Peer-reviewed article
Effect of an electronic health record-integrated machine learning asthma risk marker on pediatrician prognostic accuracy during preschool age: a pilot randomized clinical trial.
Owora AH, Jiang B, Shah Y ·
Summary
Written by AI, not yet AICS's view · claude-haiku-4-5-20251001This study tested whether a machine learning tool integrated into electronic health records could help pediatricians better predict which preschool children will develop persistent asthma by school age. Thirty-four pediatricians in Indiana evaluated patient cases with and without access to the prediction tool. Pediatricians using the machine learning tool were significantly more accurate at identifying children at risk for asthma compared to those without the tool.
Key points
- Pediatricians with access to the machine learning tool correctly classified 83% of vignettes versus 61% without access
- The improvement in accuracy was statistically significant (P = .008)
- The tool demonstrated favorable usability and feasibility for clinical practice
- Machine learning analysis used routinely collected clinical data from birth through age 3 years
- Early identification of asthma risk in preschoolers is challenging due to overlapping respiratory symptoms
Limitations
This is a pilot study with a small sample of 34 pediatricians from one US state, so results may not generalize to other regions or healthcare systems. The study used standardized vignettes rather than real clinical encounters, which may not reflect actual decision-making in practice.
Abstract
Early identification of children at risk for persistent asthma is challenging because preschool respiratory symptoms are heterogeneous and often overlap with transient wheezing illnesses. Machine learning-based prediction models may improve risk stratification, but few have been integrated into electronic health record (EHR) systems or evaluated for their effect on clinician decision-making. We evaluated whether access to an EHR-integrated machine learning-based Passive Digital Marker (PDM) improved pediatrician prognostic accuracy for school-age asthma and assessed the tool's usability, acceptability, and feasibility. In this pilot randomized clinical trial, practicing pediatricians in Indiana were randomized using a Solomon 4-group design with pretest and posttest assessments. Pediatricians evaluated 10 standardized pediatric patient vignettes derived from longitudinal EHR data from birth through age 3 years. Children with documented asthma diagnoses between ages 6 and 11 years were classified as cases. The PDM classified children as high or low risk for persistent school-age asthma using routinely collected clinical data. The primary outcome was clinician prognostic accuracy, defined as the proportion of correctly classified vignettes;secondary outcomes included usability, acceptability, and feasibility. Thirty-four pediatricians participated, and all completed study procedures. Clinicians with access to the PDM demonstrated higher prognostic accuracy than clinicians without access (mean [95% CI] 0.83 [0.69-0.97] vs 0.61 [0.52-0.70]; P = .008). In a mixed-effects model accounting for clustering of vignette assessments within clinicians, a significant interaction between PDM access and assessment timing was observed (b = 0.10; 95% CI 0.01-0.18; P = .02), indicating improved prognostic accuracy during posttest assessments when clinicians used the PDM. In this pilot randomized clinical trial, an EHR-integrated machine learning-based asthma risk marker improved pediatrician prognostic accuracy and demonstrated favorable usability and feasibility. These findings support further evaluation of machine learning-enabled clinical decision support tools to improve early identification of children at risk for persistent asthma.Trial registration: ClinicalTrials.gov Identifier: NCT05826561; registered April 12, 2023.
Findings the Hub has extracted
Each claim below is labelled by its type of design and links back to this report.
- Intervention
- Electronic health record-integrated machine learning-based Passive Digital Marker (PDM) that classifies children as high or low risk for persistent school-age asthma using routinely collected clinical data
- Population
- 34 practicing pediatricians in Indiana evaluating 10 standardized patient vignettes; children aged birth to 3 years with follow-up to ages 6-11 years
Key finding
Clinicians with PDM access achieved 83% prognostic accuracy versus 61% without access (P = .008)