Analysis of urine samples using artificial intelligence (AI) can predict when patients with chronic lung disease are likely to have a flare-up seven days before symptoms appear, study finds. symptoms.

The technology could help personalize treatment and prevent hospitalizations, academics say.

The research involved patients carrying out a simple urine dipstick test – similar to a lateral flow test – daily and sharing the results with experts using their mobile phones.

For the study, researchers analyzed urine samples from 55 patients with chronic obstructive pulmonary disease (COPD) to determine how molecules change when symptoms worsen.

COPD is a term used to refer to a group of lung conditions causing difficulty breathing such as emphysema and chronic bronchitis.

Symptoms may include shortness of breath, wheezing, and persistent coughing.

Flares, also called exacerbations, occur when symptoms suddenly get worse and are more common in winter.

Professor Chris Brightling, from the University of Leicester, who led the study, said: “COPD exacerbations occur when a person with COPD becomes very ill and needs additional treatment at home or at the hospital.

“Current treatments respond to serious illness. It would be better to be able to predict an attack before it happens and then personalize treatment to either prevent the attack or reduce its impact.

“We wanted to develop a predictive test that would act as a personal weather forecast of an impending surge.”

After identifying the changing molecules, the researchers developed a test to measure the levels of five different biomarkers in urine.

Some 105 COPD patients then tested their urine every day for six months with the dipstick test and shared their results with researchers.

The 85 results were analyzed using an artificial neural network (ANN), which is a type of algorithm that uses an artificial neural network to process data in a way that mimics the human brain.

The study, published in ERJ Open Research, found that the AI ​​model could accurately predict a flare-up up to seven days before symptoms began.

The researchers acknowledged that the study had a number of limitations, including the small sample size.

Professor Brightling added: “The advantage of urine collection is that it is relatively quick and easy for patients to do at home daily.

“We need to do more work to refine the AI ​​algorithm with data from a larger group of patients.

“We hope this will allow us to create AI tests for COPD patients that will learn what is ‘normal’ for each person and predict a flare-up of symptoms.

“Patients’ care might then be tailored, for example they might need additional tests or treatments, or they might be able to limit their exposure to triggers like pollution or pollen.”

Reacting to the study, Dr Erika Kennington, head of research and innovation at the charity Asthma + Lung UK, said: “This rapid, non-invasive test shows how our urine could be used as a warning against a deterioration in lung health.

“Allowing people with chronic obstructive pulmonary disease to take steps to manage their condition before it gets worse could really help people stay healthy and avoid being hospitalized.”

“However, this compelling research would then need to be tested in a much larger group of people with COPD and analyzed for cost-effectiveness, before it can be used in a healthcare setting. »