Prediction of good neurological recovery after out-of-hospital cardiac arrest

A machine learning analysis

Research output: Contribution to journalArticleResearchpeer-review

Abstract

Background: This study aimed to train, validate and compare predictive models that use machine learning analysis for good neurological recovery in OHCA patients. Methods: Adult OHCA patients who had a presumed cardiac etiology and a sustained return of spontaneous circulation between 2013 and 2016 were analyzed; 80% of the individuals were analyzed for training and 20% were analyzed for validation. We developed using six machine learning algorithms: logistic regression (LR), extreme gradient boosting (XGB), support vector machine, random forest, elastic net (EN), and neural network. Variables that could be obtained within 24 hours of the emergency department visit were used. The area under the receiver operation curve (AUROC) was calculated to assess the discrimination. Calibration was assessed by the Hosmer–Lemeshow test. Reclassification was assessed by using the continuous net reclassification index (NRI). Results: A total of 19,860 OHCA patients were included in the analysis. Of the 15,888 patients in the training group, 2228 (14.0%) had a good neurological recovery; of the 3972 patients in the validation group, 577 (14.5%) had a good neurological recovery. The LR, XGB, and EN models showed the highest discrimination powers (AUROC (95% CI)) of 0.949 (0.941–0.957) for all), and all three models were well calibrated (Hosmer–Lemeshow test: p >0.05). The XGB model reclassified patients according to their true risk better than the LR model (NRI: 0.110), but the EN model reclassified patients worse than the LR model (NRI: −1.239). Conclusion: The best performing machine learning algorithm was the XGB and LR algorithm.

Original languageEnglish
Pages (from-to)127-135
Number of pages9
JournalResuscitation
Volume142
DOIs
StatePublished - 1 Sep 2019

Fingerprint

Out-of-Hospital Cardiac Arrest
Logistic Models
Machine Learning
Calibration
Hospital Emergency Service

Keywords

  • Machine learning analysis
  • Out-of-hospital cardiac arrest
  • Outcome

Cite this

@article{17930ae596e54cceb4f65cec8fe76035,
title = "Prediction of good neurological recovery after out-of-hospital cardiac arrest: A machine learning analysis",
abstract = "Background: This study aimed to train, validate and compare predictive models that use machine learning analysis for good neurological recovery in OHCA patients. Methods: Adult OHCA patients who had a presumed cardiac etiology and a sustained return of spontaneous circulation between 2013 and 2016 were analyzed; 80{\%} of the individuals were analyzed for training and 20{\%} were analyzed for validation. We developed using six machine learning algorithms: logistic regression (LR), extreme gradient boosting (XGB), support vector machine, random forest, elastic net (EN), and neural network. Variables that could be obtained within 24 hours of the emergency department visit were used. The area under the receiver operation curve (AUROC) was calculated to assess the discrimination. Calibration was assessed by the Hosmer–Lemeshow test. Reclassification was assessed by using the continuous net reclassification index (NRI). Results: A total of 19,860 OHCA patients were included in the analysis. Of the 15,888 patients in the training group, 2228 (14.0{\%}) had a good neurological recovery; of the 3972 patients in the validation group, 577 (14.5{\%}) had a good neurological recovery. The LR, XGB, and EN models showed the highest discrimination powers (AUROC (95{\%} CI)) of 0.949 (0.941–0.957) for all), and all three models were well calibrated (Hosmer–Lemeshow test: p >0.05). The XGB model reclassified patients according to their true risk better than the LR model (NRI: 0.110), but the EN model reclassified patients worse than the LR model (NRI: −1.239). Conclusion: The best performing machine learning algorithm was the XGB and LR algorithm.",
keywords = "Machine learning analysis, Out-of-hospital cardiac arrest, Outcome",
author = "Park, {Jeong Ho} and Shin, {Sang Do} and Song, {Kyoung Jun} and Hong, {Ki Jeong} and Ro, {Young Sun} and Jinwook Choi and Choi, {Sae Won}",
year = "2019",
month = "9",
day = "1",
doi = "10.1016/j.resuscitation.2019.07.020",
language = "English",
volume = "142",
pages = "127--135",
journal = "Resuscitation",
issn = "0300-9572",
publisher = "Elsevier Ireland Ltd",

}

Prediction of good neurological recovery after out-of-hospital cardiac arrest : A machine learning analysis. / Park, Jeong Ho; Shin, Sang Do; Song, Kyoung Jun; Hong, Ki Jeong; Ro, Young Sun; Choi, Jinwook; Choi, Sae Won.

