Revolutionizing asthma care: AI-powered stethoscope for home monitoring of exacerbations

A recent Annals of Family Medicine study explores the use of an artificial intelligence (AI)-aided stethoscope to monitor exacerbations of asthma in adults and children remotely. 

Study: Home Monitoring of Asthma Exacerbations in Children and Adults With Use of an AI-Aided Stethoscope. Image Credit: OMfotovideocontent / Shutterstock.com

Background

Asthma affects between 10-12% of children and generally involves chronic inflammation of the airways. This health condition is also characterized by a history of respiratory symptoms, including cough, chest tightness, wheezing, and shortness of breath. 

Exacerbations of asthma entail a deterioration of lung function and symptoms as compared to the patient’s usual status. These symptoms could lead to occasional hospitalizations and visits to the emergency department; therefore, for symptom relief and proper management, early diagnosis is crucial. 

Certain tests to monitor asthma exacerbation are available for home use, such as pulmonary function tests that measure peak expiratory flow (PEF). However, these tests are not designed to be used by children younger than five years of age. The high prevalence of asthma in children emphasizes the importance of providing all patients with access to the necessary tools to recognize worsening asthma.

About this study

StethoMe is an AI-based home stethoscope that detects pathologic auscultatory phenomena, such as wheezes and rhonchi, and transient sounds, such as coarse and fine crackles. StethoMe also effectively measures other vitals, including the respiratory rate (RR), heart rate (HR), and inspiration-to-expiration duration ratio (I/E).

In the current observational study of six months, 149 asthma patients participated, 90 of whom were children. All patients performed self-examinations using three devices, including the StethoMe, PEF meter, and peripheral capillary oxygen saturation (SpO2) meter. All study participants subsequently completed a health survey that was evaluated by physicians.

For each parameter, a machine learning (ML) model was trained. In the next stage, the area under the receiver operating characteristic curve (AUC) was calculated, which allowed the researchers to assess the utility of the specific parameter in detecting symptom exacerbation.

Key findings

For children five years of age or younger, the subjective assessment of parents was insufficient to exclude or confirm asthma exacerbation. This is similar to previous research reporting inconsistencies between the evaluations of doctors and parents.

The researchers found that using a single parameter could be misleading, as, individually, RR, HR, SpO2, PEF, and I/E are weak indicators. However, continuous auscultatory sounds could be more effective when constrained to a single parameter. Nevertheless, the incorporation of several parameters was found to be the best approach for children. 

For all groups, a combination of data provided by all three devices was the best determinant of asthma exacerbation; however, the data provided by the AI-aided stethoscope alone was equally efficient for children. This finding reflects the efficacy of StethoMe in detecting exacerbations in children, including those below five years of age. 

The AI-aided stethoscope could significantly improve patient-doctor collaboration using telemedicine solutions. Telehealth programs are developing rapidly and are cost-effective, as medical records can be electronically sent and analyzed using AI modules.

Despite these advancements, there is a lack of a definitive action plan to detect asthma exacerbation, particularly for younger children. The current study suggests that the AI-aided home stethoscope could address this gap by monitoring a comprehensive set of parameters that reflect asthma severity.

Conclusions

The study findings highlight the utility of the AI-aided stethoscope in remotely detecting asthma exacerbations like wheezes, HR, RR, and rhonchi. This is especially true for younger children for whom the assessment of parents might not be precise; therefore, StethoMe appears to be a valuable device to facilitate asthma monitoring.

A key strength of the current study is the use of large-scale data from certified medical devices, thus suggesting that the data are highly reliable and superior to laboratory studies with short-term monitoring and a small number of participants.

Importantly, a notable limitation involves the reference standard used for the parameters. Since there are no well-established parameters and reference points, the standards used in this study were based on the subjective decisions of individual physicians and experience. Additionally, the current study only included Slavic patients and, as a result, is not ethnically diverse. 

Journal 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

Posted in: Child Health News | Device / Technology News | Medical Research News | Medical Condition News

Tags: Artificial Intelligence, Asthma, Children, Chronic, Cough, Doctor, Efficacy, Heart, Heart Rate, Inflammation, Laboratory, Machine Learning, Medical Devices, Medicine, Oxygen, Research, Respiratory, Stethoscope, Telemedicine

Comments (0)

Written by

Dr. Priyom Bose

Priyom holds a Ph.D. in Plant Biology and Biotechnology from the University of Madras, India. She is an active researcher and an experienced science writer. Priyom has also co-authored several original research articles that have been published in reputed peer-reviewed journals. She is also an avid reader and an amateur photographer.

Source: Read Full Article