US 2,003,208,113 · Filed 2001-07-18

The Blood Sugar Prediction Algorithm That Powers Modern Glucose Apps

Imagine an app that predicts your blood sugar levels based on what you eat, using math and your personal body data. This patent describes the software engine that lets your phone or device calculate where your glucose will go after meals — before you actually feel the spike or crash.

Curated and verified by the IsItPatented Editorial team

The plain-English version

What it protects

The patent covers a software system that takes nutritional information about food (carbs, proteins, fats, fiber, etc.), runs it through a personalized mathematical model of how your body responds to glucose, and outputs predicted blood sugar levels in real time. The claims protect the combination of the data input, the glycemic response model specific to each person, and the display of those predictions on an electronic device.

Why it matters

This is one of the foundational patents for digital glucose management tools. Instead of waiting hours to test blood sugar or relying on guesswork, people—especially those managing diabetes—can now see predictions instantly. The patent essentially locks down the idea of personalized, algorithm-driven glucose forecasting on a consumer device, which has become central to how continuous glucose monitors and diabetes apps work today.

Real-world use

When someone with diabetes logs their lunch into a health app and sees an estimated blood sugar curve appear seconds later, they're using logic that traces back to this patent's closed-loop prediction model.

Original USPTO abstract

A system for assisting a person to maintain a blood glucose level between predetermined limits comprises: an electronic device, comprising a display, a clock, a memory, and a processor; and a software program executable by the processor of the electronic device, adapted to receive nutritional data of food consumed by the person, adapted to calculate the blood glucose level for the person using the nutritional data and a glycemic response model for the person, and further adapted to present the blood glucose level to the person on the display of the electronic device.

Patent details

Publication number: US 2,003,208,113
Filing date: 2001-07-18
Grant date: Application — not yet granted
Assignee: Mault James R / John Sanderson
Inventor(s): MAULT JAMES R, SANDERSON JOHN
CPC class: A61B5/415

View original record on Google Patents →

Want to file your own patent?

If you're building a health tracking app or wearable, checking our patent scanner first can help you spot whether your glucose-prediction features overlap with existing protected territory.

Free patentability scan