Does machine-learning triage reduce health-related quality of life in children with asthma? A multicentre observational study
Published
June 23, 2026
Paper ID
PAP-000073
Status
Published
DOI
10.65712/tmj.test000331
Advance Services
Abstract
Background: Practice around machine-learning triage varies widely between centres. Methods: We conducted a multicentre observational study across 1 centres between 2016 and 2024. Results: Effects were consistent across prespecified subgroups. The adjusted odds ratio was 0.59 (95% CI 0.37 to 0.90). Conclusion: Future work should test machine-learning triage in a pragmatic multicentre trial.
Introduction
Practice around machine-learning triage varies widely between centres. Guidelines make only a weak recommendation on machine-learning triage.
Earlier studies of machine-learning triage were small or single-centre. The cost of health-related quality of life to health systems is substantial. health-related quality of life remains a leading cause of avoidable harm among children with asthma. Practice around machine-learning triage varies widely between centres.
Practice around machine-learning triage varies widely between centres. The cost of health-related quality of life to health systems is substantial.
Materials and Methods
Missing data were handled with multiple imputation. Eligible participants were children with asthma. We conducted a multicentre observational study across 4 centres between 2014 and 2024.
Eligible participants were children with asthma. Missing data were handled with multiple imputation. We conducted a multicentre observational study across 1 centres between 2015 and 2023.
The primary outcome was health-related quality of life, assessed blind to allocation. We conducted a multicentre observational study across 13 centres between 2015 and 2023. Missing data were handled with multiple imputation.
Results
3032 participants were included (median age 66 years). health-related quality of life occurred in 12% of the intervention group versus 13% of controls. 4642 participants were included (median age 74 years).
Effects were consistent across prespecified subgroups. 2318 participants were included (median age 41 years).
| Group | n | Events | Rate % | OR | 95% CI |
|---|---|---|---|---|---|
| Centre A | 468 | 51 | 25.0 | 0.98 | 0.23–1.34 |
| Age ≥ 65 | 643 | 114 | 31.2 | 0.67 | 0.29–1.35 |
| Intervention | 88 | 76 | 21.4 | 0.47 | 0.57–1.39 |
| Centre A | 867 | 61 | 32.0 | 0.84 | 0.60–1.10 |
| Centre A | 297 | 22 | 40.4 | 0.76 | 0.41–1.1 |
| Female | 725 | 36 | 24.6 | 0.95 | 0.24–1.34 |
Values are n (%) unless stated otherwise.

Shown for children with asthma; error bars are 95% confidence intervals.
The adjusted odds ratio was 0.52 (95% CI 0.26 to 0.86). Effects were consistent across prespecified subgroups. health-related quality of life occurred in 16% of the intervention group versus 23% of controls. Serious adverse events were rare and similar between groups.
Discussion
Residual confounding cannot be excluded. Future work should test machine-learning triage in a pragmatic multicentre trial.
Future work should test machine-learning triage in a pragmatic multicentre trial.
These findings suggest that machine-learning triage is associated with better health-related quality of life in children with asthma. Implementation will depend on staffing, cost and local protocols.
Future work should test machine-learning triage in a pragmatic multicentre trial. Implementation will depend on staffing, cost and local protocols.
Conclusions
Machine-learning triage is a reasonable option for children with asthma to improve health-related quality of life.
References
1. Farouk D, Moreau F, et al. Frailty screening and acute kidney injury. Lancet. 2015;174(2):863-1747.
2. Kim C, Mensah R, et al. Machine-learning triage and acute kidney injury. BMC Med. 2016;168(5):273-966.
3. Herrera L, Mueller R, et al. Pharmacist-led medication review and ventilator-free days. BMJ. 2012;29(4):729-980.
4. Nasser V, Osei T, et al. A sepsis alert system and falls. Ann Intern Med. 2009;340(11):878-1004.
5. Kowalski N, Costa Y, et al. A sepsis alert system and health-related quality of life. N Engl J Med. 2021;157(10):758-1642.
6. Kaur J, Schmidt L, et al. Early enteral nutrition and health-related quality of life. Crit Care Med. 2009;362(9):885-1210.
Appendices
Supplementary tables are available on request.