On the Use of Consumer-Grade Activity Monitoring Devices to Improve Predictions of Glycemic Variability

Chandra Krintz; Rich Wolski; Jordan Pinsker; Stratos Dimopoulos; John Brevik; Eyal Dassau

Smart City 360°. First EAI International Summit, Smart City 360°, Bratislava, Slovakia and Toronto, Canada, October 13-16, 2015. Revised Selected Papers

Research Article

On the Use of Consumer-Grade Activity Monitoring Devices to Improve Predictions of Glycemic Variability

Download

238 downloads

Cite: BibTeX Plain Text

@INPROCEEDINGS{10.1007/978-3-319-33681-7_14,
    author={Chandra Krintz and Rich Wolski and Jordan Pinsker and Stratos Dimopoulos and John Brevik and Eyal Dassau},
    title={On the Use of Consumer-Grade Activity Monitoring Devices to Improve Predictions of Glycemic Variability},
    proceedings={Smart City 360°. First EAI International Summit, Smart City 360°, Bratislava, Slovakia and Toronto, Canada, October 13-16, 2015. Revised Selected Papers},
    proceedings_a={SMARTCITY360},
    year={2016},
    month={6},
    keywords={Activity monitoring Diabetes Prediction Decision support},
    doi={10.1007/978-3-319-33681-7_14}
}

Chandra Krintz
Rich Wolski
Jordan Pinsker
Stratos Dimopoulos
John Brevik
Eyal Dassau
Year: 2016
On the Use of Consumer-Grade Activity Monitoring Devices to Improve Predictions of Glycemic Variability
SMARTCITY360
Springer
DOI: 10.1007/978-3-319-33681-7_14

Chandra Krintz¹^,*, Rich Wolski¹, Jordan Pinsker², Stratos Dimopoulos¹, John Brevik³, Eyal Dassau¹

1: University of California
2: William Sansum Diabetes Center
3: California State University

*Contact email: ckrintz@cs.ucsb.edu.edu

Abstract

This paper examines the use of partial least squares regression to predict glycemic variability in subjects with Type I Diabetes Mellitus using measurements from continuous glucose monitoring devices and consumer-grade activity monitoring devices. It illustrates a methodology for generating automated predictions from current and historical data and shows that activity monitoring can improve prediction accuracy substantially.

Keywords: Activity monitoring Diabetes Prediction Decision support

Published: 2016-06-29
Appears in: SpringerLink

: http://dx.doi.org/10.1007/978-3-319-33681-7_14