONCLUSIONSThe gradient boosted machine algorithm was the most accurate for predicting favorable neurologic outcomes in in-hospital cardiac arrest survivors. Our results highlight the utility of machine learning for predicting neurologic outcomes in resuscitated patients. Prognostication of neurologic status among survivors of in-hospital cardiac arrests remains a challenging task for physicians. Although models such as the Cardiac Arrest Survival Post-Resuscitation In-hospital score are useful for predicting neurologic outcomes, they were developed using traditional statistical techniques. In this study, we derive and compare the performance of several machine learning models with each other and with the Cardiac Arrest Survival Post-Resuscitation In-hospital score for predicting the likelihood of favorable neurologic outcomes among survivors of resuscitation. Analysis of the Get With The Guidelines-Resuscitation registry. Seven-hundred fifty-five hospitals participating in Get With The Guidelines-Resuscitation from January 1, 2001, to January 28, 2017. Adult in-hospital cardiac arrest survivors. None. Of 117,674 patients in our cohort, 28,409 (24%) had a favorable neurologic outcome, as defined as survival with a Cerebral Performance Category score of less than or equal to 2 at discharge. Using patient characteristics, pre-existing conditions, prearrest interventions, and periarrest variables, we constructed logistic regression, support vector machines, random forests, gradient boosted machines, and neural network machine learning models to predict favorable neurologic outcome. Events prior to October 20, 2009, were used for model derivation, and all subsequent events were used for validation. The gradient boosted machine predicted favorable neurologic status at discharge significantly better than the Cardiac Arrest Survival Post-Resuscitation In-hospital score (C-statistic: 0.81 vs 0.73; p < 0.001) and outperformed all other machine learning models in terms of discrimination, calibration, and accuracy measures. Variables that were consistently most important for prediction across all models were duration of arrest, initial cardiac arrest rhythm, admission Cerebral Performance Category score, and age. The gradient boosted machine algorithm was the most accurate for predicting favorable neurologic outcomes in in-hospital cardiac arrest survivors. Our results highlight the utility of machine learning for predicting neurologic outcomes in resuscitated patients. |
| Author | Edelson, Dana Mayampurath, Anoop Churpek, Matthew Hagopian, Raffi Venable, Laura Carey, Kyle |
| Author_xml | – sequence: 1 givenname: Anoop surname: Mayampurath fullname: Mayampurath, Anoop organization: Department of Pediatrics, University of Chicago, Chicago, IL – sequence: 2 givenname: Raffi surname: Hagopian fullname: Hagopian, Raffi organization: Department of Medicine, University of Chicago, Chicago, IL – sequence: 3 givenname: Laura surname: Venable fullname: Venable, Laura organization: Department of Medicine, University of Chicago, Chicago, IL – sequence: 4 givenname: Kyle surname: Carey fullname: Carey, Kyle organization: Department of Medicine, University of Chicago, Chicago, IL – sequence: 5 givenname: Dana surname: Edelson fullname: Edelson, Dana organization: Department of Medicine, University of Chicago, Chicago, IL – sequence: 6 givenname: Matthew surname: Churpek fullname: Churpek, Matthew organization: Department of Medicine, University of Wisconsin, Madison, WI |
| BackLink | https://www.ncbi.nlm.nih.gov/pubmed/34406171$$D View this record in MEDLINE/PubMed |
