Machine Learning for Predicting Critical Events Among Hospitalized Children
Sierra Strutz1, Huan Liang1, Kyle Carey2
1Department of Biostatistics & Medical Informatics, University of Wisconsin-Madison, Madison.
Insights
A new machine learning model effectively predicts critical events in hospitalized children, improving risk assessment across all hospital units. This unified approach enhances early detection and patient safety, reducing mortality and morbidity risks.
Area of Science:
- Pediatric critical care medicine
- Health informatics
- Machine learning in healthcare
Background:
- Unrecognized deterioration in hospitalized children leads to significant mortality and morbidity.
- Current pediatric risk stratification is fragmented, using different tools across hospital units (emergency, ward, intensive care).
Purpose of the Study:
- To develop a unified machine learning model for early detection of deterioration in pediatric patients.
- Enable continuous and consistent risk assessment throughout a child's hospital stay.
Main Methods:
- Retrospective cohort study of 135,621 pediatric admissions across 3 tertiary care academic hospitals.
- Developed and compared regression-based, extreme gradient-boosted machine (XGB), and deep learning models.
- Used 2 hospitals for model derivation and a third for external validation.
Main Results:
- The XGB model demonstrated superior discrimination (C statistic: 0.86) compared to existing ward-focused models (0.82 and 0.70).
- XGB required fewer alerts (6) at 80% sensitivity compared to ward models (9 and 11).
- The XGB model performed equivalently or better than unit-specific models.
Conclusions:
- A novel hospitalwide machine learning model was developed for continuous risk prediction of critical events in children.
- This model provides a unified framework for risk assessment in pediatric hospitals.
- The findings support the use of a single, adaptable model for improved pediatric patient safety.
Importance:
Unrecognized deterioration among hospitalized children is associated with a high risk of mortality and morbidity. The current approach to pediatric risk stratification is fragmented, as each hospital unit (emergency, ward, or intensive care) uses different tools for predicting specific outcomes.
Objective:
To develop a machine learning model for the early detection of deterioration across all units, thereby enabling a unified risk assessment throughout the patient's hospital stay.
Design, Setting, And Participants:
This retrospective cohort study used data from pediatric (age <18 years) admissions to inpatient and intensive care units at 3 tertiary care academic hospitals. Data were analyzed from January 2024 to March 2025.
Main Outcomes And Measures:
The primary outcome was critical events, defined as invasive mechanical ventilation, administration of vasoactive medications, or death within 12 hours of an observation.
Results:
The cohort included 135 621 patients (mean [SD] age, 7 [6] years; 60 376 [44.5%] female). Patient age, hospital unit, vital signs, laboratory results, and prior comorbidities were used to derive a regression-based model, an extreme gradient-boosted machine (XGB) model, and 2 deep learning models. Data from 2 hospitals were used as a derivation cohort, while patients in the third hospital constituted the hold-out external test cohort. The XGB model was the best-performing machine learning model, outperforming 2 existing ward-focused models in terms of discrimination (C statistic: XGB, 0.86; ward-focused models, 0.82 [P < .001] and 0.70 [P < .001]) and the number needed to alert (at an example 80% sensitivity: XGB, 6 ward-focused models: 9 and 11). The deep learning models did not exhibit improved performance. The XGB model performed better or equivalent to models trained for a specific hospital unit.
Conclusions And Relevance:
This retrospective cohort study describes the development of a novel hospitalwide model for continuously predicting the risk of critical events through the entirety of a child's stay. The model facilitated a unified framework for risk assessment in a pediatric hospital.
