Key Findings
Apollon won two categories at the Glucose Prediction Challenge 2026, held during the Diabetes Technology Meeting (DTM 2026) in Washington, D.C., from October 27 to 29. Competing against 31 teams, Apollon’s AI model recorded a Mean Absolute Relative Difference (MARD) of 4.65% and a 97.0% proportion in Zone A of the DTS error grid for clinical accuracy. The competition was supported by the Helmsley Charitable Trust.
Technical Details
The challenge evaluated the ability to predict glucose changes from 30 minutes to 2 hours in the future based on historical glucose records and insulin administration data. Apollon developed an Attention-based AI model that analyzes up to 16 days of continuous glucose monitoring (CGM) and insulin data to predict changes at 5-minute intervals for the subsequent 2 hours. The model assigns higher weights to longer prediction intervals and incorporates data from users of the same type of insulin pump to refine accuracy.
Background and Context
Apollon is developing “Moglu,” a non-invasive CGM that uses Raman spectroscopy to eliminate the need for needles or consumables. The company presented a prototype measuring 80mm x 90mm x 30mm at the DTM startup showcase. Additionally, Apollon shared joint research with the MIT Laser Bioengineering Center on non-invasive glucose and ketone measurement using bandpass Raman spectroscopy, with results published in the Journal of Diabetes Science and Technology.
Significance and Outlook
The company intends to apply its award-winning AI prediction technology to Moglu to provide proactive alerts for hypoglycemia and hyperglycemia. Apollon has filed 54 patents (21 registered) primarily in the U.S. and received a CES 2025 Innovation Award. Having secured a first round of Series A investment led by SBI Investment, the company is pursuing follow-on investment from U.S. investors and preparing clinical feasibility studies for diabetes patients at the Joslin Diabetes Center affiliated with Harvard Medical School.
Source: https://www.biotimes.co.kr/news/articleView.html?idxno=35792
Get our weekly technology intelligence — free
Receive an infographic that lets you judge at a glance whether each field’s analysis report is worth reading.
Subscribe Free — Weekly Tech Intelligence
By subscribing, you’ll receive Troy-Technical’s weekly technology intelligence newsletter.
- Your email and selected fields are used only to deliver the newsletter.
- We never share your information with third parties.
- You can unsubscribe anytime via the link in each email.
See our Privacy Policy for details.
Takes about a minute · Unsubscribe anytime