| BookMark | eNpNkMtOwzAURC0Eog_4A4S8ZJPiRxw7yyoCWqlVWcA6cpxrapTYwU4X_D1FFKmzmavR0VxpZujSBw8I3VGyoKSUj1W1XZAzCaaKCzSlgpOMsJJfnt0TNEvpkxCaC8mv0YTnOSmopFNUV6EfdHQpeBws3mqzdx7wBnT0zn_gLYz70CZsQ8SvEVpnxt94dxhN6CHhpR0h4rXPViENbtQdrnRsnTZ4GSOk8QZdWd0luD35HL0_P71Vq2yze1lXy01mcsFppgzRxlKwtFWqka0sFddS0xK0BiZymxtVcGlEYVrNGysYb46IMkwKQ4CwOXr46x1i-DocH9e9Swa6TnsIh1QzUTBBJSnVEb0_oYemh7Yeout1_K7_R2E_q0VmYA |
| CitedBy_id | crossref_primary_10_1097_CCE_0000000000001116 crossref_primary_10_1016_j_resplu_2024_100829 crossref_primary_10_3390_jcm14124026 crossref_primary_10_1186_s12938_023_01178_9 crossref_primary_10_1097_MCC_0000000000001138 crossref_primary_10_1016_j_resuscitation_2023_109704 crossref_primary_10_1097_MEJ_0000000000001031 crossref_primary_10_1097_MS9_0000000000002673 crossref_primary_10_1371_journal_pone_0278988 crossref_primary_10_1016_j_ijmedinf_2024_105659 |
| ContentType | Journal Article |
| Copyright | Copyright © 2021 by the Society of Critical Care Medicine and Wolters Kluwer Health, Inc. All Rights Reserved. |
| Copyright_xml | – notice: Copyright © 2021 by the Society of Critical Care Medicine and Wolters Kluwer Health, Inc. All Rights Reserved. |
| CorporateAuthor | American Heart Association's Get With the Guidelines-Resuscitation Investigators |
| CorporateAuthor_xml | – name: American Heart Association's Get With the Guidelines-Resuscitation Investigators |
| DBID | CGR CUY CVF ECM EIF NPM 7X8 |
| DOI | 10.1097/CCM.0000000000005286 |
| DatabaseName | Medline MEDLINE MEDLINE (Ovid) MEDLINE MEDLINE PubMed MEDLINE - Academic |
| DatabaseTitle | MEDLINE Medline Complete MEDLINE with Full Text PubMed MEDLINE (Ovid) MEDLINE - Academic |
| DatabaseTitleList | MEDLINE - Academic MEDLINE |
| Database_xml | – sequence: 1 dbid: NPM name: PubMed url: http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed sourceTypes: Index Database – sequence: 2 dbid: 7X8 name: MEDLINE - Academic url: https://search.proquest.com/medline sourceTypes: Aggregation Database |
| DeliveryMethod | no_fulltext_linktorsrc |
| Discipline | Medicine |
| EISSN | 1530-0293 |
| ExternalDocumentID | 34406171 |
| Genre | Research Support, U.S. Gov't, Non-P.H.S Research Support, Non-U.S. Gov't Journal Article Research Support, N.I.H., Extramural |
| GrantInformation_xml | – fundername: NIGMS NIH HHS grantid: R01 GM123193 – fundername: NHLBI NIH HHS grantid: K01 HL148390 |
| GroupedDBID | --- .-D .XZ .Z2 01R 0R~ 1J1 354 40H 4Q1 4Q2 4Q3 53G 5GY 5RE 5VS 6J9 6PF 71W 77Y 7O~ AAAAV AAAXR AAGIX AAHPQ AAIQE AAJCS AAMOA AAMTA AAQKA AARTV AASCR AASOK AASXQ AAUEB AAWTL AAXQO AAYEP ABASU ABBUW ABDIG ABJNI ABOCM ABPPZ ABVCZ ABXVJ ABXYN ABZAD ABZZY ACDDN ACDOF ACEWG ACGFO ACGFS ACIJW ACILI ACLDA ACOAL ACWDW ACWRI ACXJB ACXNZ ACZKN ADGGA ADHPY AE3 AE6 AEBDS AENEX AFBFQ AFDTB AFEXH AFMBP AFNMH AFSOK AFUWQ AGINI AHOMT AHQNM AHQVU AHVBC AIJEX AINUH AJCLO AJIOK AJNWD AJZMW AKCTQ AKULP ALKUP ALMA_UNASSIGNED_HOLDINGS ALMTX AMJPA AMKUR AMNEI AOHHW AOQMC BOYCO BQLVK BYPQX C45 CGR CS3 CUY CVF DIWNM DU5 E.X EBS ECM EEVPB EIF ERAAH EX3 F2K F2L F2M F2N F5P FCALG FL- GNXGY GQDEL H0~ HLJTE HZ~ IKREB IKYAY IN~ IPNFZ JF9 JG8 JK3 JK8 K-A K-F K8S KD2 KMI L-C L7B N9A NPM N~7 N~B O9- OAG OAH OB4 OBH ODMTH ODZKP OHH OHYEH OL1 OLB OLG OLH OLU OLV OLY OLZ OPUJH OVD OVDNE OVIDH OVLEI OVOZU OWBYB OWU OWV OWW OWX OWY OWZ OXXIT P2P PONUX RIG RLZ S4R S4S TEORI TSPGW V2I VVN W3M WOQ WOW X3V X3W XXN XYM YCJ YFH YOC YOJ ZFV ZY1 ~9M 7X8 ABPXF ADKSD ADSXY |
| ID | FETCH-LOGICAL-c4531-8c0acf1ef1d88b7d7983a7a19eaae254f4c8637c56cda3bf523b9838c275c0e02 |
| IEDL.DBID | 7X8 |
| ISICitedReferencesCount | 13 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=00003246-202202000-00031&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| ISSN | 1530-0293 |