In: Resuscitation, Vol. 142, 01.09.2019, p. 127-135.

Research output: Contribution to journalArticleResearchpeer-review

TY - JOUR

T1 - Prediction of good neurological recovery after out-of-hospital cardiac arrest

T2 - A machine learning analysis

AU - Park, Jeong Ho

AU - Shin, Sang Do

AU - Song, Kyoung Jun

AU - Hong, Ki Jeong

AU - Ro, Young Sun

AU - Choi, Jinwook

AU - Choi, Sae Won

PY - 2019/9/1

Y1 - 2019/9/1

N2 - Background: This study aimed to train, validate and compare predictive models that use machine learning analysis for good neurological recovery in OHCA patients. Methods: Adult OHCA patients who had a presumed cardiac etiology and a sustained return of spontaneous circulation between 2013 and 2016 were analyzed; 80% of the individuals were analyzed for training and 20% were analyzed for validation. We developed using six machine learning algorithms: logistic regression (LR), extreme gradient boosting (XGB), support vector machine, random forest, elastic net (EN), and neural network. Variables that could be obtained within 24 hours of the emergency department visit were used. The area under the receiver operation curve (AUROC) was calculated to assess the discrimination. Calibration was assessed by the Hosmer–Lemeshow test. Reclassification was assessed by using the continuous net reclassification index (NRI). Results: A total of 19,860 OHCA patients were included in the analysis. Of the 15,888 patients in the training group, 2228 (14.0%) had a good neurological recovery; of the 3972 patients in the validation group, 577 (14.5%) had a good neurological recovery. The LR, XGB, and EN models showed the highest discrimination powers (AUROC (95% CI)) of 0.949 (0.941–0.957) for all), and all three models were well calibrated (Hosmer–Lemeshow test: p >0.05). The XGB model reclassified patients according to their true risk better than the LR model (NRI: 0.110), but the EN model reclassified patients worse than the LR model (NRI: −1.239). Conclusion: The best performing machine learning algorithm was the XGB and LR algorithm.

AB - Background: This study aimed to train, validate and compare predictive models that use machine learning analysis for good neurological recovery in OHCA patients. Methods: Adult OHCA patients who had a presumed cardiac etiology and a sustained return of spontaneous circulation between 2013 and 2016 were analyzed; 80% of the individuals were analyzed for training and 20% were analyzed for validation. We developed using six machine learning algorithms: logistic regression (LR), extreme gradient boosting (XGB), support vector machine, random forest, elastic net (EN), and neural network. Variables that could be obtained within 24 hours of the emergency department visit were used. The area under the receiver operation curve (AUROC) was calculated to assess the discrimination. Calibration was assessed by the Hosmer–Lemeshow test. Reclassification was assessed by using the continuous net reclassification index (NRI). Results: A total of 19,860 OHCA patients were included in the analysis. Of the 15,888 patients in the training group, 2228 (14.0%) had a good neurological recovery; of the 3972 patients in the validation group, 577 (14.5%) had a good neurological recovery. The LR, XGB, and EN models showed the highest discrimination powers (AUROC (95% CI)) of 0.949 (0.941–0.957) for all), and all three models were well calibrated (Hosmer–Lemeshow test: p >0.05). The XGB model reclassified patients according to their true risk better than the LR model (NRI: 0.110), but the EN model reclassified patients worse than the LR model (NRI: −1.239). Conclusion: The best performing machine learning algorithm was the XGB and LR algorithm.

KW - Machine learning analysis

KW - Out-of-hospital cardiac arrest

KW - Outcome

UR - http://www.scopus.com/inward/record.url?scp=85070205046&partnerID=8YFLogxK

U2 - 10.1016/j.resuscitation.2019.07.020

DO - 10.1016/j.resuscitation.2019.07.020

M3 - Article

VL - 142

SP - 127

EP - 135

JO - Resuscitation

JF - Resuscitation

SN - 0300-9572

ER -