Evaluation of optimal scene time interval for out-of-hospital cardiac arrest using a deep neural network.

AIM: This study aims to develop a cardiac arrest prediction model using deep learning (CAPD) algorithm and to validate the developed algorithm by evaluating the change in out-of-hospital cardiac arrest patient prognosis according to the increase in scene time interval (STI). METHODS: We conducted a retrospective cohort study using smart advanced life support trial data collected by the National Emergency Center from January 2016 to December 2019. The smart advanced life support data were randomly partitioned into derivation and validation datasets. The performance of the CAPD model using the patient's age, sex, event witness, bystander cardiopulmonary resuscitation (CPR), administration of epinephrine, initial shockable rhythm, prehospital defibrillation, provision of advanced life support, response time interval, and STI as prediction variables for prediction of a patient's prognosis was compared with conventional machine learning methods. After fixing other values of the input data, the changes in prognosis of the patient with respect to the increase in STI was observed. RESULTS: A total of 16,992 patients were included in this study. The area under the receiver operating characteristic curve values for predicting prehospital return of spontaneous circulation (ROSC) and favorable neurological outcomes were 0.828 (95% confidence interval 0.826-0.830) and 0.907 (0.914-0.910), respectively. Our algorithm significantly outperformed other artificial intelligence algorithms and conventional methods. The neurological recovery rate was predicted to decrease to 1/3 of that at the beginning of cardiopulmonary resuscitation when the STI was 28 min, and the prehospital ROSC was predicted to decrease to 1/2 of its initial level when the STI was 30 min. CONCLUSION: The CAPD exhibits potential and effectiveness in identifying patients with ROSC and favorable neurological outcomes for prehospital resuscitation.

Association between Scene Time Interval and Survival in EMS-Treated Major Trauma Admitted to the Intensive Care Unit: A Multinational, Multicenter Observational Study.

Objective: Major trauma is a major concern in public health and a leading cause of mortality worldwide. This study aimed to evaluate the association between the prehospital scene time interval (STI) and survival in emergency medical service (EMS)-assessed major trauma patients admitted to the intensive care unit (ICU). Methods: A retrospective observational study using the Pan-Asian Trauma Outcomes Study (PATOS) database was conducted. Adult trauma patients with injury severity scores (ISSs) greater than 15 who were admitted to the ICU were selected. EMS STIs were categorized into three groups: short (0-8 minutes), intermediate (9-16 minutes), and long (over 16 minutes). The primary outcome was survival to hospital discharge, and the secondary outcome was good neurological outcome at hospital discharge. Multivariable logistic regression analysis was conducted to calculate odds ratios and confidence intervals, adjusting for age, sex, mechanism of injury, prehospital alertness, prehospital shock index, response time interval, and EMS intervention (airway, oxygen supplementation, and intravenous fluid administration). Sensitivity analysis for patients who underwent surgery or nontraumatic brain injury cases and interaction analysis by EMS intervention were performed. Results: Data from a total of 1,874 eligible patients were analyzed. Intermediate and long STIs showed significant associations with outcomes, with adjusted ORs (95% CI) of 1.21 (1.07-1.38) in the intermediate STI group and 1.74 (1.55-1.96) in the long STI group for survival and 1.37 (1.32-1.40) in the intermediate STI group and 1.31 (1.22-1.41) in the long STI group for neurological outcome. In the sensitivity analysis, the highest ORs were found in the intermediate STI group, with adjusted ORs (95% CI) of 1.40 (1.37-1.42) for survival and 1.32 (1.26-1.38) for neurological outcome. In the interaction analysis, EMS intervention showed a positive interaction effect with an intermediate STI on survival. Conclusion: In EMS-assessed adult major trauma patients admitted to the ICU, we found significant associations between STIs longer than 8 minutes and outcomes. EMS intervention has a positive interaction effect with an intermediate STI on survival. More research is needed to understand the implications of practice for major trauma in the field.

Association of the duration of on-scene advanced life support with good neurological recovery in out-of-hospital cardiac arrest.

