Scientists used iPhones to record the cough sounds of 585 subjects aged 12 and under in clinical environments. The automated system — which had previously been trained on the coughs of 852 patients in the same age range — then analyzed the coughs in tandem with medical history, demographic data and up to five patient- or parent-reported symptoms to produce a diagnosis.
When compared with the findings of a panel of pediatricians, the artificial intelligence system diagnosed asthma with 97 percent sensitivity and pneumonia with 87 percent sensitivity, which is higher than that of the World Health Organization’s pneumonia diagnosing guidelines. It also achieved diagnostic sensitivity in the mid-80 percent range for croup, bronchiolitis and lower respiratory tract disease.
In an accompanying blog post, study author Paul Porter, MD, a pediatrician at Joondalup Health Campus and Princess Margaret Hospitals in Australia, wrote that the tool could be used in telehealth consultations to benefit low-income countries and other areas with limited access to healthcare. The researchers are now expanding the technology to include adult respiratory diseases and differentiate between levels of disease severity.
More articles about AI:
Researchers training AI mobile app to detect early signs of oral cancer
Novant Health opens Institute of Innovation & AI
8 new hospital applications for machine learning: AWS Textract, an algorithm predicting ICU outcomes & more
At the Becker's 11th Annual IT + Revenue Cycle Conference: The Future of AI & Digital Health, taking place September 14–17 in Chicago, healthcare executives and digital leaders from across the country will come together to explore how AI, interoperability, cybersecurity, and revenue cycle innovation are transforming care delivery, strengthening financial performance, and driving the next era of digital health. Apply for complimentary registration now.