Related Experiment Video
Updated: Sep 6, 2025

Asthma Detection Research Based on Voice Signal Processing and Machine Learning
Published on: July 22, 2025
Evaluation of a pediatric asthma high-risk scoring algorithm
Harold J Farber1, Edwin A Silveira, Robert Moore
1Pulmonary Medicine Service, Texas Children's Hospital, 6701 Fannin St, Suite 1040.00, Houston, TX 77030.
Insights
A new asthma risk score identifies children at high risk for hospitalization and emergency department (ED) visits. This tool helps stratify risk for Medicaid-insured children with asthma, improving targeted interventions.
Area of Science:
- Pediatric Pulmonology
- Health Services Research
- Clinical Informatics
Background:
- Asthma is a leading cause of pediatric hospitalizations and emergency department (ED) visits.
- Identifying high-risk pediatric asthma patients is crucial for timely intervention and resource allocation.
Purpose of the Study:
- To develop and validate an asthma risk scoring algorithm for children insured by Medicaid.
- To assess the algorithm's ability to predict asthma-related hospitalizations and ED visits.
Main Methods:
- Retrospective analysis of health plan claims data from Texas Children's Health Plan.
- Algorithm development using parameters including prior asthma hospitalizations, ED visits, medication dispensing, provider numbers, and follow-up status.
- Risk score performance evaluated by predicting future asthma hospitalizations and ED visits.
Main Results:
- The asthma risk score demonstrated predictive performance, with Area Under the Curve (AUC) ranging from 0.72-0.79 for children aged 3-17 years and 0.65-0.69 for those aged 1-2 years.
- A risk score of 1 or greater identified 20-23% of pediatric asthma patients but accounted for 53-56% of subsequent asthma hospitalizations.
- 16-18% of children aged 3-17 years with a risk score of 9 or greater were hospitalized.
Conclusions:
- The developed asthma risk score effectively stratifies risk for hospitalization and ED visits in Medicaid-insured children.
- The risk score shows better predictive accuracy in older children (3-17 years) compared to younger children (1-2 years).
Objectives:
Identification of patients with asthma at increased risk for hospitalization and emergency department (ED) visits presents opportunity for intervention.
Study Design:
Retrospective analysis of computerized health plan claims data.
Methods:
Texas Children's Health Plan, a large Medicaid managed care program, developed an asthma risk scoring algorithm using the clinically relevant parameters of hospitalization for asthma, ED visits for asthma, short-acting β agonist medication dispensing, inhaled corticosteroid medication dispensing, number of prescribing providers, loss to follow-up, and oral corticosteroid dispensing. The risk score performance was evaluated using 2016-2018 risk scores to predict 2017-2019 asthma hospitalizations and ED visits.
Results:
We identified 107,811 unique members aged 1 to less than 18 years with an asthma diagnosis. For those aged 3 to less than 18 years, the area under the receiver operating characteristic curve (AUC) for risk score predicting hospitalization ranged from 0.72 to 0.79. For those aged 1 to less than 3 years, the AUC ranged from 0.65 to 0.69. Those with a risk score of 1 or greater accounted for 20% to 23% of pediatric members 3 to less than 18 years with asthma but 53% to 56% of asthma hospitalizations in the follow-up year. Sixteen to eighteen percent of those aged 3 to less than 18 years with a risk score of 9 or greater were hospitalized in the follow-up year.
Conclusions:
Texas Children's Health Plan asthma risk score stratifies risk of asthma hospitalization and ED visits for Medicaid-insured children. The risk score performs better for children aged 3 to less than 18 years than for those aged 1 to less than 3 years.
More Related Videos
Related Concept Videos
Asthma-IV: Diagnostic and Management
Clinical Assessment for Asthma:
This is the first step in diagnosing and managing asthma. It includes:
Asthma-II: Pathophysiology and Classification
Additionally, environmental and genetic factors play crucial roles in determining an individual's susceptibility to asthma and the severity of their condition.
Critical processes in asthma pathophysiology include:
Asthma-IV: Nursing Management
First, in...
Asthma-III: Symptoms and Complications
Classification of Asthma
Asthma: Pathogenesis and Management
Asthma is classified as allergic and non-allergic. Allergens such as dust mites, pollen, and pet dander trigger allergic asthma, while factors like cold air, intense emotions, or exercise can induce non-allergic asthma.
Asthma-I: Introduction