BACKGROUND: As advanced life support (ALS) provided by emergency medical services (EMS) on scene becomes more common, the scene time interval (STI) for which EMS providers stay on scene tends to lengthen. We investigated the relationship between the STI and neurological outcome of patients at hospital discharge when ALS was provided by EMS on scene. METHODS: We conducted a retrospective analysis of prospectively collected out-of-hospital cardiac arrest (OHCA) data between August 2015 and December 2018. A restricted cubic spline curve was used to investigate the relationship between the STI and neurologic outcome, and patients were divided into two groups based on the cut-off value obtained through receiver operating characteristic (ROC) analysis. Comparisons of outcomes between the two groups were performed before and after propensity score matching. RESULTS: 4548 patients were included in the analysis. In ROC analysis, the optimal cut-off value for STI was 19 min. For the group with an STI <19 min, survival admission, survival discharge, and good neurologic outcome at hospital discharge were all higher than for the group with STI ≥19 min before and after propensity score matching. The multivariable model also showed that the STI ≥19 min was significantly associated with poor neurologic outcome at hospital discharge compared with the STI <19 min (adjusted odds ratio, 2.00; 95% CI, 1.40-2.88). CONCLUSIONS: A duration of on-scene ALS more than 19 min was associated with a poor neurologic outcome of patients at hospital discharge in OHCA.

Relationship Between Nonconveyed Cases and On-Scene Time Intervals for Emergency Medical Services.

PURPOSE: Emergency medical service (EMS) consumption is increasing worldwide. Some EMS cases in Saudi Arabia result in nonconveyance of patients. The aim of the present study was to determine the relationship between nonconveyed EMS cases and on-scene time intervals in Riyadh EMS centers. METHODS: Nonrandomized retrospective data obtained from EMS providers of nonconveyed emergency cases were gathered and analyzed. Data were taken from the ten busiest EMS centers in Riyadh, Saudi Arabia from January 1 to April 30, 2019. Analyses of means ± SD, bivariate comparisons, multivariate analysis, CI correlations, and regressionwere performed. RESULTS: Categories of nonconveyed cases were "Treatment given at the scene" V1 = 66, "Refused by patient/relative" (V2 = 876), "Patient not found" (V3 = 67), "Dead patient" (V4 = 80", "Other (police, etc)" (V5 = 34), and NA (96). We found highly significant differences (p<0.001) among several categories of nonconveyed cases and on-scene time intervals among EMS centers. CONCLUSION: This study found that there were highly significant differences among several categories of nonconveyed cases in relation to on-scene time intervals for different EMS centers. Results indicated that the probability of nonconveyance decisions was more likely to increase in the categories "Refused by patient/relative," "Patient not found," and "Dead patient." The results did not reveal details of what happened on scene during or after the nonconveyance decision had been made, which needs to be investigated.

Mandated 30-minute Scene Time Interval Correlates With Improved Return of Spontaneous Circulation at Emergency Department Arrival: A Before and After Study.

BACKGROUND: Conflicting ideas exist about whether or not Emergency Medical Service (EMS) personnel should treat a cardiac arrest on scene or transport immediately. OBJECTIVE: Our aim was to examine patient outcomes before and after an urban EMS system implemented a protocol change mandating a 30-min scene time interval (STI) for out-of-hospital cardiac arrest (OHCA). METHODS: This was a retrospective, single-center, observational study of OHCA patients before and after an EMS protocol change mandating resuscitation on scene. Data were retrieved from an EMS cardiac arrest database for all adults with non-traumatic OHCA between January 2015 and August 2016. Descriptive statistics were used to summarize the study population, and a regression model was used to determine the associations of the protocol with the return of spontaneous circulation (ROSC). RESULTS: A total of 633 patients were included in the study population, which was primarily male (61.3%) with a mean age of 65 years. After the 30-min STI was implemented, ROSC from OHCA increased to 40.1% of cases compared to 27.3% before the protocol change (p = 0.001; 95% confidence interval [CI] 0.053-0.203). The STI increased from 19 min 23 s to 29 min 40 s in the pre and post periods, respectively (p < 0.001). Regression indicated that the protocol change was independently associated with an improved chance of ROSC (OR 1.81; 95% CI 1.23-2.64). CONCLUSIONS: A protocol change mandating a 30-min STI in OHCA correlated with increased STI and increased ROSC. While increased ROSC may not always equate with positive neurologic outcome, logistic regression indicated that the protocol change was independently associated with improved ROSC at emergency department arrival.

