Reviewed by Lexie CornerNov 20 2024
A study published in ERJ Open Research describes how researchers used artificial intelligence (AI) to analyze patient urine samples and predict when chronic obstructive pulmonary disease (COPD) symptoms would flare up.
A urine test measures levels of five biomarkers to forecast a flare-up of COPD. Image Credit: European Respiratory Society / Global Access Diagnostics
The study participants performed a simple daily urine dipstick test and submitted their results to researchers via their mobile phones.
Researchers used AI to analyze the data and predict a worsening of symptoms one week in advance. This could allow for early interventions, such as adjusting the course of treatment, to help reduce or potentially prevent a flare-up.
COPD is a serious, chronic lung disease that includes emphysema and chronic bronchitis. The World Health Organization ranks COPD as the third leading cause of death worldwide. An exacerbation occurs when symptoms, such as coughing and difficulty breathing, worsen.
Professor Chris Brightling from the University of Leicester in the United Kingdom, affiliated with the National Institute for Health and Social Care Leicester Biomedical Research Centre, led the study.
COPD exacerbations are when someone with COPD becomes very ill and needs additional treatment either at home or in hospital. The current treatments are reactive to a severe illness. It would be better if we could 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 like a personal weather forecast of an impending flare-up.
Chris Brightling, Professor, University of Leicester
The researchers began by studying urine samples from 55 individuals with COPD to identify any changes in the composition of their urine that could precede a worsening of symptoms. This led to the discovery of a set of 'biomarkers'—chemicals that change as COPD deteriorates.
Next, Global Access Diagnostics in Bedford, UK, developed a urine test to assess five of these biomarkers. The test is similar to COVID lateral flow tests. Researchers then asked 105 COPD patients from Glenfield Hospital in Leicester and Prince Philip Hospital in Llanelli, UK, to test their urine daily for six months and report the data back to the researchers via mobile phones.
The researchers used an artificial neural network to detect variations in the biomarkers and predict when a patient's COPD symptoms would flare up.
They found that this AI analysis could accurately predict a flare-up about seven days before any symptoms appeared.
Brightling added, “Our study first explored many substances in urine samples from people with COPD during a flare-up and when they were stable. We found that a small number of these substances could identify a flare up. We then followed up a group of people with COPD and tested five substances daily. This allowed us to develop the risk prediction or forecasting AI-tool. We found the AI tool could reliably predict a flare-up in symptoms seven days prior to a diagnosis.”
“The advantage of sampling urine is that it’s relatively quick and easy for patients to do at home on a daily basis. We need to do more work to refine the AI algorithm with data from a bigger group of patients. We hope this will allow us to create AI testing for COPD patients that will learn what is ‘normal’ for each person and forecast a flare-up in symptoms. Patients’ care could then be adapted; for example, they might need further testing or treatment, or they might be able to limit their exposure to triggers like pollution or pollen,” Brightling added.
COPD is a common and serious condition. There is no cure for COPD, so monitoring and treatment is crucial for helping patients stay well enough to carry out their normal day-to-day activities. When COPD symptoms flare up, it can lead to permanent deterioration, so we want to do all we can to prevent or minimize flare-ups. This research is promising because it suggests we can use AI analysis of urine samples to predict a flare-up before it starts. If it proves successful in the longer term, this testing could make sure patients get the treatment and care they need to reduce symptom flare-ups as quickly as possible.
Apostolos Bossios, Professor, Karolinska Institutet
Professor Apostolos Bossios of the Karolinska Institutet and Karolinska University Hospital in Stockholm, Sweden, is the Head of the European Respiratory Society’s airway disease assembly and did not participate in the study.
Journal Reference
Yousuf, A. J. et. al. (2024) Artificial neural network risk prediction of chronic obstructive pulmonary disease (COPD) exacerbations using urine biomarkers. ERJ Open Research. doi.org/10.1183/23120541.00797-2024