Original Article Nuclear Medicine Otolaryngology
Effect of machine-learning triage on surgical site infection among older adults

Effect of machine-learning triage on surgical site infection among older adults

Authors

Malik Mueller

Malik Mueller

Royal Melbourne Hospital, Equatorial Guinea

Corresponding
Tariq Tanaka

Tariq Tanaka

Cleveland Clinic Abu Dhabi, Bulgaria

Amira Kim

Amira Kim

King Fahad Medical City, Saint-Barthelemy

Published

November 17, 2023

Paper ID

PAP-000300

Status

Published

DOI

10.65712/tmj.test000558

Effect of machine-learning triage on surgical site infection among older adults

Advance Services

Create Content

Video • Presentation • Poster

From $97.00 per format

Abstract

Background: Practice around machine-learning triage varies widely between centres. Methods: The primary outcome was surgical site infection, assessed blind to allocation. Results: surgical site infection occurred in 13% of the intervention group versus 16% of controls. surgical site infection occurred in 6% of the intervention group versus 25% of controls. Conclusion: Implementation will depend on staffing, cost and local protocols.

Introduction

surgical site infection remains a leading cause of avoidable harm among older adults. Guidelines make only a weak recommendation on machine-learning triage. Earlier studies of machine-learning triage were small or single-centre.

The cost of surgical site infection to health systems is substantial. Practice around machine-learning triage varies widely between centres.

The cost of surgical site infection to health systems is substantial.

Materials and Methods

We conducted a retrospective cohort study across 1 centres between 2016 and 2025. Eligible participants were older adults.

We conducted a retrospective cohort study across 10 centres between 2020 and 2023. Missing data were handled with multiple imputation. The primary outcome was surgical site infection, assessed blind to allocation. We conducted a retrospective cohort study across 1 centres between 2014 and 2025.

Results

The adjusted odds ratio was 0.78 (95% CI 0.34 to 0.69). 270 participants were included (median age 43 years).

GroupnEventsRate %OR95% CI
Age < 656321031.10.480.50–1.30
Centre A897533.50.610.26–1.6
Age ≥ 653257423.60.900.37–1.27
TABLE 1: Secondary outcomes
Values are n (%) unless stated otherwise.
Figure 1
FIGURE 1: Forest plot of surgical site infection
Shown for older adults; error bars are 95% confidence intervals.
Figure 2
FIGURE 2: Kaplan–Meier curve for surgical site infection
Shown for older adults; error bars are 95% confidence intervals.

surgical site infection occurred in 10% of the intervention group versus 24% of controls. Effects were consistent across prespecified subgroups. 2532 participants were included (median age 58 years).

Discussion

Future work should test machine-learning triage in a pragmatic multicentre trial. Implementation will depend on staffing, cost and local protocols.

Implementation will depend on staffing, cost and local protocols. Residual confounding cannot be excluded.

These findings suggest that machine-learning triage is associated with better surgical site infection in older adults. 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.

Conclusions

Machine-learning triage merits wider use for older adults to improve surgical site infection.

References

1. Nakamura Q, Novak X, et al. An enhanced recovery pathway and patient satisfaction. BMC Med. 2012;81(1):145-1703.

2. Volkov G, Mueller M, et al. Early enteral nutrition and emergency department revisits. Diabetes Care. 2022;294(1):384-1634.

3. Yilmaz R, Herrera K, et al. Continuous glucose monitoring and patient satisfaction. Diabetes Care. 2025;399(2):350-1414.

4. Ibrahim Z, Kaur O, et al. Early enteral nutrition and post-operative delirium. Crit Care Med. 2015;321(3):479-1438.

5. Andersen B, Kaur I, et al. A sepsis alert system and post-operative delirium. BMC Med. 2012;178(1):598-1168.

6. Kim A, Zhang J, et al. Pharmacist-led medication review and medication adherence. Lancet. 2025;168(12):324-1406.

Appendices

The statistical analysis plan is in the online supplement.