AI Urine Test Predicts COPD Flares Before Symptoms Appear
Posted on 22 Nov 2024
Chronic obstructive pulmonary disease (COPD) affects over 400 million people worldwide and is expected to become the third leading cause of death by 2030. COPD is characterized by persistent symptoms, including breathlessness, cough, and wheezing, along with ongoing impairment in lung function. At times, the symptoms worsen, leading to exacerbations. These exacerbations are triggered by various factors, such as viral and bacterial infections, as well as a series of smaller disruptions that lead to the destabilization of the disease. COPD exacerbations can be detrimental as they cause further damage to the lungs, making prevention essential for improving quality of life and reducing the risk of death. Current methods of measuring inflammation in COPD typically involve blood or sputum samples taken during exacerbations, compared to stable visits occurring weeks apart. However, these approaches have not led to a widely adopted test due to limitations in sensitivity and specificity, as well as difficulties in obtaining timely samples for proper management. The challenge now is to develop near-patient tests capable of detecting and analyzing the heterogeneous inflammatory response that precedes an exacerbation. Now, researchers have applied artificial intelligence (AI) to urine samples to predict when COPD symptoms will flare up.
Global Access Diagnostics (Bedford, UK) has developed a prototype test called Headstart, a remote patient monitoring platform that measures five biomarkers in urine. Headstart is currently being tested to detect the early signs of exacerbation with enough reliability to help patients determine whether they need to seek medical attention. A study led by the University of Leicester (Leicester, UK) involved patients using this simple daily dipstick test to monitor their urine and sending the results to researchers via their mobile phones. Using AI to analyze the data, the researchers were able to predict a deterioration in symptoms up to one week in advance, providing an opportunity to adjust treatment to prevent or reduce flare-ups.
The study began by analyzing urine samples from 55 COPD patients to identify any changes in urine composition that could precede a worsening of symptoms. This led to the identification of a set of biomarkers—molecules that shift when COPD is deteriorating. The researchers then asked 105 additional COPD patients to use the Headstart device daily over six months, sending their results back to the researchers via mobile phones. AI, specifically an artificial neural network, was employed to examine fluctuations in these biomarkers and predict when a flare-up would occur. The study, published in ERJ Open Research, demonstrated that the AI analysis could predict an exacerbation approximately seven days before any symptoms appeared.
"Our study first explored many substances in urine samples from people with COPD during a flare up and when they were stable,” said Professor Chris Brightling from the University of Leicester. “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.”
