Understanding Etiologies of Cardiac Arrest: Seeking Definitional Clarity

Construction and validation of prognostic model for ICU mortality in cardiac arrest patients: an interpretable machine learning modeling approach

BACKGROUND

The incidence and mortality of cardiac arrest (CA) is high. We developed interpretable machine learning models for early prediction of ICU mortality risk in patients diagnosed with CA.

METHODS

Data from the Medical Information Mart for Intensive Care (MIMIC-IV, version 2.2) was randomized to training set (0.7) and internal validation set (0.3), and data from eICU(version 2.0.1) was used as external validation set. Five models including Logistic Regression (LR), Random Forest (RF), K Nearest Neighbor (KNN), Decision Tree (DT), and Extreme Gradient Boost (XGBoost) were developed. The model with the largest area under the Receiver Operating Characteristic (ROC) curve (AUC) and good performance in other features was defined as the best model, and Shapley Additive Explanations (SHAP) was used to improve the interpretability of the optimal model.

RESULTS

A total of 1088 patients from MIMIC-IV, and 3542 patients from eICU were included. Seven variables were selected to construct models by Least Absolute Shrinkage and Selection Operator (LASSO) regression. The RF model was the best predictive model with AUC and 95% CI at 0.83 (0.78-0.88) in internal validation set, and 0.71(0.68-0.74) in external validation set. SHAP analysis found that the variables that had a high impact on the risk of ICU death were minimal Glasgow Coma Scale (GCS), base excess, anion gap, and urine output.

CONCLUSION

RF is the optimal model for predicting the risk of ICU death in CA patients. The development of this model is important for early identification and intervention of CA patients who are at risk of dying in the ICU.

Factors Associated With Withdrawal of Life-Sustaining Therapy After Out-of-Hospital Cardiac Arrest

Background

Out-of-hospital cardiac arrest (OHCA) is a leading cause of global mortality. Most patients get hypoxic brain injury, which often leads to the withdrawal of life-sustaining therapy (WLST) because of concerns of poor neurologic prognosis. This study describes the rates and reasons for WLST and identifies factors associated with early WLST, defined as occurring within 72 hours of admission.

Methods

We conducted a multicentered, retrospective cohort study of adult OHCA patients admitted to 3 large academic hospitals in Toronto from January 2012 to December 2019. Data were extracted from medical records and analyzed using descriptive statistics and cause-specific hazards regression models to identify factors associated with WLST and documented goals of care (GOC) discussions.

Results

Among 264 patients (median age 66 years, 76.5% male), the in-hospital mortality rate was 62.1%. Of the nonsurvivors, 67.1% died following WLST (90% of cases because of concern of poor neurologic prognosis), with 50% of WLST occurring <72 hours from admission. Formal declaration of brain death only occurred 9.8% of the time. Older age significantly increased the risk of early WLST. GOC discussions were documented only 56.4% of the time in the overall cohort and significantly associated with WLST across all time periods.

Conclusions

This study highlights the high incidence of WLST, and specifically early WLST, in OHCA patients. GOC discussions are routinely undocumented and is associated with a higher likelihood of WLST. These findings underscore heterogeneity of practice, and the influence of GOC discussions in education and shared decision making.

Machine learning derivation of two cardiac arrest subphenotypes with distinct responses to treatment

INTRODUCTION

Cardiac arrest (CA), characterized by its heterogeneity, poses challenges in patient management. This study aimed to identify clinical subphenotypes in CA patients to aid in patient classification, prognosis assessment, and treatment decision-making.

METHODS

For this study, comprehensive data were extracted from the Medical Information Mart for Intensive Care IV (MIMIC-IV) 2.0 database. We excluded patients under 18 years old, those not initially admitted to the intensive care unit (ICU), or treated in the ICU for less than 72 h. A total of 57 clinical parameters relevant to CA patients were selected for analysis. These included demographic data, vital signs, and laboratory parameters. After an extensive literature review and expert consultations, key factors such as temperature (T), sodium (Na), creatinine (CR), glucose (GLU), heart rate (HR), PaO2/FiO2 ratio (P/F), hemoglobin (HB), mean arterial pressure (MAP), platelets (PLT), and white blood cell count (WBC) were identified as the most significant for cluster analysis. Consensus cluster analysis was utilized to examine the mean values of these routine clinical parameters within the first 24 h post-ICU admission to categorize patient classes. Furthermore, in-hospital and 28-day mortality rates of patients across different CA subphenotypes were assessed using multivariate logistic and Cox regression analysis.

RESULTS

After applying exclusion criteria, 719 CA patients were included in the study, with a median age of 67.22 years (IQR: 55.50-79.34), of whom 63.28% were male. The analysis delineated two distinct subphenotypes: Subphenotype 1 (SP1) and Subphenotype 2 (SP2). Compared to SP1, patients in SP2 exhibited significantly higher levels of P/F, HB, MAP, PLT, and Na, but lower levels of T, HR, GLU, WBC, and CR. SP2 patients had a notably higher in-hospital mortality rate compared to SP1 (53.01% for SP2 vs. 39.36% for SP1, P < 0.001). 28-day mortality decreased continuously for both subphenotypes, with a more rapid decline in SP2. These differences remained significant after adjusting for potential covariates (adjusted OR = 1.82, 95% CI: 1.26-2.64, P = 0.002; HR = 1.84, 95% CI: 1.40-2.41, P < 0.001).

CONCLUSIONS

The study successfully identified two distinct clinical subphenotypes of CA by analyzing routine clinical data from the first 24 h following ICU admission. SP1 was characterized by a lower rate of in-hospital and 28-day mortality when compared to SP2. This differentiation could play a crucial role in tailoring patient care, assessing prognosis, and guiding more targeted treatment strategies for CA patients.

