A smartphone app that uses artificial intelligence (AI) to analyse coughs could diagnose if your child has asthma, according to a study published today.
ResApp has been demonstrated in a study conducted by researchers at Curtin University and The University of Queensland, Australia.
The results published in Respiratory Research show that the app is 97% accurate in diagnosing asthma and correctly ruled out asthma with 91% accuracy.
“It can be difficult to differentiate between respiratory disorders in children, even for experienced doctors,” says Dr Paul Porter, a corresponding author of the study. “This study demonstrates how new technology, mathematical concepts, machine learning and clinical medicine can be successfully combined to produce completely new diagnostic tests utilising the expertise of several disciplines.”
The app uses machine learning technology similar to existing speech recognition software, which was then trained to recognise the auditory characteristics present in coughs of five different respiratory diseases. Users select their child’s symptoms (fever, wheezing etc), record them coughing using the app and check the results.
The accuracy of the app’s diagnosis was compared to that of a panel of paediatricians, who had reviewed results of imaging, laboratory findings, hospital charts and conducted all available clinical investigations. When compared to the paediatricians’ diagnoses, ResApp showed a high accuracy (between 81% and 97%) in diagnosing asthma, croup, pneumonia, lower respiratory tract disease and bronchiolitis. Previous studies with adults have shown similar positive results, where the app’s diagnosis was more than 86% accurate.
Asthma app: Helping telehealth, hospitals and clinics
Providing an accurate diagnosis without a clinical examination is a major limiting feature of existing telehealth consultations, so use of the app to diagnose respiratory disorders could enable clinical services to begin targeted treatments sooner.
“As the tool does not rely on clinical investigations, it can be used by healthcare providers of all levels of training and expertise,” Porter adds. “However, we would advise that where possible the tool should be used in conjunction with a clinician to maximise the clinical accuracy.”
ResApp could also aid diagnoses in emergency room or general consultations, due to its fast, accurate and – most importantly for those countries where you have to pay for healthcare – low-costing results. For example, using the app as a diagnostic tool for pneumonia will cost significantly less than an x-ray and follow up consultation, and provides results quicker than x-ray; leading to faster treatment.
Big data insights
With the users’ permission, ResApp can collect data anonymously. Globally, hundreds of millions of people use smartphones capable of running the app.
Collecting this data would essentially be an ongoing clinical trial across the world, providing researchers with a new level of insight into respiratory conditions, and the effectiveness of treatment options. User’s data would also be added to the database used by the app, improving its performance and accuracy over time.