JMIR Publications

ABSTRACT

Background:

Diabetes affects millions of people worldwide and is steadily increasing. A serious condition associated with diabetes is low glucose levels (hypoglycemia). Monitoring blood glucose is usually performed by invasive methods or devices that are intrusive, and these devices are currently not available to all patients with diabetes. Hand tremor is a significant symptom of hypoglycemia as nerves and muscles are powered by blood sugar. However, to our knowledge, no validated tools or algorithms exist to monitor and detect hypoglycemic events through hand tremors.

Objective:

In this paper, we propose a non-invasive method to detect hypoglycemic events based on hand tremors using accelerometer data.

Methods:

We analyzed triaxial accelerometer data from a smartwatch recorded from 33 patients with type 1 diabetes over the course of a month. Time- and frequency-domain features were extracted from acceleration signals to explore different machine learning models to classify and differentiate between hypoglycemic (HG) and non-hypoglycemic (non-HG) states.

Results:

The mean duration of HG state was 27.31 (±25.15) minutes per day for each patient. On average, patients had 1.06 (±0.77) HG events per day. The Ensemble Learning model based on random forest, support vector machines, and K-nearest neighbors had the best performance with a precision of 81.5% and a recall of 78.6%. The results were validated using continuous glucose monitor readings as ground truth.

Conclusions:

Results indicate that the proposed approach can be a potential tool to detect hypoglycemia and can serve as a proactive, non-intrusive alert mechanism for hypoglycemic events.