Artificial intelligence and diabetes: two topics that are very close to my heart. That’s why, in association with World Diabetes Day, I’ve decided to show you the many fascinating ways AI is helping the medical world gain ground in the fight against the disease.
Whether you have diabetes or not: I have no doubt you’ll enjoy humankind’s ability to innovate.
Recognizing World Diabetes Day
On Saturday, November 14th, the world’s focus turned to World Diabetes Day: an annual global campaign raising awareness of diabetes. The International Diabetology Federation established the campaign in 1991.
And they chose November 14th as it’s the birthday of Frederick Banting: the gentleman who discovered insulin.
“Some 422 million people worldwide have diabetes.”
Diabetes is important both for me as a person who struggles with the disease — and for me as a professional, as my team and I continue to develop Suguard: an AI-based smartphone app that makes everyday life easier for people with the condition.
Suguard is an internal project we’ve been developing since 2014, which is when we founded DiabetesLab: our second company focused on creating advanced software that helps people manage an illness using AI.
Suguard is both my idea and my dream. As someone struggling with the condition, I see a great need for such a personalized application. And my experience has driven me forward as I look for a solution to help me stay active and enjoy sports.
People with diabetes typically require intensive treatment and exceptional care, especially during sporting activities. But that doesn’t make them impossible. And I believe I’m a shining example that you can still play sports to a good level with the condition.
The reason I’m talking about it is that my ambition to play sport drove me to create a solution that would help me. And I hope that soon, it will be the most useful app in the world for anyone with Type 1 diabetes.
If it sounds interesting, you can learn more about the project in my article on How AI and Data Science Can Help Manage Diabetes in Everyday Life). That said, today, my focus isn’t on Suguard.
Instead, I’m here to share other AI-based solutions that are helping diabetics manage the disease.
I hope you enjoy the insight.
5 Ways Artificial Intelligence Improves Diabetes Care
There are plenty of ways to use AI for diabetes management. The following five are the most creative applications I know: if you’re aware of others, please send them my way.
1. Diabetic Retinopathy Diagnosis
Doctors are successfully leveraging deep learning to automate the diagnosis of diabetic retinopathy: a complication associated with diabetes that can cause blindness.
Specialists refer to AI-based screening to detect and monitor incidences of diabetic retinopathy, with 96% of patients satisfied with the service. The technology uses convolutional neural networks to indicate likely issues on a patient’s retina, boasting accuracy levels of 92.3% and specificity levels of 93.7%.
2. Disease Risk Modelling
Healthcare organizations use machine learning to model the risk of diabetes in a subset of a population. They do this by analyzing lifestyles, physical and mental health, and social media activity.
The model used data from 68,994 people to train its diabetes prediction algorithm, and it now works to a very high degree of accuracy. The software can indicate the risk of developing long-term complications, including Diabetic Retinopathy and cardiovascular or renal issues — alongside short-term concerns, like hypoglycemia.
3. Diabetes Self-management
Diabetes self-management is crucial in treating the disease. Thanks to AI, patients are now empowered to self-manage their condition, using personal data to adapt their lifestyle and essentially act as an at-home physician.
Artificial intelligence enables patients to decide what to eat or drink as much as what level of physical activity is appropriate. And smartphone apps, including Suguard, make self-management much easier via features like real-time analysis of the calorific value of food.
4. Advanced Genomics
Genes hold the secret to your health. And advanced molecular phenotyping, epigenetic alterations, and the development of digital biomarkers are helping medical specialists advance the diagnosis and management of conditions like diabetes by leveraging genomics.
Microbiome data has opened up a repository for microbial marker genes that predict the likelihood of diabetes (these can also guide treatment). Elsewhere, studies have identified more than 400 signals indicating when someone is at risk of developing diabetes due to their genetics.
5. Complications Monitoring
Diabetes can lead to several common complications, including vascular pathologies (presenting as strokes, blood clots, or arterial disease) and peripheral neuropathies (presenting as weakness, numbness, and pain, often in the hands and feet).
Much like we saw in point one with Diabetic Retinopathy diagnosis, machine learning can help spot and monitor other issues. An application called FootSnap, for example, can both detect inflammation and effectively predict potential foot ulcerations.
AI Is Changing Lives
Artificial intelligence has had a transformational impact on the everyday lives of people with diabetes.
Swathes of disease-related data are both improving self-management and personalizing treatment plans — while there’s an increasing number of advanced solutions entering the field every year.
We promise to let you know as soon as new features appear.
For now: take care 😊