People who suffer from loneliness, insomnia, or mental health issues such as depression and anxiety may face a 35% higher risk of developing type 2 diabetes, according to a new study. Researchers from Anglia Ruskin University (ARU) analysed data from nearly 20,000 adults over 17 years, using artificial intelligence to model disease progression.
The study, published in Frontiers in Digital Health, found that when all three factors were combined, the estimated risk increased by 78 percentage points. The link is thought to be due to chronic stress, which can cause inflammation, disrupt blood sugar regulation, and lead to overproduction of the stress hormone cortisol.
Behavioural and psychological factors are often overlooked in diabetes risk prediction, which typically relies on BMI, age, and blood pressure. The researchers argue that including these factors could provide meaningful signals for early intervention. They also noted that people experiencing loneliness, insomnia, or mental health problems were more likely to consume salty, sugary cereals and processed meats, further increasing risk.
Dr Mahreen Kiran, lead author and postgraduate researcher at ARU, said: “This study shows the importance of including behavioural and psychosocial variables such as loneliness, sleep disruption and mental health history within health datasets used for risk prediction. These factors are often overlooked, yet they provide meaningful signals about future disease risk.”
Professor Barbara Pierscionek, deputy dean at ARU, added: “Type 2 diabetes is a rising global health concern which we know is heavily influenced by lifestyle. However, current risk prediction models over-simplify this disease and overlook the more complex interconnected behavioural and emotional factors.”
An estimated 4.6 million people in the UK have a diabetes diagnosis, with up to 1.3 million more potentially living with undiagnosed type 2 diabetes. The study used a digital twin model to simulate disease progression and test interventions, which the researchers say could offer a cost-effective way to improve diagnosis and treatment.
