AI algorithm to help manage diabetes

Researchers and physicians at Oregon Health & Science University, using artificial intelligence and automated monitoring, have designed a method to help people with type 1 diabetes better manage their glucose levels.

Photo

"Our system design is unique," said lead author Nichole Tyler, an M.D.-Ph.D. student in the OHSU School of Medicine. "We designed the AI algorithm entirely using a mathematical simulator, and yet when the algorithm was validated on real-world data from people with type 1 diabetes at OHSU, it generated recommendations that were highly similar to recommendations from endocrinologists."

That's significant because the people with diabetes typically go three to six months between appointments with their endocrinologist. In that time, they can be at risk of dangerous complications if glucose levels in their blood rise too high or fall too low. People with type 1 diabetes do not produce their own insulin, so they must take it continuously through the day using an insulin pump or through multiple daily injections. The algorithm developed by OHSU scientists uses data collected from a continuous glucose monitor and wireless insulin pens to provide guidance on adjustments.

Paired with a smartphone app called DailyDose, the recommendations from the algorithm were shown to be in agreement with physicians 67.9% of the time.

The new study involved monitoring 16 people with type 1 diabetes over the course of four weeks, showing that the model can help reduce hypoglycemia, or low glucose. If left untreated, hypoglycemia can cause coma or death.

The engine was developed in a collaboration between the OHSU Harold Schnitzer Diabetes Health Center and the Artificial Intelligence for Medical Systems Lab led by Peter Jacobs, Ph.D., associate professor of biomedical engineering in the OHSU School of Medicine. "There are other published algorithms on this, but not a lot of clinical studies," said Jacobs, senior author on the study. "Very few have shown a statistically relevant outcome—and most do not compare algorithm recommendations with those of a physician. In addition to showing improvement in glucose control, our algorithm generated recommendations that had very high correlation with physician recommendations with over 99% of the algorithm's recommendations delivered across 100 weeks of patient testing considered safe by physicians."

OHSU intends to continue to advance the technology. "We have plans over the next several years to run several larger trials over eight and then 12 weeks and to compare DailyDose with other insulin treatment strategies, including automated insulin delivery," said co-author Jessica Castle, M.D., associate professor of medicine (endocrinology, diabetes and clinical nutrition) in the OHSU School of Medicine.

Subscribe to our newsletter

Related articles

mhealth: App diagnoses sleep apnea

mhealth: App diagnoses sleep apnea

Computer science students designed an Android application, which helps to identify the signs of sleep apnea at home.

Smartwatch turns into biochemical monitoring system

Smartwatch turns into biochemical monitoring system

Engineers have designed a thin adhesive film that could upgrade a consumer smartwatch into a powerful health monitoring system.

App monitors COVID-19 symptoms and mental health needs

App monitors COVID-19 symptoms and mental health needs

A new app that helps patients in self-isolation monitor for symptoms of COVID-19 and identify their mental health needs has been developed.

mhealth: an app to screen for early signs of dementia

mhealth: an app to screen for early signs of dementia

Dementia screening could be as easy as using a smartphone app that listens to elderly people speak.

mhealth: blood pressure monitoring as easy as taking a selfie

mhealth: blood pressure monitoring as easy as taking a selfie

Transdermal optical imaging measures blood pressure by detecting blood flow changes in smartphone-captured facial videos.

Smartphone AI detects diabetic retinopathy

Smartphone AI detects diabetic retinopathy

Pairing a smartphone to capture retinal images with an AI may offer a solution for better screening for diabetic retinopathy.

‘Second Chance’ app detects opioid overdose and its precursors

‘Second Chance’ app detects opioid overdose and its precursors

Researchers have developed an app that uses sonar to monitor someone's breathing rate and sense when an opioid overdose has occurred.

Swift Skin and Wound: App gives touchless measurements

Swift Skin and Wound: App gives touchless measurements

The app "Swift Skin and Wound", which accurately measures and charts the progression of skin wounds, could potentially have a significant impact on clinical management and patient outcomes.

mhealth: assessing anemia without drawing blood

mhealth: assessing anemia without drawing blood

Researchers have developed a way to use smartphone images of a person's eyelids to assess blood hemoglobin levels, a protein in red blood cells.

Popular articles