Nur Shahidah

Prediction of cardiac arrest in critically ill patients presenting to the emergency department using a machine learning score incorporating heart rate variability compared with the modified early warning score.

IntroductionA key aim of triage is to identify those with high risk of cardiac arrest, as they require intensive monitoring, resuscitation facilities, and early intervention. We aim to validate a novel machine learning (ML) score incorporating heart rate variability (HRV) for triage of critically ill patients presenting to the emergency department by comparing the area under the curve, sensitivity and specificity with the modified early warning score (MEWS).MethodsWe conducted a prospective observational study of critically ill patients (Patient Acuity Category Scale 1 and 2) in an emergency department of a tertiary hospital. At presentation, HRV parameters generated from a 5-minute electrocardiogram recording are incorporated with age and vital signs to generate the ML score for each patient. The patients are then followed up for outcomes of cardiac arrest or death.ResultsFrom June 2006 to June 2008 we enrolled 925 patients. The area under the receiver operating characteristic curve (AUROC) for ML scores in predicting cardiac arrest within 72 hours is 0.781, compared with 0.680 for MEWS (difference in AUROC: 0.101, 95% confidence interval: 0.006 to 0.197). As for in-hospital death, the area under the curve for ML score is 0.741, compared with 0.693 for MEWS (difference in AUROC: 0.048, 95% confidence interval: -0.023 to 0.119). A cutoff ML score ≥ 60 predicted cardiac arrest with a sensitivity of 84.1%, specificity of 72.3% and negative predictive value of 98.8%. A cutoff MEWS ≥ 3 predicted cardiac arrest with a sensitivity of 74.4%, specificity of 54.2% and negative predictive value of 97.8%.ConclusionWe found ML scores to be more accurate than the MEWS in predicting cardiac arrest within 72 hours. There is potential to develop bedside devices for risk stratification based on cardiac arrest prediction.

Comparison of emergency medical services systems in the pan-Asian resuscitation outcomes study countries: Report from a literature review and survey

Asia–Pacific countries have unique prehospital emergency care or emergency medical services (EMS) systems, which are different from European or Anglo‐American models. We aimed to compare the EMS systems of eight Asia–Pacific countries/regions as part of the Pan Asian Resuscitation Outcomes Study (PAROS), to provide a basis for future comparative studies across systems of care.

Heart rate variability risk score for prediction of acute cardiac complications in ED patients with chest pain

BACKGROUND We aimed to develop a risk score incorporating heart rate variability (HRV) and traditional vital signs for the prediction of early mortality and complications in patients during the initial presentation to the emergency department (ED) with chest pain. METHODS We conducted a prospective observational study of patients with a primary complaint of chest pain at the ED of a tertiary hospital. The primary outcome was a composite of mortality, cardiac arrest, ventricular tachycardia, hypotension requiring inotropes or intraaortic balloon pump insertion, intubation or mechanical ventilation, complete heart block, bradycardia requiring pacing, and recurrent ischemia requiring revascularization, all within 72 hours of arrival at ED. RESULTS Three hundred nine patients were recruited, and 25 patients met the primary outcome. Backwards stepwise logistic regression was used to derive a scoring model that included heart rate, systolic blood pressure, respiratory rate, and low frequency to high frequency ratio. For predicting complications within 72 hours, the risk score performed with an area under the curve of 0.835 (95% confidence interval [CI], 0.749-0.920); and a cutoff of 4 and higher in the risk score gave a sensitivity of 0.880 (95% CI, 0.677-0.968), specificity of 0.680 (95% CI, 0.621-0.733), positive predictive value of 0.195, and negative predictive value of 0.985. The risk score performed better than ST elevation/depression and troponin T in predicting complications within 72 hours. CONCLUSION A risk score incorporating heart rate variability and vital signs performed well in predicting mortality and other complications within 72 hours after arrival at ED in patients with chest pain.

