Wheeze-Counting Wearable Device Monitors Patient's Breathing In Real Time

Traditionally, medical professionals diagnose these conditions by listening to a patient's breathing using a stethoscope to detect abnormal sounds like wheezing or crackling, which are common indicators of many lung and respiratory diseases. This diagnostic method demands significant expertise, and misinterpreting these sounds can result in incorrect diagnoses. Researchers have now developed an artificial intelligence (AI) algorithm that continually monitors a patient’s breathing and issues early medical alerts for potential asthma attacks or other respiratory issues.

Developed by a team at the University of Texas at Dallas (Richardson, TX, USA), this algorithm monitors a patient’s breathing in real time and analyzes the frequency of wheezes. This enhances the monitoring of lung sounds for symptom prevention, early detection of respiratory diseases, and symptom alleviation. The research team trained their deep-learning model using a dataset comprising 535 respiration cycles from various patient data sources to identify breathing patterns indicative of asthmatic symptoms. This innovative wheeze counter is poised to transform the approach to predicting lung diseases based on long-term breathing patterns.

The challenge in a clinical setting is continuously monitoring the pattern and frequency of abnormal lung sounds over extended periods, which is currently impractical. The algorithm developed addresses this by not only identifying abnormal sounds in each breath but also by capturing a comprehensive set of data that includes atypical breathing patterns. The next step for the researchers is to integrate this technology into a wearable device, allowing for its use in both clinical and non-clinical settings to facilitate on-the-go detection and remote medical interventions. Going forward, the team aims to combine real-time air pollution readings with real-time breathing sound analysis into a single wearable device to offer continuous monitoring of respiratory health.

“We developed the deep-learning algorithm to detect automatically whether someone’s breathing is problematic. When someone is wheezing, the algorithm will count the number of incidences and analyze their timing,” said Dr. Dohyeong Kim, a University of Texas at Dallas researcher. “Our wheeze-counting method is straightforward yet effective, with potential for expansion into automatic symptom monitoring. This could be crucial in predicting the onset or severity of future abnormalities, as well as detecting current symptoms.”

Related Links:
University of Texas at Dallas