- Scientists have developed an AI tool to help mental health professionals personalise treatments for patients with depression
- The new tool could improve outcomes for thousands of patients each year
- A three-year clinical trial conducted in England was the first to demonstrate the benefit of using AI in mental health services
AI can help NHS professionals provide quicker and more personalised treatments for depression and improve outcomes for patients, according to new research.
An international team of scientists, led by the University of Sheffield, has developed a new AI tool that helps mental health professionals personalise treatments for patients with depression.
Within the NHS in England, current practices for treating depression frequently involve a trial and error method. Patients are usually first offered a low intensity or brief form of treatment and then those who remain unwell are then offered a more intensive, long-running treatment.
It is hoped the implementation of this tool could see patients getting more tailored care to treat their depression much quicker.
Dr Jaime Delgadillo, lead investigator from the University of Sheffield - UK, said: "Depression is one of the most common and disabling mental health problems and is said to affect around 280 million people worldwide. One of the biggest challenges healthcare professionals face is deciding which treatment will work for each individual patient out of several psychological and pharmaceutical treatments.
"If we are able to offer the right treatment to the right patient at the right time, treatment outcomes could be improved for thousands of patients each year without a need to develop any new interventions."
Following a three-year clinical trial, the findings published in JAMA Psychiatry showed the tool led to significant improvements in patient outcomes, making this the first trial to demonstrate the benefit of AI in mental health services.
The tool was developed by analysing data from over 1,000 patients previously treated in psychological services, to identify which treatments are most beneficial for patients with specific symptoms and personality traits.
The research was conducted by scientists at the University of Sheffield in the UK, Western University Canada, University of California Los Angeles and University of Pennsylvania in the USA.
The effectiveness of the new tool was assessed in the first clinical trial of its kind, which involved over 900 NHS patients in Lancashire, Rotherham and Doncaster.
Dr Shehzad Ali, Professor of Public Health Economics at Western University's Schulich School of Medicine & Dentistry - Canada, said: "Our economic analysis shows that this new method of treatment selection improves the effectiveness of currently available treatments, with just a small and affordable increase in overall treatment costs, since it appropriately fast-tracks more patients to intensive treatments."