Features of hospital and emergency medical service in out-of-hospital cardiac arrest patients with shockable rhythm.

OBJECTIVE: Predicting the outcome of out-of-hospital cardiac arrest (OHCA) patients is crucial. We examined hospital characteristics and parameters of emergency medical service (including scene time interval and direct ambulance delivery to intensive heart hospitals) as survival or outcome predictors. STUDY DESIGN: Data from 546 consecutive OHCA shockable patients treated between January 2012 and December 2015 in Taoyuan City (Taiwan, ROC) were collected. In addition to demographic data, location of arrest, initial rhythm, availability of a hospital with or without 24/7 percutaneous coronary intervention (PCI), emergency medical service (EMS) time, provision of cardiopulmonary resuscitation by a bystander, presence of a witness at collapse, and level of life support were analysed. RESULTS: Multivariate analysis showed that hospitalisation with immediate PCI availability was an independent predictor (OR: 4.32; 95% CI: 1.27-14.70) solely for the outcome of survival until discharge. The presence of a witness while collapsing (OR: 3.52; 95% CI: 1.03-11.98), EMS response time (OR: 0.83; 95% CI: 0.70-0.98), and scene time interval (STI; OR: 0.89; 95% CI: 0.81-0.99) were valuable for predicting the neurological outcome. CONCLUSIONS: Direct ambulance delivery to intensive heart hospitals that had 24/7 PCI availability was associated with a higher probability of surviving until discharge in OHCA patients with shockable rhythms. Similarly, a witnessed collapse was correlated with being discharged alive from hospital and recovering with good cerebral performance. In addition, longer response time and scene time interval indicated poorer survival and neurological outcome.

Association between resuscitation time interval at the scene and neurological outcome after out-of-hospital cardiac arrest in two Asian cities.

BACKGROUND AND AIM: It is unclear whether the scene time interval (STI) for cardiopulmonary resuscitation (CPR) is associated with outcomes of out-of-hospital cardiac arrest (OHCA) or not. The present study aimed to determine the association between STI and neurological outcome after OHCA using two large population-based cohorts covering two metropolitan cities in Asia. METHODS: A retrospective analysis based on two large population-based cohorts from Seoul (2008-2010) and Osaka (2007-2009) was performed for witnessed adult OHCA with presumed cardiac aetiology. The STI, defined as time from wheel arrival at the scene to departure to hospital, was categorised as short (<8min), intermediate (from 8 to <16min) and long (16min or longer) STI on the basis of sensitivity analysis. The primary outcome was good neurological outcome (cerebral performance category 1 or 2). Adjusted odds ratios (AORs) with 95% confidence intervals (CIs) were calculated to determine the association between STIs and outcomes in comparison to the short STI group adjusting for potential risk factors and interaction products. RESULTS: A total of 7757 patients, 3594 from Seoul and 4163 from Osaka, were finally analysed. There were significant differences among the STI groups for most potential risk variables. Survival to admission was higher in the intermediate STI group (35.7%) than in the short (31.8%) or long STI group (32.6%) (p=0.004). Survival to discharge was not different among groups, at 13.7%, 13.1% and 11.5%, respectively (p=0.094). The intermediate STI group had a significantly better neurological outcome compared with the short STI group (7.7% vs. 4.6%; AOR=1.32; 95% CI, 1.03-1.71), while the long STI (6.6%) did not. CONCLUSION: Data from two metropolitan cities demonstrated a positive association between intermediate STI from 8 to 16min and good neurological outcome after OHCA.