| Wheezing in preschool children is a common condition that has seen a rise in prevalence over the past decade. |
| Affecting up to one-third of preschoolers, recurrent wheezing significantly impacts both quality of life and healthcare resources. |
| Recent advancements in Artificial Intelligence (AI) and Machine Learning (ML) are offering promising solutions to enhance diagnosis, monitoring, and treatment of wheezing and its progression to asthma. |
| This article explores the latest AI applications in pediatric wheezing management, emphasizing their potential benefits for doctors and healthcare systems. |
| AI Revolutionizing Wheezing Diagnosis and Monitoring |
| Preschool wheezing, often triggered by viral infections, affects 30–50% of children, with one in three experiencing recurrent episodes. These episodes increase asthma risk and place a significant economic burden, costing the European Union EUR 5.2 billion annually. |
| AI Tools for Wheezing Management: |
| Traditional auscultation methods lack standardization, but AI has introduced innovative solutions: |
| StethoMe |
|
|
| Detects pathological lung sounds, including wheezing, across age groups. |
|
|
|
|
| Provides remote monitoring for improved self-management. |
|
|
|
|
| |
| StethAid® |
|
|
| Uses deep learning to recognize wheezing sounds with 84% accuracy. |
|
|
|
|
| Enhances diagnostic accuracy at home or in clinics. |
|
|
|
|
| These AI-powered tools empower both doctors and parents to monitor lung health effectively, reducing healthcare visits and improving outcomes. |
| AI in Asthma Prediction: Moving Beyond Wheezing Recognition |
| Predicting asthma in children who experience wheezing has always been challenging, as many wheezing episodes are transient and may not indicate asthma. However, AI and ML models are now being employed to predict the long-term risk of asthma development based on early-life wheezing patterns and associated risk factors. |
| ML algorithms, such as artificial neural networks (ANNs) |
 |
Analyze a range of factors, including parental asthma history, allergic sensitization, and environmental exposures. |
|
Predict asthma onset with better sensitivity and specificity than traditional methods. For instance, the CHILDhood Asthma Risk Tool (CHART) has shown promise in identifying preschool children at high risk for persistent wheezing and asthma development, enabling earlier interventions. |
|
Demonstrate an impressive accuracy of 95.54%. |
| Telemonitoring and Telemanagement: A New Era in Wheezing Care |
| The COVID-19 pandemic has underscored the need for remote care. AI-powered devices and apps are revolutionizing wheezing management by enabling at-home monitoring and reducing hospital visits: |
|
| WheezeScan® Detector: |
|
|
| Helps parents monitor their child’s respiratory symptoms at home, sharing data remotely with healthcare providers for better-informed decisions. |
|
|
|
|
| |
| ResAppDx®: |
|
|
| A smartphone app that analyzes cough sounds, offering diagnostic support and real-time symptom tracking for wheezing and asthma-related issues. |
|
|
|
|
| Conclusion |
| AI is transforming pediatric wheezing care with tools like smart stethoscopes and apps. These innovations improve outcomes, personalize care, and reduce healthcare burdens. Pediatricians can leverage AI to enhance patient care and quality of life. |
|
