Use of Time-to-Event Analysis to Develop On-Scene Return of Spontaneous Circulation Prediction for Out-of-Hospital Cardiac Arrest Patients

Individualized decision making in on-scene resuscitation time for out-of-hospital cardiac arrest using reinforcement learning

On-scene resuscitation time is associated with out-of-hospital cardiac arrest (OHCA) outcomes. We developed and validated reinforcement learning models for individualized on-scene resuscitation times, leveraging nationwide Korean data. Adult OHCA patients with a medical cause of arrest were included (N = 73,905). The optimal policy was derived from conservative Q-learning to maximize survival. The on-scene return of spontaneous circulation hazard rates estimated from the Random Survival Forest were used as intermediate rewards to handle sparse rewards, while patients' historical survival was reflected in the terminal rewards. The optimal policy increased the survival to hospital discharge rate from 9.6% to 12.5% (95% CI: 12.2-12.8) and the good neurological recovery rate from 5.4% to 7.5% (95% CI: 7.3-7.7). The recommended maximum on-scene resuscitation times for patients demonstrated a bimodal distribution, varying with patient, emergency medical services, and OHCA characteristics. Our survival analysis-based approach generates explainable rewards, reducing subjectivity in reinforcement learning.

Association between out-of-hospital cardiac arrest quality indicator and prehospital management and clinical outcomes for major trauma

INTRODUCTION

It is unclear whether emergency medical service (EMS) agencies with good out-of-hospital cardiac arrest (OHCA) quality indicators also perform well in treating other emergency conditions. We aimed to evaluate the association of an EMS agency's non-traumatic OHCA quality indicators with prehospital management processes and clinical outcomes of major trauma.

METHODS

This retrospective cross-sectional study analyzed data from registers of nationwide, population-based OHCA (adult EMS-treated non-traumatic OHCA patients from 2017 to 2018) and major trauma (adult, EMS-treated, and injury severity score ≥16 trauma patients in 2018) in South Korea. We developed a prehospital ROSC prediction model to categorize EMS agencies into quartiles (Q1-Q4) based on the observed-to-expected (O/E) ROSC ratio for each EMS agency. We evaluated the national EMS protocol compliance of on-scene management according to O/E ROSC ratio quartile. The association between O/E ROSC ratio quartiles and trauma-related early mortality was determined in a multi-level logistic regression model by adjusted odds ratios (OR) and 95 % confidence intervals (95 % CI).

RESULTS

Among 30,034 severe trauma patients, 4,836 were analyzed. Patients in Q4 showed the lowest early mortality rate (5.6 %, 5.5 %, 4.8 %, and 3.4 % in Q1, Q2, Q3, and Q4, respectively). In groups Q1 to Q4, increasing compliance with the national EMS on-scene management protocol (trauma center transport, basic airway management for patients with altered mentality, spinal motion restriction for patients with spinal injury, and intravenous access for patients with hypotension) was observed (p for trend <0.05). Multivariable multi-level logistic regression analysis showed significantly lower early mortality in Q4 than in Q1 (adjusted OR [95 % CI] 0.56 [0.35-0.91]).

CONCLUSION

Major trauma patients managed by EMS agencies with high success rates in achieving prehospital ROSC in non-traumatic OHCA were more likely to receive protocol-based care and exhibited lower early mortality.

Prediction Models for Return of Spontaneous Circulation in Patients with Cardiac Arrest: A Systematic Review and Critical Appraisal

Objectives

Prediction models for the return of spontaneous circulation (ROSC) in patients with cardiac arrest play an important role in helping physicians evaluate the survival probability and providing medical decision-making reference. Although relevant models have been developed, their methodological rigor and model applicability are still unclear. Therefore, this study aims to summarize the evidence for ROSC prediction models and provide a reference for the development, validation, and application of ROSC prediction models.

Methods

PubMed, Cochrane Library, Embase, Elsevier, Web of Science, SpringerLink, Ovid, CNKI, Wanfang, and SinoMed were systematically searched for studies on ROSC prediction models. The search time limit was from the establishment of the database to August 30, 2022. Two reviewers independently screened the literature and extracted the data. The PROBAST was used to evaluate the quality of the included literature.

Results

A total of 8 relevant prediction models were included, and 6 models reported the AUC of 0.662-0.830 in the modeling population, which showed good overall applicability but high risk of bias. The main reasons were improper handling of missing values and variable screening, lack of external validation of the model, and insufficient information of overfitting. Age, gender, etiology, initial heart rhythm, EMS arrival time/BLS intervention time, location, bystander CPR, witnessed during sudden arrest, and ACLS duration/compression duration were the most commonly included predictors. Obvious chest injury, body temperature below 33°C, and possible etiologies were predictive factors for ROSC failure in patients with TOHCA. Age, gender, initial heart rhythm, reason for the hospital visit, length of hospital stay, and the location of occurrence in hospital were the predictors of ROSC in IHCA patients.

Conclusion

The performance of current ROSC prediction models varies greatly and has a high risk of bias, which should be selected with caution. Future studies can further optimize and externally validate the existing models.

