A new study has found that artificial intelligence (AI) can predict when patients with chronic lung disease are likely to suddenly worsen seven days before symptoms appear by analyzing urine samples.
According to experts, this technology could help tailor patient treatment and prevent hospital admissions.
In the study, patients performed a simple dipstick test on their urine daily (similar to a lateral flow test) and shared the results with experts using their mobile phones.
For the study, scientists examined urine samples from 55 patients with chronic obstructive pulmonary disease (COPD) to determine how molecules change when symptoms worsen.
About 105 COPD patients then tested their urine every day for six months with a dipstick test and shared their results with the researchers.
The results of the 85 were analyzed using an artificial neural network (ANN), a type of algorithm that uses a network of artificial neurons to process data in a way that the human brain does.
COPD is a term used for a variety of lung conditions that cause difficulty breathing (such as emphysema and chronic bronchitis).
Symptoms can include shortness of breath, wheezing when breathing, and a persistent chesty cough.
The disease is often exacerbated when symptoms suddenly get worse, and this is common in the middle of winter.
“A COPD exacerbation is when someone with COPD becomes very ill and needs additional treatment at home or in hospital,” said Chris Brightling, a professor at the University of Leicester and lead researcher on the study.
