Sean Pikulin, Irad Yehezkel, Robert Moskovitch
Abstract
Ensuring stable blood glucose (BG) levels within the norm is crucial for potential long-term health complications prevention when managing a chronic disease like Type 1 diabetes (T1D), as well as body weight.
Introduction
Predicting Blood Glucose (BG) levels is desirable for various purposes, such as for type 1 diabetes patients [1], as well as for professional athletes [2]. Knowing in advance when BG is approaching unsafe levels, whether low or high, provides time to proactively avoid hypo\hyper-glycemia and their associated complications.
Materials and Methods
We introduce here Gludict, a framework that we had developed for the prediction of glucose levels, that includes the following components—collecting data from several sources, storing the data from all the sources in a database, data transformations, and inducing a prediction model for BG levels.
Result
We describe here the results of the experiments that were described earlier.
Discussion
Predicting BG levels is crucial for a variety of purposes, including the management of type 1 diabetes and the optimization of performance for professional athletes. BG levels are influenced by daily activities such as eating and drinking, varying according to their contents, as well as by exercise.
Conclusion
In conclusion, we highly recommend using physiological data like step count and heart rate alongside the glucose for better prediction. In addition, using automatically monitored data brings much better results than using manually recorded activities.
Citation: Pikulin S, Yehezkel I, Moskovitch R (2024) Enhanced blood glucose levels prediction with a smartwatch. PLoS ONE 19(7): e0307136. https://doi.org/10.1371/journal.pone.0307136
Editor: Suja A. Alex, St Xavier’s Catholic College of Engineering, INDIA
Received: March 12, 2024; Accepted: July 2, 2024; Published: July 18, 2024
Copyright: © 2024 Pikulin et al. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.
Data Availability: The data are uploaded to Figshare and you will be able to find it in the following link: https://figshare.com/articles/dataset/Glucdict_-_Wearable_Sensors_and_CGM/25939312 Additionally, the DOI is: 10.6084/m9.figshare.25939312.v1.
Funding: This study was funded by the Israeli Ministry of Science, Technology and Space, Grant #81573. The funders had no role in study design, data collection and analysis, decision to publish, or preparation of the manuscript.
Competing interests: The authors have declared that no competing interests exist.
Source: https://journals.plos.org/plosone/article?id=10.1371/journal.pone.0307136#abstract0
