A new artificial intelligence tool that accurately predicts the need for a feeding tube could transform patient care and improve quality of life for people living with motor neurone disease (MND).
The new tool, developed by a team at the University of Sheffield, will improve patient care by providing doctors and patients with the critical information to plan life-prolonging intervention at the ideal time.
MND – also known as Amyotrophic Lateral Sclerosis (ALS) – is a devastating, progressive and fatal condition that attacks the nerve cells that control muscles. As the disease progresses, many patients find it difficult to swallow, leading to dangerous weight loss and malnutrition. A gastrostomy is a procedure to place a feeding tube directly into the stomach, which is vital for maintaining nutrition, quality of life, and even survival.
However, time is of the essence. If the procedure is done too early, it can have a negative impact on quality of life. If done too late, it carries greater risks and may be less effective because patients can enter a “refractory” stage of malnutrition. The process may even become impossible due to weakened respiratory muscles.
Researchers from across Europe, led by Professor Johnathan Cooper-Knock at the University of Sheffield’s Institute for Translational Neuroscience (SITraN), have created a sophisticated machine learning (AI) model to tackle the challenge of MND’s unpredictable progression. The model uses routine measurements collected at the time of diagnosis to estimate how quickly the disease will progress in each individual patient, thereby allowing clinicians to determine the optimal time for critical intervention.
“One of the hardest aspects of living with MND is the uncertainty, it’s a cruel and devastating disease.” said Professor Johnathan Cooper-Knock from the University of Sheffield.
“Until now it has been impossible for clinicians to predict when someone living with MND might need a feeding tube – it can be anywhere from eight months after diagnosis to 20 years.
“By identifying the optimal window for a gastrostomy within three months, doctors and patients can better plan surgery, and we can help ensure the best possible quality of life and potentially prolong survival.”
Researchers used data from more than 20,000 MND patients to develop the AI model to predict when significant weight loss will occur – a key indicator that a feeding tube is needed. The new tool was able to predict the optimal window within a median error of just 3.7 months at the time of diagnosis. For patients reassessed six months after diagnosis, the model’s accuracy improved further, with a median error of just 2.6 months.
Professor Johnathan Cooper-Knock added: “It’s not just about a surgical procedure, it’s about preserving the patient’s dignity and ability to maintain their diet safely. For a clinician, knowing this critical window allows us to move from reacting to disease progression to proactively managing it, providing optimal patient care and avoiding rushing the patient when they are already struggling. frail.”
“Ultimately, this tool ensures patients get the right care at the right time, maximizing the quality of every day.”
The promising results of the study, published in the journal eBioMedicine, mean the researchers are now planning a prospective clinical trial to formally validate the tool before it becomes a standard part of MND care.
