Machine learning for early prediction of in-hospital cardiac arrest in patients with acute coronary syndromes.

BACKGROUND: Previous studies have used machine leaning to predict clinical deterioration to improve outcome prediction. However, no study has used machine learning to predict cardiac arrest in patients with acute coronary syndrome (ACS). Algorithms are required to generate high-performance models for predicting cardiac arrest in ACS patients with multivariate features. HYPOTHESIS: Machine learning algorithms will significantly improve outcome prediction of cardiac arrest in ACS patients. METHODS: This retrospective cohort study reviewed 166 ACS patients who had in-hospital cardiac arrest. Eight machine learning algorithms were trained using multivariate clinical features obtained 24 h prior to the onset of cardiac arrest. All machine learning models were compared to each other and to existing risk prediction scores (Global Registry of Acute Coronary Events, National Early Warning Score, and Modified Early Warning Score) using the area under the receiver operating characteristic curve (AUROC). RESULTS: The XGBoost model provided the best performance with regard to AUC (0.958 [95%CI: 0.938-0.978]), accuracy (88.9%), sensitivity (73%), negative predictive value (89%), and F1 score (80%) compared with other machine learning models. The K-nearest neighbor model generated the best specificity (99.3%) and positive predictive value (93.8%) metrics, but had low and unacceptable values for sensitivity and AUC. Most, but not all, machine learning models outperformed the existing risk prediction scores. CONCLUSIONS: The XGBoost model, which was generated based on a machine learning algorithm, has high potential to be used to predict cardiac arrest in ACS patients. This proposed model significantly improves outcome prediction compared to existing risk prediction scores.

Decision tree model for predicting in-hospital cardiac arrest among patients admitted with acute coronary syndrome.

BACKGROUND: In-hospital cardiac arrest (IHCA) may be preventable, with patients often showing signs of physiological deterioration before an event. Our objective was to develop and validate a simple clinical prediction model to identify the IHCA risk among cardiac arrest (CA) patients hospitalized with acute coronary syndrome (ACS). HYPOTHESIS: A predicting model could help to identify the risk of IHCA among patients admitted with ACS. METHODS: We conducted a case-control study and analyzed 21 337 adult ACS patients, of whom 164 had experienced CA. Vital signs, demographic, and laboratory data were extracted from the electronic health record. Decision tree analysis was applied with 10-fold cross-validation to predict the risk of IHCA. RESULTS: The decision tree analysis detected seven explanatory variables, and the variables' importance is as follows: VitalPAC Early Warning Score (ViEWS), fatal arrhythmia, Killip class, cardiac troponin I, blood urea nitrogen, age, and diabetes. The development decision tree model demonstrated a sensitivity of 0.762, a specificity of 0.882, and an area under the receiver operating characteristic curve (AUC) of 0.844 (95% CI, 0.805 to 0.849). A 10-fold cross-validated risk estimate was 0.198, while the optimism-corrected AUC was 0.823 (95% CI, 0.786 to 0.860). CONCLUSIONS: We have developed and internally validated a good discrimination decision tree model to predict the risk of IHCA. This simple prediction model may provide healthcare workers with a practical bedside tool and could positively impact decision-making with regard to deteriorating patients with ACS.

Characteristics and outcomes of in-hospital cardiac arrest in adults hospitalized with acute coronary syndrome in China.

AIMS: This retrospective study aims to analyze and explore the clinical characteristics, risk factors, and in-hospital outcomes - including return of spontaneous circulation (ROSC) and survival to discharge - of hospitalized patients admitted with acute coronary syndrome (ACS) suffering cardiac arrest. METHODS: ACS patients admitted to three tertiary hospitals in Fujian, China, were evaluated retrospectively from January 1, 2012 to December 30, 2016. Data were collected, based on the Utstein Style, for all cases of attempted resuscitation for IHCA. We analyzed patient characteristics, pre-event variables, event variables, and the main outcomes, including ROSC and survival to discharge, and identified the influencing factors on the outcomes. RESULTS: The total number of ACS admissions across the three hospitals during this study period was 21,337. Among these admissions, 320 ACS patients experienced IHCA (incidence: 1.50%); 134 (41.9%) patients experienced ROSC; and 68 (21.2%) survived to discharge. The findings indicated that four factors were associated with ROSC, including age <70 years-old, shockable rhythm, duration of resuscitation (≤15 min and 16-30 min), and PCI. Five factors were associated with survival to discharge, including age <70 years-old, shockable rhythm, the duration of resuscitation (≤15 min and 16-30 min), Killip ≤ II, and CCI ≤ 2. CONCLUSION: Younger age, shockable rhythm, and shorter duration of resuscitation were all factors demonstrated to be a predictor of ROSC and survival to hospital discharge.