Related Experiment Videos
Novel computer-based assessment of asthma strategies in inner-city children
J T Jaing1, J A Sepulveda, A M Casillas
1Department of Pediatrics, UCLA School of Medicine, Los Angeles, California 90095-1680, USA.
Insights
Artificial neural networks (ANNs) can effectively analyze and categorize different childhood asthma management strategies. This technology aids in understanding and automating the evaluation of how children manage their asthma.
Area of Science:
- Pediatric Respiratory Medicine
- Artificial Intelligence in Healthcare
- Computational Biology
Background:
- Childhood asthma is a significant and growing public health concern in the U.S., impacting millions of children.
- There has been a concerning rise in asthma-related mortality rates among children aged 5-14.
- Effective management strategies are crucial for improving outcomes in pediatric asthma patients.
Purpose of the Study:
- To assess the utility of artificial neural networks (ANNs) for evaluating problem-based asthma management approaches in children.
- To develop a computational model for analyzing and classifying diverse asthma management behaviors.
- To explore the potential of ANNs in standardizing the assessment of pediatric asthma care.
Main Methods:
- Recruited children with mild-to-moderate persistent asthma from an inner-city clinic.
- Participants managed 10 simulated asthma-related problems, with decisions recorded in a database.
- Trained an artificial neural network (ANN) on this database to cluster and analyze management performances.
Main Results:
- Analyzed 305 distinct asthma management performances using the trained ANN.
- Identified five distinct clusters representing varied strategies for acute asthma case management.
- Graphical evaluation of ANN outputs provided insights into behavioral patterns.
Conclusions:
- Artificial neural networks (ANNs) demonstrate capability in modeling complex behaviors and solving classification problems with hidden patterns.
- ANNs can automate the evaluation of asthma management strategies, offering a novel approach to clinical assessment.
- This pilot study highlights the potential of ANNs to enhance our understanding of pediatric asthma self-management.
Background:
Childhood asthma continues to be a growing medical concern in the United States, affecting > 17 million children in 1998. The mortality rate from asthma in children aged 5 to 14 years has nearly doubled, from 1.7 deaths per million to 3.2 deaths per million between 1980 and 1993.
Objective:
To evaluate the use of artificial neural networks (ANNs) to rate problem-based strategies for asthma management in a defined population of children.
Methods:
The participants in our study were recruited from a local inner-city medical facility in Los Angeles. The majority of participants had received the diagnosis of mild-to-moderate-persistent asthma. Each participant was given 10 asthma-based problems and asked to manage them. Each management decision and its order were entered into a database. This database was used to train an artificial neural network (ANN). The trained ANN was then used to cluster the various performances, and outputs were evaluated graphically.
Results:
Three hundred five performances were analyzed through our trained neural network. Our ANN classified five major clusters representing different approaches to solving an acute asthma case.
Conclusions:
ANNs can build rich models of complex phenomena through a training and pattern-recognition process. Such networks can solve classification problems with ill-defined categories in which the patterns are deeply hidden within the data, and models of behavior are not well defined. In our pilot study, we have shown that ANNs can be useful in automating evaluation and improving our understanding of how children manage their asthma.