Why personalised support holds the key to diabetes prevention

“We are what we eat… but perhaps we don’t realise it,” says John Grumitt of DigitalHealth.London Accelerator company Changing Health, in this blog post published as part of Diabetes Prevention week.

That much was made clear in February, when a new report from the Office National Statistics revealed the average Briton consumes an alarming 50% more calories than we think each day. The report found that men are more likely to underestimate their calorie intake, and the higher that intake is, the less accurate our estimates are.

There are psychological factors in play. When we recount what we’ve eaten recently, we’re often prone to confirmation bias. In other words, we subconsciously allow for some flexibility with the truth to support a view we wish to be true (“I’m eating well”), suggesting a limited understanding of how our lifestyles are impacting on our health.

Take, for example, Special K: it’s often considered one of the healthiest breakfast choices for a daily routine. But it’s high in sugar (17%) and low in fibre (1.1g), so that isn’t the case. If we can’t reliably understand and keep track of our diet, and instead see the world only the way we want it to be, we’re unlikely to recognise when we need to make a change.

Data from a sample of 215 Changing Health app users indicates people are selective in the diet choices they keep track of. The app allows users to keep a photo food diary and identify whether their meal was “green” or “red” – healthy, or not. Over 8 weeks, 60% of service users log their healthy choices on more weeks than they log their unhealthy choices.

A 2016 report from the Behavioural Insights Team, or “nudge unit”, pointed out that we under-report our energy intake at a national level too. Official statistics show a large decline in calorie consumption since the 1970s, which would be “equivalent to every single adult in England jogging for an hour less per day, every day, than they were in the 1970s” to account for our average weight gain. This seems implausible. Given the official statistics are largely based on surveys that require individuals and households to self-report, a more likely explanation is that we don’t understand or don’t accurately recall what we eat.

For diabetes prevention to work, we need an evidence-based, personalised approach. Our behaviour is influenced by a whole host of factors – age, ethnicity, gender, socioeconomic status, educational attainment, and existing habits are just a few of them. But data insights, like those captured by the Changing Health app, give us an opportunity to proactively identify which patients self-report their diet the least reliably, are the most likely to be influenced by social, environmental or other factors and are at the highest risk of developing diabetes.

As artificial intelligence steadily evolves, it will be possible to create personas in seconds – i.e. “Person X has a higher than average BMI for a 51 year old, believes they’re healthier on average than their peers, smokes, feels they don’t have time to exercise regularly”. Interventions can then be tailor-made to the individual, taking into account their self-awareness on diet, level of health literacy, personal traits, attitudes and values, and use clinical and behavioural biomarkers to track that person’s journey.

Technology will make it easier and more cost-efficient to reach those people most at risk of diabetes and begin prevention before it’s too late. With the condition rapidly becoming one of the most urgent public health crises of our time, the recognition that one size does not fit all can’t come a moment too soon.

Changing Health’s white paper, “Personalisation: the secret ingredient to lasting lifestyle change,” will be published on 16 May at the Primary Care and Public Health Conference, Birmingham.