Skip to main navigation Skip to main content

CEEM : Clinical and Experimental Emergency Medicine

OPEN ACCESS
ABOUT
BROWSE ARTICLES
FOR CONTRIBUTORS

Page Path

3
results for

"Stephanie Fook-Chong"

Article category

Publication year

Keywords

"Stephanie Fook-Chong"

Original Articles

Critical Care

Download Citation

Download a citation file in RIS format that can be imported by all major citation management software, including EndNote, ProCite, RefWorks, and Reference Manager.

Format:

Include:

Epidemiologic Trends and Practice Patterns in the Management of Sepsis in Emergency Departments: A Five-Year Singapore Cohort Study (2017-2021)
Download Citation

Download a citation file in RIS format that can be imported by all major citation management software, including EndNote, ProCite, RefWorks, and Reference Manager.

Format:
Include:
Epidemiologic Trends and Practice Patterns in the Management of Sepsis in Emergency Departments: A Five-Year Singapore Cohort Study (2017-2021)
Close
Objective
Southeast Asia is undergoing rapid population ageing, yet longitudinal ED-based sepsis data from the region are absent. We characterised sepsis epidemiology and management trends across three adult emergency departments (EDs) in Singapore over five years, establishing regional benchmarking data and examining evidence-to-practice translation during a period of active guideline change.
Methods
We conducted a retrospective cohort study of adult ED encounters with explicit sepsis ICD- 10 codes across three EDs (January 2017- December 2021) using the EM-RADAR database. Outcomes included incidence, demographics, admission rates, length of stay, mortality, fluid resuscitation, antibiotic timing, and vasopressor use. Temporal trends were assessed by regression with calendar year as a predictor.
Results
Among 1,636,828 ED encounters, 17,117 (1.05%) had explicit sepsis codes. Admissions (98.4%), hospital length of stay (median 6.03 days), in-hospital mortality (8.9%), and vasopressor requirement (4.9%) remained stable. The proportion of patients ≥65 years increased from 68.5% to 72.2% (OR 1.05 per year, 95% CI 1.02-1.07). Balanced crystalloid adoption increased six-fold (11.3% to 61.9%; OR 1.81 per year, 95% CI 1.76-1.86). Median time to antibiotics decreased to 80.8 minutes (IQR 45.5-124.2) by 2021; 64.2% of patients who required vasopressors received antibiotics within one hour. First-line vasopressor use shifted from dopamine (57.8%) to norepinephrine (67.1%).
Conclusions
Sepsis incidence (1.05%) was comparable to international reports, predominantly affecting elderly patients. Rapid balanced crystalloid adoption and risk-stratified antibiotic timing reflect successful evidence-to-practice translation. Opportunities remain in reducing antibiotic delays for patients requiring vasopressors and optimizing vasopressor selection. Findings provide benchmarking framework for ED sepsis quality improvement.
  • 391 View
  • 7 Download

AI & Digital Health | Cardiovascular

Download Citation

Download a citation file in RIS format that can be imported by all major citation management software, including EndNote, ProCite, RefWorks, and Reference Manager.

Format:

Include:

Pilot Evaluation of a Novel Artificial Intelligence (AI) Heart Rate Variability (HRV)-Guided Risk Stratification for Chest Pain in the Emergency Department: A Randomized Controlled Trial
Download Citation

Download a citation file in RIS format that can be imported by all major citation management software, including EndNote, ProCite, RefWorks, and Reference Manager.