| IngestDate | Sun Sep 28 01:04:12 EDT 2025 Thu Apr 03 07:09:48 EDT 2025 |
| IsDoiOpenAccess | false |
| IsOpenAccess | true |
| IsPeerReviewed | true |
| IsScholarly | true |
| Issue | 2 |
| Language | English |
| License | Copyright © 2021 by the Society of Critical Care Medicine and Wolters Kluwer Health, Inc. All Rights Reserved. |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-c4531-8c0acf1ef1d88b7d7983a7a19eaae254f4c8637c56cda3bf523b9838c275c0e02 |
| Notes | ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 23 |
| OpenAccessLink | https://www.ncbi.nlm.nih.gov/pmc/articles/8810601 |
| PMID | 34406171 |
| PQID | 2562517098 |
| PQPubID | 23479 |
| ParticipantIDs | proquest_miscellaneous_2562517098 pubmed_primary_34406171 |
| PublicationCentury | 2000 |
| PublicationDate | 2022-02-01 20220201 |
| PublicationDateYYYYMMDD | 2022-02-01 |
| PublicationDate_xml | – month: 02 year: 2022 text: 2022-02-01 day: 01 |
| PublicationDecade | 2020 |
| PublicationPlace | United States |
| PublicationPlace_xml | – name: United States |
| PublicationTitle | Critical care medicine |
| PublicationTitleAlternate | Crit Care Med |
| PublicationYear | 2022 |
| SSID | ssj0014573 |
| Score | 2.4842622 |
| Snippet | Prognostication of neurologic status among survivors of in-hospital cardiac arrests remains a challenging task for physicians. Although models such as the... |
| SourceID | proquest pubmed |
| SourceType | Aggregation Database Index Database |
| StartPage | e162 |
| SubjectTerms | Aged Area Under Curve Cohort Studies Female Forecasting - methods Heart Arrest - complications Heart Arrest - epidemiology Heart Arrest - mortality Humans Machine Learning - standards Machine Learning - statistics & numerical data Male Middle Aged Outcome Assessment, Health Care - methods Outcome Assessment, Health Care - statistics & numerical data Prognosis ROC Curve Survivors - statistics & numerical data |
| Title | Comparison of Machine Learning Methods for Predicting Outcomes After In-Hospital Cardiac Arrest |
| URI | https://www.ncbi.nlm.nih.gov/pubmed/34406171 https://www.proquest.com/docview/2562517098 |
| Volume | 50 |
| WOSCitedRecordID | wos00003246-202202000-00031&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| hasFullText | |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV07T8MwELaAIsTC-1FeMhKrVedpZ0IoooIhpQNI3SLbsRFLUpqW38_ZceiEhESGTLFjne583_nO9yF0B16HphwMyXprEhtdEWlYQqQwVRQngVRJRzbBJhM-m2VTf-DW-rLKfk90G3XVKHtGPgotUg8Yzfj9_JNY1iibXfUUGptoEAGUsVrNZussQpy4DDMYNSUU_Fp_dS5jozwvutaF_kncberfQKZzNuP9_y7zAO15mIkfOr04RBu6PkI7hU-kH6My_-EfxI3BhSup1Nh3W33HhSOWbjFAWjxd2GG2PBq_rJawDN3iB0stjp9r0vOO4NypmoJfWraPE_Q2fnzNn4jnWiAqBjMkXFGhTKBNUHEuWcUyHgkmgkwLoSGINLHiacRUkqpKRNJA_CrhE65CliiqaXiKtuqm1ucIh1nIUikVo4o7LhMIYSpDGYM50yo1Q3Tbi64EXbYJClHrZtWWa-EN0Vkn_3LeNd0oo9hCDxZc_GH0JdoN7S0FV1x9hQYGLFlfo231tfxoFzdOSeA9mRbfFlzEvA |
| linkProvider | ProQuest |
| openUrl | ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Comparison+of+Machine+Learning+Methods+for+Predicting+Outcomes+After+In-Hospital+Cardiac+Arrest&rft.jtitle=Critical+care+medicine&rft.au=Mayampurath%2C+Anoop&rft.au=Hagopian%2C+Raffi&rft.au=Venable%2C+Laura&rft.au=Carey%2C+Kyle&rft.date=2022-02-01&rft.eissn=1530-0293&rft.volume=50&rft.issue=2&rft.spage=e162&rft_id=info:doi/10.1097%2FCCM.0000000000005286&rft_id=info%3Apmid%2F34406171&rft_id=info%3Apmid%2F34406171&rft.externalDocID=34406171 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1530-0293&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1530-0293&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1530-0293&client=summon |