Aetiology and predictors of outcome in non-shockable in-hospital cardiac arrest: A retrospective cohort study from the Swedish Registry for Cardiopulmonary Resuscitation

BACKGROUND

Non-shockable in-hospital cardiac arrest (IHCA) is a condition with diverse aetiology, predictive factors, and outcome. This study aimed to compare IHCA with initial asystole or pulseless electrical activity (PEA), focusing specifically on their aetiologies and the significance of predictive factors.

METHODS

Using the Swedish Registry of Cardiopulmonary Resuscitation, adult non-shockable IHCA cases from 2018 to 2022 (n = 5788) were analysed. Exposure was initial rhythm, while survival to hospital discharge was the primary outcome. A random forest model with 28 variables was used to generate permutation-based variable importance for outcome prediction.

RESULTS

Overall, 60% of patients (n = 3486) were male and the median age was 75 years (IQR 67-81). The most frequent arrest location (46%) was on general wards. Comorbidities were present in 79% of cases and the most prevalent comorbidity was heart failure (33%). Initial rhythm was PEA in 47% (n = 2702) of patients, and asystole in 53% (n = 3086). The most frequent aetiologies in both PEA and asystole were cardiac ischemia (24% vs. 19%, absolute difference [AD]: 5.4%; 95% confidence interval [CI] 3.0% to 7.7%), and respiratory failure (14% vs. 13%, no significant difference). Survival was higher in asystole (24%) than in PEA (17%) (AD: 7.3%; 95% CI 5.2% to 9.4%). Cardiopulmonary resuscitation (CPR) durations were longer in PEA, 18 vs 15 min (AD 4.9 min, 95% CI 4.0-5.9 min). The duration of CPR was the single most important predictor of survival across all subgroup and sensitivity analyses. Aetiology ranked as the second most important predictor in most analyses, except in the asystole subgroup where responsiveness at cardiac arrest team arrival took precedence.

CONCLUSIONS

In this nationwide registry study of non-shockable IHCA comparing asystole to PEA, cardiac ischemia and respiratory failure were the predominant aetiologies. Duration of CPR was the most important predictor of survival, followed by aetiology. Asystole was associated with higher survival compared to PEA, possibly due to shorter CPR durations and a larger proportion of reversible aetiologies.

Out of hospital cardiac arrest - new insights and a call for a worldwide registry and guidelines

INTRODUCTION

Out of hospital cardiac arrest (OHCA) is a major public health problem with substantial mortality rates worldwide. Genetic diseases and primary electrical disorders are the most common etiologies at younger ages, while ischemic heart disease and cardiomyopathies are common causes at older ages. Despite improvement in prevention and treatment in recent years, OHCA is still a major cause of cardiovascular death.

METHOD

We report prospective data regarding etiology, characteristics, clinical course, and outcomes of patients with OHCA who were admitted to a tertiary care center intensive cardiac care unit (ICCU) between 2020-2023.

RESULTS

A total of 92 patients admitted after OHCA were included in the cohort. Mean age was 63.8 ± 13.8 years and 75 (82%) were males. The most common etiology of OHCA was acute coronary syndrome (ACS) in 54 (59%) patients, of whom 46 (85%) patients had ST elevation myocardial infarction and 8 (15%) had non-ST elevation myocardial infarction. During hospitalization, 42 (46%) patients underwent targeted temperature management and 13 (14%) received mechanical circulatory support. Interestingly, 77 (84%) patients underwent coronary angiography, while only 51 (55%) received percutaneous coronary intervention (PCI). Neurologic status was favorable in 49 (53%) patients with Cerebral Performance Category score of 1-2. Overall, mortality rates were relatively low, with 15 (16%) in-hospital deaths and 24 (26%) deaths at 30-day follow-up.

CONCLUSION

Although ACS was the most common etiology for OHCA, only 55% of patients underwent PCI. Most OHCA patients admitted to the ICCU survived hospitalization and were discharged. Increased awareness, public education, worldwide registries, and specific evidence-based guidelines for the treatment of OHCA patients may lead to improved outcomes for these patients who often carry poor prognoses.

Differences among young unwitnessed sudden cardiac death, according to time from last seen alive: Insights from a 15-year nationwide study

BACKGROUND

More than half of all sudden cardiac deaths (SCDs) are unwitnessed, but the composition of the unwitnessed SCD population is poorly described.

OBJECTIVE

The purpose of this study was to compare clinical and autopsy characteristics of young unwitnessed SCD subjects, based on the time from last contact to being found dead.

METHODS

All unwitnessed SCD subjects aged 1-35 years in Denmark from 2000-2014 identified through a multisource approach were included. Time from last seen alive to being found dead was dichotomized to <1 hour or 1-24 hours. Clinical characteristics and autopsy results were compared, and predictors of autopsy were assessed by logistic regression.

RESULTS

Of 440 unwitnessed SCD subjects, 366 (83%) had not been seen alive within 1 hour of being found dead. Comorbidities differed between the groups, with more epilepsy (17% vs 5%) and psychiatric diseases (13% vs 7%) in the 24-hour group. Patients in the 24-hour group died more frequently during sleep (64% vs 23%), the autopsy rate was higher (75% vs 61%), and deaths were more often unexplained after autopsy (69% vs 53%). Having been seen within 1 hour of death independently decreased the chance of being autopsied (odds ratio 0.51; 95% confidence interval 0.27-1.00; P = .0497).

CONCLUSION

The majority of unwitnessed SCD subjects had not been seen alive within 1 hour of being found dead. Clinical- and autopsy-related characteristics differed between the 2 groups. Differences were mainly attributable to death-related circumstances and comorbidities. Excluding SCD cases not seen alive within 1 hour of being found dead would severely underestimate the burden of SCD.