find a balance between scope, practicality, and affordability, and must navigate a biological maze of unforeseeable dead ends. It should come as no surprise, therefore, that research into the root causes of diabetes is consistently slow. This is not to minimise the incredible work of thousands of researchers around the world who are making concrete progress in untangling the complex set of disorders – it is simply to suggest that procedural limitations hamstring them. To truly make progress, we need more thoughtful research. Cancer research has experienced a revolution, demonstrating that it is possible to make progress with complicated diseases, and we need to take a similar approach to diabetes research. Limitations of research also mean that novel, practical solutions for people living with diabetes are always just out of reach. Consider the case of the elusive affordable, portable ‘artificial pancreas’. It keeps being promised, but continually requires further research before it can reach the people it could help.

The technology remains hampered by the complexity of real-time measurement and insulin delivery, leaving people with diabetes to continue to monitor their glucose levels and administer insulin manually. While we wait for radical, revolutionary leaps forward such as the artificial pancreas, we must consider other solutions to improve the lives of people with diabetes. Some might look at diabetes and consider it a ‘solved problem’: don’t people with diabetes just take insulin and go about their lives? Insulin treatments save lives, something that everybody should be grateful for, but it is not a full solution. People with diabetes are still at significantly increased risk of health problems, including mental health problems, and are hospitalised at a far higher rate than the general population. Those with diabetes also have a shorter life expectancy, in large part due to the complications associated with diabetes. Despite this, many people remain silent, accepting that a trial and error approach to insulin treatment is the best that modern medicine has to offer. It is not. We must take a human-led approach to alleviate some of the pain and inconvenience associated with diabetes and look at how we can meaningfully improve people’s lives.

How can technology help? Technology offers us an opportunity to break free of the research gridlock and take a human-led approach to make meaningful improvements in the lives of people with diabetes in the short term. Machine learning (ML), for example, is well suited to identifying patterns and trends in vast amounts of data which human eyes might have missed. ML algorithms use large datasets of existing information and known

Despite treatment for diabetes costing less than treating the complications, there is still poor access to treatment in the first place. People are still having to fight to get access to the latest treatment, or to even see an endocrinologist.

outcomes, to ‘train’ or develop heuristics to predict outcomes.

In the case of diabetes, this could mean looking at various characteristics of a person (age, gender, diet, activity level, etc) and computing data about the insulin regimens which have been successful in the past to suggest a customised recommended dosage. Where ML excels, especially considered to current techniques, is in finding the relationship between multiple variables. For instance, the appropriate insulin schedule for a 50-year old, active woman who follows a vegan diet might be significantly different than the same woman with another diet, despite her demographic data remaining identical. Quin is using technology to pool the insights of people with diabetes through its diabetes management app. It aggregates data from people with diabetes and their existing devices, sensors and phones to take some of the guesswork out of insulin dosage. The app currently considers events already broadly known to affect blood glucose such as injections of insulin, eating and drinking, activity, and the time of day.

One benefit of an app over a formalised

study is the ease with which variables can be added in the future, such as more specific types of exercise, menstruation, travel, and stress. Each event or situation can affect a person’s blood glucose over a number of hours, so Quin classifies it and analyses its intersection with other factors. For example, instead of trying to quantify the impact of adrenaline within someone’s body, the app observes what you do and what is happening in terms of blood sugar when adrenaline levels spike. It then uses this data to form a personalised set of recommendations about what insulin dose is right for you in that scenario, and when best to take it. By running past data through smart algorithms, Quin is able to lift some of the stress that comes with remembering what has worked in the past and understanding how complex factors interact. Our research programme is currently focused on iPhone users, leveraging Apple Health, and adults using an insulin pen for multiple daily Injections therapy and a continuous glucose monitor (CGM) such as the Dexcom G5 or G6, or FreeStyle Libre. We collate the precise readings from these devices to generate an entirely new understanding of the root causes of blood glucose fluctuations, with the ultimate goal of creating a personal regimen for everybody living with insulin-treated diabetes. By leveraging a relatively mature market of CGMs and applying intelligent insights, diabetes management apps promise to reduce the amount of frustrating trial and error that people with diabetes go through. For many people with diabetes, management apps already play an important part of their daily life.

Apps offer a reliable and consistent way of tracking progress, recalling what works well for each individual and what doesn’t, which can be easily shared with medical professionals. It stops people having to try and be scientists and lets them get on with their lives.


According to a study in Frontiers in Endocrinology, people who used apps to manage their insulin intake reported a significantly higher self-care score than non-users across the areas of “blood glucose monitoring,” “general diet,” and “physical activity”.

Apps also offer a reliable and consistent way of tracking progress, recalling what works well for each individual and what doesn’t, which can be easily shared with medical professionals. It stops people having to try and be scientists, and lets them get


Page 1  |  Page 2  |  Page 3  |  Page 4  |  Page 5  |  Page 6  |  Page 7  |  Page 8  |  Page 9  |  Page 10  |  Page 11  |  Page 12  |  Page 13  |  Page 14  |  Page 15  |  Page 16  |  Page 17  |  Page 18  |  Page 19  |  Page 20  |  Page 21  |  Page 22  |  Page 23  |  Page 24  |  Page 25  |  Page 26  |  Page 27  |  Page 28  |  Page 29  |  Page 30  |  Page 31  |  Page 32  |  Page 33  |  Page 34  |  Page 35  |  Page 36  |  Page 37  |  Page 38  |  Page 39  |  Page 40  |  Page 41  |  Page 42  |  Page 43  |  Page 44  |  Page 45  |  Page 46  |  Page 47  |  Page 48  |  Page 49  |  Page 50  |  Page 51  |  Page 52  |  Page 53  |  Page 54  |  Page 55  |  Page 56  |  Page 57  |  Page 58  |  Page 59  |  Page 60  |  Page 61  |  Page 62  |  Page 63  |  Page 64  |  Page 65  |  Page 66  |  Page 67  |  Page 68  |  Page 69  |  Page 70  |  Page 71  |  Page 72  |  Page 73  |  Page 74  |  Page 75  |  Page 76  |  Page 77  |  Page 78  |  Page 79  |  Page 80  |  Page 81  |  Page 82  |  Page 83  |  Page 84  |  Page 85  |  Page 86  |  Page 87  |  Page 88  |  Page 89  |  Page 90  |  Page 91  |  Page 92