Format:
Include:
Pilot Evaluation of a Novel Artificial Intelligence (AI) Heart Rate Variability (HRV)-Guided Risk Stratification for Chest Pain in the Emergency Department: A Randomized Controlled Trial
Close
Background
Heart rate variability (HRV) analysis powered by artificial intelligence (AI) offers a rapid, non-invasive, and objective approach for acute coronary syndrome (ACS) risk stratification in the emergency department (ED). The objective of this study was to evaluate the feasibility and impact of aiTriage™, an AI HRV-guided tool for chest pain triage, compared with standard care.
Methods
In this single-blinded randomized controlled trial, 560 ED patients with suspected ACS underwent 5- minute ECG monitoring for HRV analysis, which generated a 0–100 risk score and triage recommendations (high, medium, or low risk). Patients were randomized to standard care (control) or an HRV-guided protocol (intervention). Physicians in the control group were blinded to HRV results.
Results
Of 426 analysed patients (mean age 54 ± 13 years, 35% female, 16.2% prior MI), the HRV-guided protocol reduced hospital admissions (50.2% vs 61.1%; risk difference -10.9 percentage points, 95% CI: -20.1 to -1.8) and serial cardiac enzyme testing (32.1% vs 41.7%; risk difference -9.6 percentage points, 95% CI: -18.4 to -0.9) compared with standard care. Among discharged patients, the median ED length of stay was 20 minutes shorter in the intervention group (95% CI: -45 minutes to 3 minutes). The overall 30-day MACE rate was 9.5%, with no events among discharged patients.
Conclusion
A rapid AI HRV-guided risk stratification tool was feasible to deploy, and has potential to reduce serial cardiac enzyme testing, ED LOS and hospital admissions. An adequately powered RCT is needed to confirm these findings and assess clinical safety. This trial is registered at ClinicalTrials.gov (NCT07074808).
  • 1,241 View
  • 78 Download

Download Citation

Download a citation file in RIS format that can be imported by all major citation management software, including EndNote, ProCite, RefWorks, and Reference Manager.

Format:

Include:

Integrating the interpretable machine learning Score for Emergency Risk Prediction (SERP) with emergency department triage to better predict 30-day mortality
Clin Exp Emerg Med. 2026;13(3):292-302.   Published online April 3, 2026
Download Citation

Download a citation file in RIS format that can be imported by all major citation management software, including EndNote, ProCite, RefWorks, and Reference Manager.

Format:
Include:
Integrating the interpretable machine learning Score for Emergency Risk Prediction (SERP) with emergency department triage to better predict 30-day mortality
Clin Exp Emerg Med. 2026;13(3):292-302.   Published online April 3, 2026
Close
Objective
This study integrated a machine learning–based Score for Emergency Risk Prediction (SERP), developed using objective mortality endpoints, with the Patient Acuity Category Scale (PACS) and evaluated its predictive performance in clinical use. Methods This single-center, retrospective cohort study included all emergency department (ED) patients from a large tertiary hospital between January 1, 2018, and December 31, 2019. Using a reclassification framework, SERP was incorporated into PACS to derive two enhanced triage models. PACS+ model 1 down-triaged patients with low predicted 30-day mortality risk and up-triaged those with high risk. PACS+ model 2 up-triaged only high-risk patients, whereas lowrisk patients retained their original category. Predictive performance in the test cohort was assessed using the area under the receiver operating characteristic curve (AUC) and decision curve analysis. Results The derivation cohort included 97,188 ED visits, and the test cohort included 97,212 ED visits. In the derivation set, the mean age of the patients was 58.97±18.41 years, and 47,993 (49.4%) were female. Overall, 19.9%, 57.4%, 22.5%, and 0.2% of patients were triaged to PACS categories P1–P4, respectively. The 30-day mortality rate was 2.8% in the derivation set and 2.7% in the test cohort. For 30-day mortality prediction, PACS+ model 1 (AUC, 0.828; 95% confidence interval [CI], 0.820–0.836) and PACS+ model 2 (AUC, 0.812; 95% CI, 0.805–0.818) outperformed PACS (AUC, 0.722; 95% CI, 0.714–0.729). PACS+ model 1 consistently achieved greater net benefit across the range of clinical thresholds. Conclusion Integrating machine learning–based SERP with PACS improved 30-day mortality prediction in ED triage.
  • 3,036 View
  • 44 Download