A before-after interventional trial of dispatcher-assisted cardio-pulmonary resuscitation for out-of-hospital cardiac arrests in Singapore

AIM To evaluate the effects of a comprehensive dispatcher-assisted CPR (DACPR) training program on bystander CPR (BCPR) rate and the outcomes of out-of-hospital cardiac arrest (OHCA) in Singapore. METHODS This is an initial program evaluation of a national DACPR intervention. A before-after analysis was conducted using OHCA cases retrieved from a local registry and DACPR information derived from audio recordings and ambulance notes. The primary outcomes were survival to admission, survival at 30 days post-arrest and good functional recovery. RESULTS Data was collected before the intervention (April 2010 to December 2011), during the run-in period (January 2012 to June 2012) and after the intervention (July 2012 to February 2013). A total of 2968 cases were included in the study with a mean age of 65.6. Overall survival rate was 3.9% (116) with good functional recovery in 2.2% (66) of the patients. BCPR rate increased from 22.4% to 42.1% (p<0.001) with odds ratio (OR) of 2.52 (95% confidence interval [CI]: 2.09-3.04) and ROSC increased significantly from 26.5% to 31.2% (p=0.02) with OR of 1.26 (95%CI: 1.04-1.53) after the intervention. Significantly higher survival at 30 days was observed for patients who received BCPR from a trained person as compared to no BCPR (p=0.001, OR=2.07 [95%CI: 1.41-3.02]) and DACPR (p=0.04, OR=0.30 [95%CI: 0.04-2.18]). CONCLUSION A significant increase in BCPR and ROSC was observed after the intervention. There was a trend to suggest improved survival outcomes with the intervention pending further results from the trial.

Spatial Variation and Geographic-Demographic Determinants of Out-of-Hospital Cardiac Arrests in the City-State of Singapore

STUDY OBJECTIVE Our primary objective is to calculate the relative risk of cardiac arrests at the development guide plan (DGP) (equivalent to census tract) level in a city-state, Singapore, and examine its relationship with key area-level population characteristics. METHODS This was an observational ecological study design. We calculated the relative risk as the ratio of the observed and population standardized expected counts of out-of-hospital cardiac arrests in Singapore, aggregated at DGP level. Data were collected from October 2001 to October 2004. We used conditional autoregressive spatial models to examine the predictors of increased risk at the DGP level. RESULTS We found a spatial distribution of cardiac arrests, with an unexpected cluster caused by nonresident arrests occurring at the international airport. The risk of out-of-hospital cardiac arrest more than doubled, 2.35 (95% confidence interval [CI] 1.28 to 4.48), for each 5-point increase in the proportion of people aged 65 years and older. For each 5-point increase in the proportion of Chinese individuals living in a DGP, the risk of out-of-hospital cardiac arrest was reduced by a factor of 0.8 (95% CI 0.7 to 0.9). The risk of out-of-hospital cardiac arrest increased by 1.49-fold (95% CI 1.18 to 1.82) for every 5-point increase in the proportion of households with no family nucleus (live alone). When restricted to residential cases of out-of-hospital cardiac arrest, none of the variables remained significant, possibly because of small sample size. CONCLUSION The risk of cardiac arrests could be related to the age and racial and family structure of DGPs in Singapore. This article models how such data can help to direct public health education, cardiopulmonary resuscitation training, and public access defibrillation programs in other health systems.

How accurate are vital signs in predicting clinical outcomes in critically ill emergency department patients.

Objectives We aimed to evaluate the predictive value of pulse rate (PR), systolic blood pressure (SBP), diastolic blood pressure, respiratory rate (RR), oxygen saturation (SaO2), and the Glasgow Coma Scale (GCS) for cardiac arrest and death in critically ill patients. Methods In total, 1025 patients had vital signs recorded at triage at our Emergency Department and were followed up for three clinical outcomes: cardiac arrest in 72 h, admission to ICU, and death within 30 days. Vital signs were used in univariate and multivariate analyses for outcomes. Age was added in multivariate analysis. Results PR, SBP, RR, SaO2, and GCS were significantly associated with cardiac arrest within 72 h, whereas PR, SBP, RR, SaO2, and GCS were associated with death within 30 days. Only PR and GCS were associated with ICU admission. In the multivariate analysis, age, PR (>100) [odds ratio (OR) 1.65; 95% confidence interval (CI) 1.00–2.71], SBP (>140; OR 0.41; 95% CI: 0.21–0.79), RR (>20; OR 2.90; 95% CI: 1.67–5.03), and GCS (<15; OR 5.71; 95% CI: 3.40–9.57) were significantly associated with death. Vital signs with age have low sensitivity (cardiac arrest 11.54%, death 22.73%, ICU 12.50%) and high specificity (cardiac arrest 99.28%, death 97.22%, ICU 93.80%). Age and GCS were found to be independent predictors of all three outcomes. Conclusion Not all vital signs are useful in the prediction of clinical outcomes. Vital signs had high specificity but very low sensitivity as predictors of clinical outcomes. Clinicians should always remember to treat patients and not numbers.

