Case Report Dermatology Family/General Practice Geriatrics
Does machine-learning triage reduce emergency department revisits in preterm neonates? A cross-sectional survey

Does machine-learning triage reduce emergency department revisits in preterm neonates? A cross-sectional survey

Authors

Omar Patel

Omar Patel

Mayo Clinic, Maldives

Corresponding
Tariq Novak

Tariq Novak

Cleveland Clinic Abu Dhabi, Barbados

Mariam Haddad

Mariam Haddad

King Fahad Medical City, Nigeria

Lina Mensah

Lina Mensah

Aga Khan University Hospital, Chile

Felix Silva

Felix Silva

Toronto General Hospital, Mexico

Published

October 25, 2025

Paper ID

PAP-000185

Status

Published

DOI

10.65712/tmj.test000443

Does machine-learning triage reduce emergency department revisits in preterm neonates? A cross-sectional survey

Advance Services

Create Content

Video • Presentation • Poster

From $97.00 per format

Abstract

Background: The cost of emergency department revisits to health systems is substantial. Methods: We conducted a cross-sectional survey across 10 centres between 2016 and 2024. Results: emergency department revisits occurred in 11% of the intervention group versus 27% of controls. The adjusted odds ratio was 0.55 (95% CI 0.31 to 0.61). Conclusion: Strengths include the sample size and blinded outcome assessment.

Introduction

Practice around machine-learning triage varies widely between centres. The cost of emergency department revisits to health systems is substantial.

The cost of emergency department revisits to health systems is substantial. emergency department revisits remains a leading cause of avoidable harm among preterm neonates.

Guidelines make only a weak recommendation on machine-learning triage. The cost of emergency department revisits to health systems is substantial.

Discussion

These findings suggest that machine-learning triage is associated with better emergency department revisits in preterm neonates. Strengths include the sample size and blinded outcome assessment.

Residual confounding cannot be excluded. Implementation will depend on staffing, cost and local protocols. These findings suggest that machine-learning triage is associated with better emergency department revisits in preterm neonates.

Strengths include the sample size and blinded outcome assessment. Implementation will depend on staffing, cost and local protocols.

Strengths include the sample size and blinded outcome assessment. Future work should test machine-learning triage in a pragmatic multicentre trial.

Residual confounding cannot be excluded. Strengths include the sample size and blinded outcome assessment. Future work should test machine-learning triage in a pragmatic multicentre trial.

Conclusions

Machine-learning triage is a reasonable option for preterm neonates to improve emergency department revisits.

References

1. Yilmaz B, Moreau K, et al. High-flow nasal oxygen and chronic pain scores. BMJ. 2015;38(2):618-1615.

2. Silva O, Yilmaz T, et al. Frailty screening and time to diagnosis. Diabetes Care. 2012;21(11):725-1687.

3. Dubois R, Silva A, et al. Tranexamic acid and chronic pain scores. Pediatrics. 2012;96(9):479-1045.

4. Volkov V, Farouk C, et al. Pharmacist-led medication review and medication adherence. JAMA. 2019;292(2):523-1561.

5. Schmidt Z, Dubois R, et al. Early mobilisation and length of stay. N Engl J Med. 2022;124(4):609-1082.

6. Rahman A, Okafor X, et al. SGLT2 inhibitors and surgical site infection. N Engl J Med. 2013;305(6):326-1759.

Appendices

Ethics approval: IRB-1349.

Materials and Methods

Missing data were handled with multiple imputation. Eligible participants were preterm neonates.

Eligible participants were preterm neonates.

Missing data were handled with multiple imputation. Analyses were adjusted for age, sex and baseline severity.

Results

3828 participants were included (median age 36 years). Serious adverse events were rare and similar between groups.

GroupnEventsRate %
Centre A666346.1
Male606595.9
Control28254.8
Male8377028.0
Centre B8182833.7
Age ≥ 655452834.6
TABLE 1: Subgroup analysis
Values are n (%) unless stated otherwise.
Figure 1
FIGURE 1: Trend in emergency department revisits
Shown for preterm neonates; error bars are 95% confidence intervals.

2677 participants were included (median age 74 years). 4228 participants were included (median age 49 years). The adjusted odds ratio was 0.73 (95% CI 0.21 to 0.73). emergency department revisits occurred in 19% of the intervention group versus 30% of controls.

emergency department revisits occurred in 8% of the intervention group versus 38% of controls. The adjusted odds ratio was 0.50 (95% CI 0.43 to 0.72). Effects were consistent across prespecified subgroups.