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 that blocks airflow from the lungs.
It affects around 1.2 million people in the UK and costs the NHS an estimated £1.9 million a year, largely due to flare-ups of symptoms.
READ MORE: How Edinburgh became a world leader in artificial intelligence
The study by a team from NHS Greater Glasgow and Clyde will apply a form of artificial intelligence (AI) known as machine learning to data stored on secure electronic devices. health records.
The goal is to identify patients at higher risk of adverse events early so that they can be reviewed by experts on the COPD team, which could allow for proactive interventions that reduce the likelihood of ending up in hospital.
Dr Chris Carlin, a respiratory disease physician leading the project, said: “This is an incredibly exciting project.
“This is the first time we have gathered AI predictive information for COPD in real clinical practice.
“With the aging of the population and the increasing prevalence and complexity of long-term conditions, clinicians are overwhelmed with data that they don’t have the ability to review.
“We need to implement assistive technologies to give us priority insights from patient data.
“These have the potential to give us back time to focus on human patient-physician interactions, and allow us to optimize preventative management to improve patient outcomes and quality of life rather than continue to grapple with unsustainable unscheduled reactive care. ”.
The AI study builds on an earlier collaboration between Lenus Health, NHSGGC and the West of Scotland Innovation Hub, which uses digital technology to enable COPD to manage their condition and receive support from doctors from home.
READ MORE: Diagnoses of tuberculosis and pneumonia could be accelerated with the help of AI
Paul McGinness, CEO of Lenus Health, said: “This trial is the culmination of many years of work spanning model training, developing the technical infrastructure to automate the production of model scores, and establishing processes and features of explainability with the clinical team to act on the knowledge provided.
“We are confident that the introduction of AI-generated insights-based clinical decision support is the intervention that can truly transform the management of chronic conditions such as COPD by enabling optimization of prioritized care and better proactive support for self-management.”
It comes just days after the University of Dundee announced that its scientists will play a leading role in a European project exploring whether AI can improve outcomes for patients with high blood pressure.
Arterial hypertension (AHT) affects 40-50 percent of the population over 40 years of age and is the leading 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 worldwide could be attributed to hypertension.
Despite the existence of effective pharmacological treatments, it continues to be a poorly controlled pathology.
This is largely due to the difficulty of identifying the different forms of hypertension with the right medication, which means that there is often a delay in finding the right treatment for each patient.
Now a six-year, €8 million (£7 million) project by the EU HORIZON consortium aims to speed up diagnosis by using machine learning to identify key biomarkers in blood and urine.
The University of Dundee is an associate partner of the consortium.
READ MORE: Why artificial intelligence will be key to the NHS workforce and the challenges of waiting times
Dr Christian Cole, from the university’s School of Medicine’s Health Informatics Center (HIC), said: “High blood pressure is uncontrolled or poorly controlled in more than half of patients.
“When such a large 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, 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 if it is truly effective in ensuring that patients receive the most appropriate treatment for them.”