Dataset Information

Prediction of Neurological Outcomes in Out-of-hospital Cardiac Arrest Survivors Immediately after Return of Spontaneous Circulation: Ensemble Technique with Four Machine Learning Models.

ABSTRACT:

Background

We performed this study to establish a prediction model for 1-year neurological outcomes in out-of-hospital cardiac arrest (OHCA) patients who achieved return of spontaneous circulation (ROSC) immediately after ROSC using machine learning methods.

Methods

We performed a retrospective analysis of an OHCA survivor registry. Patients aged ≥ 18 years were included. Study participants who had registered between March 31, 2013 and December 31, 2018 were divided into a develop dataset (80% of total) and an internal validation dataset (20% of total), and those who had registered between January 1, 2019 and December 31, 2019 were assigned to an external validation dataset. Four machine learning methods, including random forest, support vector machine, ElasticNet and extreme gradient boost, were implemented to establish prediction models with the develop dataset, and the ensemble technique was used to build the final prediction model. The prediction performance of the model in the internal validation and the external validation dataset was described with accuracy, area under the receiver-operating characteristic curve, area under the precision-recall curve, sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV). Futhermore, we established multivariable logistic regression models with the develop set and compared prediction performance with the ensemble models. The primary outcome was an unfavorable 1-year neurological outcome.

Results

A total of 1,207 patients were included in the study. Among them, 631, 139, and 153 were assigned to the develop, the internal validation and the external validation datasets, respectively. Prediction performance metrics for the ensemble prediction model in the internal validation dataset were as follows: accuracy, 0.9620 (95% confidence interval [CI], 0.9352-0.9889); area under receiver-operator characteristics curve, 0.9800 (95% CI, 0.9612-0.9988); area under precision-recall curve, 0.9950 (95% CI, 0.9860-1.0000); sensitivity, 0.9594 (95% CI, 0.9245-0.9943); specificity, 0.9714 (95% CI, 0.9162-1.0000); PPV, 0.9916 (95% CI, 0.9752-1.0000); NPV, 0.8718 (95% CI, 0.7669-0.9767). Prediction performance metrics for the model in the external validation dataset were as follows: accuracy, 0.8509 (95% CI, 0.7825-0.9192); area under receiver-operator characteristics curve, 0.9301 (95% CI, 0.8845-0.9756); area under precision-recall curve, 0.9476 (95% CI, 0.9087-0.9867); sensitivity, 0.9595 (95% CI, 0.9145-1.0000); specificity, 0.6500 (95% CI, 0.5022-0.7978); PPV, 0.8353 (95% CI, 0.7564-0.9142); NPV, 0.8966 (95% CI, 0.7857-1.0000). All the prediction metrics were higher in the ensemble models, except NPVs in both the internal and the external validation datasets.

Conclusion

We established an ensemble prediction model for prediction of unfavorable 1-year neurological outcomes in OHCA survivors using four machine learning methods. The prediction performance of the ensemble model was higher than the multivariable logistic regression model, while its performance was slightly decreased in the external validation dataset.

SUBMITTER: Heo JH

PROVIDER: S-EPMC8289719 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:BACKGROUND:Despite advances in resuscitation care, mortality rates following cardiac arrest (CA) remain high. Between one-quarter (in-hospital CA) and two-thirds (out of hospital CA) of patients admitted comatose to intensive care die of neurological injury. Neuroprognostication determines an informed and timely withdrawal of life sustaining treatment (WLST), sparing the patient unnecessary suffering, alleviating family distress and allowing a more utilitarian use of resources. The latest Resuscitation Council UK (2015) guidance on post-resuscitation care provides the current multi-modal neuroprognostication strategy to predict neurological outcome. Its modalities include neurological examination, neurophysiological tests, biomarkers and radiology. Despite each of the current strategy's predictive modalities exhibiting limitations, meta-analyses show that three, namely PLR (pupillary light reflex), CR (corneal reflex) and N20 SSEP (somatosensory-evoked potential), accurately predict poor neurological outcome with low false positive rates. However, the quality of evidence is low, reducing confidence in the strategy's results. While infrared pupillometry (IRP) is not currently used as a prognostication modality, it can provide a quantitative and objective measure of pupillary size and PLR, giving a definitive view of the second and third cranial nerve activity, a predictor of neurological outcome. METHODS:The proposed study will test the hypothesis, "in those patients who remain comatose following return of spontaneous circulation (ROSC) after CA, IRP can be used early to help predict poor neurological outcome". A comprehensive review of the evidence using a PRISMA-P (2015) compliant methodology will be underpinned by systematic searching of electronic databases and the two authors selecting and screening eligible studies using the Cochrane data extraction and assessment template. Randomised controlled trials and retrospective and prospective studies will be included, and the quality and strength of evidence will be assessed using the Grading of Recommendation, Assessment and Evaluation (GRADE) approach. DISCUSSION:IRP requires rudimentary skill and is objective and repeatable. As a clinical prognostication modality, it may be utilised early, when the strategy's other modalities are not recommended. Corroboration in the evidence would promote early use of IRP and a reduction in ICU bed days. SYSTEMATIC REVIEW REGISTRATION:PROSPERO CRD42018118180.