Mayo Clinic's AI Tools Revolutionize Early Detection of Severe Asthma Risks in Children

Mayo Clinic's AI Innovation in Pediatric Asthma Care

Mayo Clinic researchers have made a significant breakthrough in the field of pediatric asthma care by developing artificial intelligence (AI) tools that can identify children at high risk for severe asthma complications. This groundbreaking study, published in the Journal of Allergy and Clinical Immunology, demonstrates that these tools can detect risks as early as age 3, potentially revolutionizing asthma management in young children 1

1

2

The Burden of Childhood Asthma

Asthma affects nearly 6 million children in the United States, making it a leading cause of school absenteeism, emergency room visits, and hospitalizations. The variability and changing nature of asthma symptoms over time have made it challenging for clinicians to identify the most vulnerable patients, a gap that Mayo Clinic's new AI tools aim to address 1

1

Source: Medical Xpress

AI-Powered Early Detection

The research team examined electronic health records of over 22,000 children born between 1997 and 2016 in southeastern Minnesota. To analyze this vast amount of data, they developed multiple AI tools utilizing machine learning and natural language processing to extract crucial information from doctors' notes 2

2

These tools captured vital information such as symptoms and family history, enabling the application of two widely used diagnostic checklists for asthma in young children: the Predetermined Asthma Criteria and the Asthma Predictive Index. Children who met the criteria on both lists were identified as a distinct subgroup at higher risk for serious complications 1

1

Revealing Asthma Risks by Age 3

The study's findings were striking. By age 3, children in the high-risk subgroup were experiencing:

1. Pneumonia more than twice as often
2. Influenza nearly three times as often
3. Higher rates of asthma attacks requiring steroids, emergency visits, or hospitalization
4. More frequent Respiratory Syncytial Virus (RSV) infections during their first three years of life 2

   2

Additionally, these children were more likely to have a family history of asthma, eczema, allergic rhinitis, or food allergies. Laboratory tests from a previous study showed signs of allergic inflammation and impaired lung function in this group .

Related Stories

AI Models Breakthrough: Predicting Sepsis Risk in Children

AI predicts ADHD in children by age 5, years before most get diagnosed

AI Tool Revolutionizes Medical Chart Review for ADHD Follow-Up Care

AI Models Predict COVID-19 Severity and Treatment for Hospitalized Patients

Implications for Precision Medicine

Dr. Young Juhn, professor of pediatrics at Mayo Clinic and senior author of the study, emphasized the significance of this research: "This study takes us a step closer to precision medicine in childhood asthma, where care shifts from reactive care for advanced severe asthma to prevention and early detection of high-risk patients" 2

2

Future Directions

The research team plans to expand their work by:

1. Testing the AI tools in broader clinical settings and more diverse populations
2. Combining the tools with biological data to refine asthma subtype definitions and early treatment approaches
3. Exploring a compound that could potentially calm overactive immune responses linked to asthma
4. Using lab-grown cell models (organoids) to develop methods for earlier detection and prevention of childhood asthma on a larger scale 1

   1

   2

   2

This innovative research, supported by a National Institutes of Health-funded R01 grant, represents a significant step forward in the management of childhood asthma and showcases the potential of AI in transforming pediatric healthcare.