Personalized Understanding of Blood Glucose Dynamics via Mobile Sensor Data

TL;DR

This paper presents a novel approach combining GPS, activity, and blood glucose data from a smartphone to analyze lifestyle events and improve diabetes management for a type-1 diabetic patient.

Contribution

It introduces a new data collection method integrating sensor inputs with CGM data and develops analytical tools for lifestyle event detection and visualization.

Findings

GPS and activity data correlate with blood glucose changes

Lifestyle events can be identified from sensor data

Enhanced visualizations aid diabetes management

Abstract

Continuous Blood Glucose (CGM) monitors have revolutionized the ability of diabetics to manage their blood glucose, and paved the way for artificial pancreas systems. In this paper we augment CGM data with sensor input collected by a smart phone and use it to provide analytical tools for patients and clinicians. We collected GPS data, activity classifications, and blood glucose data with a custom iOS application over a 9 month period from a single free-living type-1 diabetic patient. This data set is novel in terms of it's size, the inclusion of GPS data, and the fact that it was collected non-intrusively from a free-living patient. We describe a method to measure the occurrence of lifestyle \textit{events} based on GPS and activity data, and show that they can capture instances of food consumption and are therefore correlated to changes in blood glucose. Finally, we incorporate these event representations into our system to create useful visualizations and notifications to aid patients in managing their diabetes.