Machine learning pre-hospital real-time cardiac arrest outcome prediction (PReCAP) using time-adaptive cohort model based on the Pan-Asian Resuscitation Outcome Study

To save time during transport, where resuscitation quality can degrade in a moving ambulance, it would be prudent to continue the resuscitation on scene if there is a high likelihood of ROSC occurring at the scene. We developed the pre-hospital real-time cardiac arrest outcome prediction (PReCAP) model to predict ROSC at the scene using prehospital input variables with time-adaptive cohort. The patient survival at discharge from the emergency department (ED), the 30-day survival rate, and the final Cerebral Performance Category (CPC) were secondary prediction outcomes in this study. The Pan-Asian Resuscitation Outcome Study (PAROS) database, which includes out-of-hospital cardiac arrest (OHCA) patients transferred by emergency medical service in Asia between 2009 and 2018, was utilized for this study. From the variables available in the PAROS database, we selected relevant variables to predict OHCA outcomes. Light gradient-boosting machine (LightGBM) was used to build the PReCAP model. Between 2009 and 2018, 157,654 patients in the PAROS database were enrolled in our study. In terms of prediction of ROSC on scene, the PReCAP had an AUROC score between 0.85 and 0.87. The PReCAP had an AUROC score between 0.91 and 0.93 for predicting survived to discharge from ED, and an AUROC score between 0.80 and 0.86 for predicting the 30-day survival. The PReCAP predicted CPC with an AUROC score ranging from 0.84 to 0.91. The feature importance differed with time in the PReCAP model prediction of ROSC on scene. Using the PAROS database, PReCAP predicted ROSC on scene, survival to discharge from ED, 30-day survival, and CPC for each minute with an AUROC score ranging from 0.8 to 0.93. As this model used a multi-national database, it might be applicable for a variety of environments and populations.

Artificial intelligence and machine learning in prehospital emergency care: A scoping review

Our scoping review provides a comprehensive analysis of the landscape of artificial intelligence (AI) applications in prehospital emergency care (PEC). It contributes to the field by highlighting the most studied AI applications and identifying the most common methodological approaches across 106 included studies. The findings indicate a promising future for AI in PEC, with many unique use cases, such as prognostication, demand prediction, resource optimization, and the Internet of Things continuous monitoring systems. Comparisons with other approaches showed AI outperforming clinicians and non-AI algorithms in most cases. However, most studies were internally validated and retrospective, highlighting the need for rigorous prospective validation of AI applications before implementation in clinical settings. We identified knowledge and methodological gaps using an evidence map, offering a roadmap for future investigators. We also discussed the significance of explainable AI for establishing trust in AI systems among clinicians and facilitating real-world validation of AI models.

The impact of COVID-19 pandemic on out-of-hospital cardiac arrest system-of-care: Which survival chain factor contributed the most?

OBJECTIVES

In many communities, out-of-hospital cardiac arrest (OHCA) survival outcomes decreased after the coronavirus disease 2019 (COVID-19) pandemic. This study aimed to identify and compare the impacts of each survival chain factor on the change of survival outcomes after COVID-19.

METHODS

Using a Korean out-of-hospital cardiac arrest registry, we analyzed OHCA patients whose arrest was not witnessed by emergency medical service (EMS) providers between 2017 and 2021. Because lack of hospital and survival information in 2021, the 2021 data were used only to identify the expected trend. We developed a prediction model for survival to discharge using patients from 2017 to 2019 (Pre-COVID-19 set) and validated it using patients from 2020 (post-COVID-19 set). Using Utstein elements, a stepwise logistic regression model was constructed, and discrimination and calibration were evaluated by c-statistics and scaled Brier score. Using the distribution change of predictors from one year before the pandemic (2019) to post-COVDI-19, we calculated the magnitude of survival difference according to each predictor's distribution change using the marginal standardization method.

RESULTS

Among 83,273 patients (mean age 67.2 years and 64.3% males), 61,180 and 22,092 patients belonged to pre-COVOD-19 and post-COVID-19 sets. Survival to discharge was 5019 (8.2%) in pre-COVID-19 set and 1457 (6.6%) in post-COVID-19 set. The proportion of bystander cardiopulmonary resuscitation was 59.0% in the pre-COVID-19 set and 61.0% in the post-COVID-19 set. The median (interquartile range) response time was 7 (5-9) minutes in the pre-COVID-19 set and 8 (6-10) minutes in the post-COVID-19 set. The area under the receiver operating characteristic (AUROC) curve (95% confidence interval) was 0.907 (0.902-0.912) in the pre-COVID-19 set, and 0.924 (0.916-0.931) in the post-COVID-19 set, and scaled Brier score were 0.39 in pre-COVID-19 sets, and 0.40 in the post-COVID-19 set. Among various predictors, EMS factors showed the highest impact. Response time and on-scene management of EMS showed the highest impact on decreased survival. A similar trend was also expected in the 2021.

CONCLUSION

The effort to create a rapid response system for OHCA patients could have priority for the recovery of survival outcomes in OHCA patients in the post-COVID-19 period. Further studies to recover survival outcomes of OHCA are warranted.