The July 2022 issue of IEEE Spectrum is here!

Close bar

Algorithms Outperform Diabetics at Blood Sugar Control

Small real-world trials hint at automated diabetes treatment devices

2 min read
Algorithms Outperform Diabetics at Blood Sugar Control
Photo: Getty Images

Doing math or any other mental activity when you have low blood sugar is a recipe for errors. For sufferers of Type 1 diabetes, who must track and adjust their own blood sugar levels, it can mean more than inability to focus. It can be fatal. Yet a small real-world study announced Sunday at a meeting of the American Diabetes Association (ADA) in San Francisco offers hope that software could monitor blood sugar levels and adjust insulin levels for them, even outside of controlled settings such as hospitals.

The study's authors conducted parallel 10-day trials with 52 participants. One trial tested adolescents at a summer camp. A parallel trial consisted of adults with only minor restriction on their activity or diet.

For five days, all of the participants wore continuous glucose monitors and a pump for insulin and glucagon, hormones which regulate blood sugar levels. The devices communicated with mobile phones, where an experimental application monitored blood sugar levels and governed the delivery of the hormones. The participants also recorded some of their meals in the application during the five-day period of the intervention. The team compared results with those from a five-day period during which the same participants managed their own care.

The researchers, from Boston University and Massachusetts General Hospital, among other institutions, report in the New England Journal of Medicine that the adults using the algorithm spent around 4.8 percent of the time with blood sugar lower than 70 milligrams per deciliter, compared with about 7.4 percent of the time when they managed their own care. Adolescents showed a smaller difference: 6.1 percent with the algorithm vs. 7.6 percent on their own. The adults also had to take emergency sugar interventions with lower frequency: once every 2.3 days versus every 1.5 days in the control setup. Adolescents, who were more active than adults, took sugar interventions every 1.6 days while using the algorithm instead of every 0.8 days on their own.

Automated monitoring and intervention for Type 1 diabetes is a busy research area and a Food and Drug Administration (FDA) priority. Another team at the ADA meeting reported positive results from a small feasibility trial of its own artificial pancreas algorithm. And a study published last month in Diabetes Care focused on overnight automated blood sugar monitoring and intervention. In that trial, 45 participants compared the algorithm to no interventions over an average of 42 nights. On the nights they used the software, the participants averaged 81 percent less time with low blood sugar.

Such devices take a long time to get from trial to market, but that kind of math should help Type 1 diabetes sufferers one day get a better night's rest.

The Conversation (0)
A photo showing machinery in a lab

Foundries such as the Edinburgh Genome Foundry assemble fragments of synthetic DNA and send them to labs for testing in cells.

Edinburgh Genome Foundry, University of Edinburgh

In the next decade, medical science may finally advance cures for some of the most complex diseases that plague humanity. Many diseases are caused by mutations in the human genome, which can either be inherited from our parents (such as in cystic fibrosis), or acquired during life, such as most types of cancer. For some of these conditions, medical researchers have identified the exact mutations that lead to disease; but in many more, they're still seeking answers. And without understanding the cause of a problem, it's pretty tough to find a cure.

We believe that a key enabling technology in this quest is a computer-aided design (CAD) program for genome editing, which our organization is launching this week at the Genome Project-write (GP-write) conference.

With this CAD program, medical researchers will be able to quickly design hundreds of different genomes with any combination of mutations and send the genetic code to a company that manufactures strings of DNA. Those fragments of synthesized DNA can then be sent to a foundry for assembly, and finally to a lab where the designed genomes can be tested in cells. Based on how the cells grow, researchers can use the CAD program to iterate with a new batch of redesigned genomes, sharing data for collaborative efforts. Enabling fast redesign of thousands of variants can only be achieved through automation; at that scale, researchers just might identify the combinations of mutations that are causing genetic diseases. This is the first critical R&D step toward finding cures.

Keep Reading ↓Show less