File photo use for representation only.
With an aim to redefine the strategies for prevention and management of diabetes in future, Qatar Computing Research Institute (QCRI) of Qatar Foundation’s Hamad Bin Khalifa University, has developed AI tools to support the local population, where rates of diabetes are high.
AI is at the early stage of use across the world in diabetes prevention and management. If it is implemented here, Qatar will set an example for rest of the world, according to Dr. Faisal Farooq, Principal Scientist, at QCRI.
The System for Integrated Health Analytics (SIHA), a web-based cloud computing platform developed by the QCRI allows clinicians to efficiently monitor and analyse patients with diabetes and other chronic diseases, and gain deeper insights using visual and predictive analytics. The platform also enables clinicians to collaborate with researchers for additional insights, ensuring they can stay on top of the latest studies.
“We are working on various aspects of the management of diabetes and how AI can support some of the work being conducted in this field. We are currently developing risk scores that can predict the possibility of individuals to develop diabetes. These screening methods can be used by individuals easily at home and outside of a clinical setting, predominantly by using applications and other tools that can inform these candidates about their risk,” Dr. Farooq told The Peninsula on the occasion of World Diabetes Day, being observed today.
QCRI is also working on AI models that mirror the lifestyles of individuals, which is extremely important in addressing diseases such as diabetes. “For example, we have developed models that predict, in advance, the quality of sleep of certain individuals based on their current lifestyle factors.
Dr. Farooq said: We are also trying to develop models to understand patterns of sedentary versus active periods in individuals using smart watches and mobile devices such that AI-based recommendations and the right kind of notifications can be made, in an effort to increase the activity of individuals or improve their overall lifestyle.
“In addition, we plan on developing models that can predict the risk of gestational diabetes in females that are about to get married or who are planning to start a family, as well as predicting their risk of progressing from gestational to type-2 diabetes. Using mobile applications, we plan to provide education to such individuals and inform them of the risks as well as provide recommendations on what they can do to reduce this risk.”
The large-scale project involves multiple stakeholders, including the Ministry of Public Health (MoPH), Primary Health Care Corporation (PHCC), Qatar Diabetes Association (QDA), Qatar Metabolic Institute (QMI), Sidra Medicine, Weill Cornell Medicine – Qatar (WCM-Q), Qatar Biobank, and Qatar Genome Programme.
As part of the project, the team at QCRI looked at the impact of fasting for diabetic patients to help those who fast for Ramadan to predict and manage glycaemic events. Working in collaboration with physicians from HMC, more than 80 patients with type 2 diabetes received a Fitbit to measure activity and sleep, as well as a wearable device that continuously monitored their glucose readings before and during Ramadan.
“We used this to develop a tailored AI algorithm which proved to have a high predictive performance for hyperglycaemic excursions,” said Dr. Farooq.
“The success of the trial showcases AI’s potential to save lives by predicting low blood sugar events during fasting, and providing clinicians with key insights into risk factors that cause these events, such as a patient’s treatment regimen. The same AI models are now being generalised to be implemented in a large-scale national trial led by HMC to reverse Type 2 and gestational diabetes,” he added.
