The year-long trial is the first of its kind in the world for patients suffering from Chronic Obstructive Pulmonary Disease (COPD), a chronic inflammatory condition which blocks airflow from the lungs.
It affects around 1.2 million people in the UK and costs the NHS an estimated £1.9 billion a year, largely due to flare ups in symptoms.
The study by a team at NHS Greater Glasgow and Clyde will apply a form of artificial intelligence (AI) known as machine-learning to data stored in secure electronic health records.
The goal is to identify patients at highest risk of adverse events early so that they can be brought in for a review by experts from the COPD team, potentially enabling proactive interventions that reduce their likelihood of ending up in hospital.
Dr Chris Carlin, consultant respiratory physician who is leading the project, said: “This is an incredibly exciting project.
"It’s the first time we’re bringing together predictive AI insight for COPD into live clinical practice.
“With the ageing population and rising prevalence and complexity of long-term conditions, clinicians are overwhelmed with data that they don’t have the capacity to review.
"We need to deploy assistive technologies to provide us with prioritised insights from patient data.
“These have the potential to give us back time to focus on patient-clinician human interactions, and allow us to optimise preventative management to improve patient outcomes and quality of life rather than continue to firefight with unsustainable reactive unscheduled care.”
The AI study builds on a previous collaboration between Lenus Health, NHSGGC and the West of Scotland Innovation Hub, which uses digital technology to allow COPD to manage their condition and receive support from clinicians from home.
Paul McGinness, CEO of Lenus Health, said: “This trial is the culmination of many years’ work covering model training, developing the technical infrastructure to automate production of model scores and establishing processes and explainability features with the clinical team to act on the insights provided.
“We are confident that the introduction of clinical decision support based on AI generated insights is the intervention which can truly transform management of chronic conditions like COPD by enabling prioritised care optimisation and enhanced proactive self-management support.”
It comes just days after Dundee University announced that its scientists are to play a leading role in a Europe-wide project exploring whether AI can improve outcomes for patients with high blood pressure.
Arterial hypertension (AHT) affects 40-50 per cent of the population over the age of 40 and is the first risk factor for major health problems such as myocardial infarction, heart or kidney failure, stroke and cognitive disorders.
In 2019, it was estimated that more than 10 million deaths globally could be attributed to hypertension.
Despite the existence of effective drug treatments, it remains a poorly controlled pathology.
This is largely because of the difficulty of identifying the different forms of hypertension with the appropriate medication, meaning there is often a delay in finding the correct treatment for individual patients.
Now, a six-year, €8 million (£7m) project by the EU HORIZON consortium aims to speed up diagnosis by using machine learning to identify key biomarkers in blood and urine.
Dundee University is an associate partner to the consortium.
Dr Christian Cole, from the university’s School of Medicine Health Informatics Centre (HIC), said: “Arterial hypertension is not controlled or is poorly controlled in more than half of patients.
"When such a vast number of people have high blood pressure and when it is linked to so many serious health conditions, the potential for real harm is significant.
“Getting the right treatment to patients sooner would dramatically improve outcomes for them, and so by taking the HIC-developed machine learning predictor and making it applicable for clinical settings using HIC’s secure infrastructure, we hope to do just that.
“Clinical trials will then test the algorithm to determine whether it is indeed effective in ensuring that patients receive the most appropriate treatment for them.”