Asthma is a common chronic respiratory condition that affects between 10-12% of children and can cause significant health issues. Early detection and management of asthma exacerbations are crucial in preventing hospitalizations and improving patient outcomes. In a recent study published […]
Asthma is a common chronic respiratory condition that affects between 10-12% of children and can cause significant health issues. Early detection and management of asthma exacerbations are crucial in preventing hospitalizations and improving patient outcomes.
In a recent study published in the Annals of Family Medicine, researchers explored the use of artificial intelligence (AI)-supported stethoscopy for remote monitoring of asthma exacerbations in both adults and children.
Asthma is characterized by chronic inflammation of the airways and is accompanied by respiratory symptoms such as coughing, chest tightness, wheezing, and shortness of breath. Asthma exacerbations refer to the worsening of lung function and symptoms compared to a patient’s usual condition.
There are various tests available for monitoring asthma exacerbations, such as peak expiratory flow (PEF) measurements. However, these tests are not suitable for children under the age of five. Given the high prevalence of asthma in children, it is important to provide all patients with the necessary tools to identify exacerbations.
In this six-month observational study, 149 asthma patients, including 90 children, participated in self-monitoring using three devices: the AI-supported stethoscope called StethoMe, a PEF meter, and a device for measuring peripheral capillary oxygen saturation (SpO2). All study participants also completed a health questionnaire evaluated by physicians.
A machine learning (ML) model was created for each parameter, and the area under the receiver operating characteristic curve (AUC) was calculated to assess the usefulness of each parameter in detecting exacerbations.
For children under the age of five, relying solely on subjective assessments from parents is not sufficient to confirm or exclude asthma exacerbations. Using individual parameters such as respiratory rate (RR), heart rate (HR), SpO2, PEF, and the ratio of inhalation to exhalation (I/E) can be misleading. However, continuous auscultatory sounds may be more effective when limited to a single parameter. Nevertheless, incorporating multiple parameters yielded the best approach for children.
For all age groups, combining data from all three devices provided the most accurate indication of asthma exacerbation. However, the data generated by the AI-supported stethoscope proved to be equally effective, particularly for children, including those under the age of five.
The AI-supported stethoscope has the potential to significantly improve patient-doctor collaboration through telemedicine solutions. Telemedicine programs are rapidly developing and cost-effective, as medical data can be electronically transmitted and analyzed using AI algorithms.
The findings of this research highlight the utility of AI-supported stethoscopes in remotely detecting asthma exacerbations by assessing wheezing, HR, RR, and abnormalities in breath sounds. This is especially relevant for younger children, where parental assessments may be unreliable. StethoMe is a valuable device that facilitates asthma monitoring.
It is important to note that the study’s strength lies in the use of a large volume of data from certified medical devices, suggesting high reliability and superiority compared to short-term laboratory studies with limited participants.
However, there are limitations regarding the reference standard used for the parameters. As there are no well-established parameters and reference values, the standards used in this study are based on subjective decisions by individual physicians. Additionally, the study only included Slovenian patients and, therefore, lacks ethnic diversity.
Reference: Emeryk, A., Derom, E., Janeczek, K., et al. (2023) Home Monitoring of Asthma Exacerbations in Children and Adults With Use of an AI-Aided Stethoscope. The Annals of Family Medicine 21(6);517-525. doi:10.1370/afm.3039