Geographical validation of the Smart Triage Model by age group

TL;DR

This study validates a clinical prediction model for identifying critically ill children in low-resource settings, finding it effective for most age groups but less so for neonates, prompting model updates.

Contribution

The study externally validates and updates the Smart Triage model for neonates in low-resource settings, improving its predictive accuracy.

Findings

The original model showed good discrimination for children under five (AUROC 0.81) but poor performance for neonates (AUROC 0.62).

After revision, the neonatal model achieved improved discrimination (AUROC 0.83) with new risk thresholds.

The updated model is suitable for use in local healthcare facilities across different age groups.

Abstract

Infectious diseases in neonates account for half of the under-five mortality in low- and middle-income countries. Data-driven algorithms such as clinical prediction models can be used to efficiently detect critically ill children in order to optimize care and reduce mortality. Thus far, only a handful of prediction models have been externally validated and are limited to neonatal in-hospital mortality. The aim of this study is to externally validate a previously derived clinical prediction model (Smart Triage) using a combined prospective baseline cohort from Uganda and Kenya with a composite endpoint of hospital admission, mortality, and readmission. We evaluated model discrimination using area under the receiver-operator curve (AUROC) and visualized calibration plots with age subsets (< 30 days, ≤ 2 months, ≤ 6 months, and < 5 years). Due to reduced performance in neonates (< 1 month), we re-estimated the intercept and coefficients and selected new thresholds to maximize sensitivity and specificity. 11595 participants under the age of five (under-5) were included in the analysis. The proportion with an endpoint ranged from 8.9% in all children under-5 (including neonates) to 26% in the neonatal subset alone. The model achieved good discrimination for children under-5 with AUROC of 0.81 (95% CI: 0.79–0.82) but poor discrimination for neonates with AUROC of 0.62 (95% CI: 0.55–0.70). Sensitivity at the low-risk thresholds (CI) were 85% (83%–87%) and 68% (58%–76%) for children under-5 and neonates, respectively. After model revision for neonates, we achieved an AUROC of 0.83 (95% CI: 0.79–0.87) with 13% and 41% as the low- and high-risk thresholds, respectively. The updated Smart Triage performs well in its predictive ability across different age groups and can be incorporated into current triage guidelines at local healthcare facilities. Additional validation of the model is indicated, especially for the neonatal model.

Clinical prediction modeling is becoming evermore popular in various medical fields as it can improve clinical decision-making by providing personalized risk estimate for patients. It is a statistical technique that incorporates patient-specific factors to personalize treatment and optimize health resources allocation. Clinical prediction models need to be validated in a different setting and population, and updated accordingly to ensure accuracy and relevance in clinical settings. We aim to evaluate one such model currently being implemented at the outpatient pediatric department at multiple hospitals in Uganda and Kenya. This model has been incorporated into a digital platform that is used to quickly identify critically ill children at triage. After validating the model against different age groups, we found the current model is well suited for various age groups under five years old except neonates and thus attempted to update the model. Our study provides new insight into clinical variables that impact neonatal outcomes and we hope to lower neonatal mortality for low-resource settings.

Figures