People with common problems ‘have 35pc higher diabetes risk’

Those experiencing loneliness, sleep difficulties and mental health conditions, including depression and anxiety, could face an elevated risk of developing type 2 diabetes, research indicates. The connection may be attributed to the body’s reaction to chronic stress, scientists suggest.

Behavioural and psychological elements are “often overlooked” in disease risk prediction, experts noted, yet could “provide meaningful signals”. The research, spearheaded by scientists at Anglia Ruskin University (ARU), examined lifestyle and health information from 19,774 adults featured in the UK Biobank and monitored for up to 17 years.

Researchers employed artificial intelligence (AI) to forecast and model the progression of type 2 diabetes utilising behaviour, diet and psychological elements. The research determined that loneliness, insomnia and poor mental health were calculated to raise diabetes risk by 35 percentage points each.

When all three elements were combined, the calculated risk reached 78 percentage points. The research suggests psychological elements “likely reflect” well-documented reactions to chronic stress, including inflammation, difficulty maintaining blood sugar levels and excessive production of the stress hormone cortisol.

These effects also “underscore” that psychosocial distress represents not merely a mental challenge, but a “potent metabolic disruptor with real and measurable health consequences”, scientists stated. A correlation was also identified between the three psychological stressors and diet.

Those affected by loneliness, insomnia and mental health struggles were found to be more prone to consuming salty, sugary cereals and processed meats, all of which can significantly raise the risk of developing type 2 diabetes.

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.”

Some 4.6 million people in the UK currently carry a diabetes diagnosis, though estimates indicate that a further 1.3 million may be living with undetected type 2 diabetes.

Professor Barbara Pierscionek, deputy dean for research and innovation in the Faculty of Health, Medicine and Social Care at ARU, said: “Type 2 diabetes is a rising global health concern which we know is heavily influenced by lifestyle. However, current risk prediction models rely on BMI, age and blood pressure, which over-simplify this disease and overlook the more complex interconnected behavioural and emotional factors that precede and shape the onset of the condition.”

The research, published in Frontiers in Digital Health, employed a digital twin model, which harnesses artificial intelligence to replicate a patient’s health profile and simulate the advancement of disease, as well as gauge how effective potential interventions might prove to be.

Prof Pierscionek added: “Digital twin model systems replicate an individual’s health profiles, enabling us to test ‘what-if’ scenarios and tailor care to individual needs.

“However, most of these existing models rely on real-time data from wearable devices, which can be a barrier for settings lacking in technical infrastructure or underserved communities that struggle with costs.

“Digital twin model systems present a viable cost-effective way of diagnosis, testing and treatment for a number of conditions.”