Geographical Variation in Ambulance Calls Is Associated With Socioeconomic Status

OBJECTIVES   The main objective was to explore the relationship between socioeconomic status and the spatial distribution of ambulance calls, as modeled in the island nation of Singapore, at the Development Guide Plan (DGP) level (equivalent to census tracts in the United States). METHODS   Ambulance call data came from a nationwide registry from January to May 2006. We used a conditional autoregressive (CAR) model to create smoothed maps of ambulance calls at the DGP level, as well as spatial regression models to evaluate the relationship between the risk of calls with regional measures of socioeconomic status, such as household type and both personal and household income. RESULTS   There was geographical correlation in the ambulance calls, as well as a socioeconomic gradient in the relationship with ambulance calls of medical-related (but not trauma-related) reasons. For instance, the relative risk (RR) of medical ambulance calls decreased by a factor of 0.66 (95% credible interval [CrI] = 0.56 to 0.79) for every 10% increase in the proportion of those with monthly household income S

Spatial Analysis of Ambulance Response Times Related to Prehospital Cardiac Arrests in the City-State of Singapore

5000 and above. The top three DGPs with the highest risk of medical-related ambulance calls were Changi (RR = 29, 95% CrI = 24 to 35), downtown core (RR = 8, 95% CrI = 6 to 9), and Orchard (RR = 5, 95% CrI = 4 to 6). CONCLUSIONS   This study demonstrates the utility of geospatial analysis to relate population socioeconomic factors with ambulance call volumes. This can serve as a model for analysis of other public health systems.

Implications for public access defibrillation placement by non-traumatic out-of-hospital cardiac arrest occurrence in Singapore

Abstract Objectives. The main objective of this study was to establish the spatial variation in ambulance response times for out-of-hospital cardiac arrests (OHCAs) in the city-state of Singapore. The secondary objective involved studying the relationships between various covariates, such as traffic condition and time and day of collapse, and ambulance response times. Methods. The study design was observational and ecological in nature. Data on OHCAs were collected from a nationally representative database for the period October 2001 to October 2004. We used the conditional autoregressive (CAR) model to analyze the data. Within the Bayesian framework of analysis, we used a Weibull regression model that took into account spatial random effects. The regression model was used to study the independent effects of each covariate. Results. Our results showed that there was spatial heterogeneity in the ambulance response times in Singapore. Generally, areas in the far outskirts (suburbs), such as Boon Lay (in the west) and Sembawang (in the north), fared badly in terms of ambulance response times. This improved when adjusted for key covariates, including distance from the nearest fire station. Ambulance response time was also associated with better traffic conditions, weekend OHCAs, distance from the nearest fire station, and OHCAs occurring during nonpeak driving hours. For instance, the hazard ratio for good ambulance response time was 2.35 (95% credible interval [CI] 1.97–2.81) when traffic conditions were light and 1.72 (95% CI 1.51–1.97) when traffic conditions were moderate, as compared with heavy traffic. Conclusions. We found a clear spatial gradient for ambulance response times, with far-outlying areas’ exhibiting poorer response times. Our study highlights the utility of this novel approach, which may be helpful for planning emergency medical services and public emergency responses.

Derivation of indices of socioeconomic status for health services research in Asia.

The American Heart Association recommends automated external defibrillator placement in public areas with a high probability (>1) of out‐of‐hospital cardiac arrest (OHCA) occurring in 5 years. We aimed to determine the incidence rate of OHCA for different location categories in Singapore.