JMIR Publications

ABSTRACT

Background:

Continuous glucose monitoring (CGM) can facilitate weight management and lower the risk of metabolic diseases by providing real-time feedback on glycemic responses, thereby enabling more informed lifestyle decisions. However, current CGM systems remain constrained by invasiveness, cost, short sensor lifespan, limiting their practicality for guiding individualized postprandial low-glycemic diets.

Objective:

Extending earlier proof-of-concept findings, this study aimed to validate an interstitial glucose (IG) machine learning algorithm in real-world environments using multimodal, continuous data collected from wearable sensors and smartwatches.

Methods:

A total of 74 participants, 34 healthy and 40 metabolically at-risk, simultaneously used an invasive CGM device together with two non-invasive wristbands over two weeks.

Results:

The proposed long short-term memory network based on feature vectors obtained the best IG prediction performance with an average root mean squared error of 21.04 ± 8.32 mg/dL and 98.3% of predictions in Zone A and B of the Clarke error grid analysis, representing a high level of predictive accuracy.

Conclusions:

This study demonstrates that IG levels can be predicted from multimodal, non-invasive wearable sensor data using a machine learning approach under real-world conditions. While further validation in larger and more diverse cohorts is warranted, this approach represents a promising step toward accessible, personalized glycemic monitoring and dietary guidance.