A data-driven approach to classifying daily continuous glucose monitoring (CGM) time series

2021 ◽  
pp. 1-1
Author(s):  
Benjamin Lobo ◽  
Leon Farhy ◽  
Mahdi Shafiei ◽  
Boris Kovatchev
Keyword(s):  
Time Series ◽  
Continuous Glucose Monitoring ◽  
Glucose Monitoring ◽  
Data Driven ◽  
Data Driven Approach

Continuous Glucose Monitoring Time Series and Hypo/Hyperglycemia Prevention: Requirements, Methods, Open Problems

2008 ◽  
Vol 4 (3) ◽  
pp. 181-192 ◽  
Author(s):  
Giovanni Sparacino ◽  
Andrea Facchinetti ◽  
Alberto Maran ◽  
Claudio Cobelli
Keyword(s):  
Time Series ◽  
Continuous Glucose Monitoring ◽  
Glucose Monitoring ◽  
Open Problems ◽  
Monitoring Time

Time-Series Analysis of Continuous Glucose Monitoring Data to Predict Treatment Efficacy in Patients with T2DM

2021 ◽  
Author(s):  
Li Li ◽  
Jie Sun ◽  
Liemin Ruan ◽  
Qifa Song
Keyword(s):  
Time Series ◽  
Time Series Analysis ◽  
Continuous Glucose Monitoring ◽  
Treatment Efficacy ◽  
Treatment Effects ◽  
Glucose Monitoring ◽  
Therapeutic Effects ◽  
Time Series Clustering ◽  
Glucose Lowering ◽  
Series Analysis

Abstract Context There is a challenge to predict treatment effects in patients with T2DM. Objective To assess and predict treatment effects in patients with T2DM through time-series analysis of continuous glucose monitoring (CGM) measurements. Design We extracted and clustered the trend components of CGM measurements to generate representative time-series profiles, which were used as a predictor of treatment effects in groups of patients. Setting and Participants We recruited 111 outpatients with T2DM at Ningbo City First Hospital. Intervention The patients underwent CGM measurement for 14 days at the beginning of glucose-lowering treatment. Main Outcome Measures HbA1c and FPG were obtained at the beginning and 6-month of treatment. Results 111 patients each had 960 –1344 CGM measurements for 14 days at 96 measurements per day. The patients were classified into three groups according to the profiles of trend components of CGM observed values by time-series clustering method, including decreasing (47 patients), increasing (26 patients), and unchanged (38 patients) profiles. After six-month glucose-lowering treatment, FPG declined from 10.2 to 6.8 mmol/L (a decline of 3.5 mmol/L) in the decreasing group, from 8.9 to 9.2 mmol/L (a rise of 0.3 mmol/L) in the increasing group, and from 8.4 to 7.5 mmol/L (a decline of 0.9 mmol/L). The changes of HbA1c were 2.2%, 0.2%, and 0.9% for the three groups (P<0.01), respectively. Conclusions Clustering of the trend components of CGM data generates representative CGM profiles that are predictive of six-month therapeutic effects for T2DM.

scholarly journals Bandt-Pompe symbolization dynamics for time series with tied values: A data-driven approach

2018 ◽  
Vol 28 (7) ◽  
pp. 075502 ◽  
Author(s):  
Francisco Traversaro ◽  
Francisco O. Redelico ◽  
Marcelo R. Risk ◽  
Alejandro C. Frery ◽  
Osvaldo A. Rosso
Keyword(s):  
Time Series ◽  
Data Driven ◽  
Data Driven Approach

A data-driven approach for denoising GNSS position time series

2017 ◽  
Vol 92 (8) ◽  
pp. 905-922 ◽  
Author(s):  
Yanyan Li ◽  
Caijun Xu ◽  
Lei Yi ◽  
Rongxin Fang
Keyword(s):  
Time Series ◽  
Data Driven ◽  
Data Driven Approach ◽  
Position Time Series ◽  
Gnss Position Time Series

Data-driven approach to identify obsolete functions of products for design improvements

2021 ◽  
pp. 1-14
Author(s):  
Zhihua Zhao ◽  
Yupeng Li ◽  
Xuening Chu
Keyword(s):  
Time Series ◽  
Functional Performance ◽  
Smart Phone ◽  
Data Driven ◽  
Design Elements ◽  
Customer Expectations ◽  
Data Driven Approach ◽  
Identification Approach ◽  
Previous Identification

Identifying defective design elements is a prerequisite for design improvements. Previous identification methods were implemented in the context of static customer requirements (CRs). However, CRs always evolve continuously, which easily leads to a failure of existing product functions in fulfilling customer expectations; this, in turn, can lead to a decline in customer satisfaction. In this study, the phenomenon is termed as ‘function obsolescence’, and a data-driven identification approach for obsolete functions is proposed for design improvements. Firstly, product operating data are employed to construct the observing parameters of functional performance (OPs), and based on the distribution of OPs, the desired level of functional performance (DL) is defined to quantitatively characterise CRs. Secondly, the time series of DL is constructed to embody the evolution of CRs, in which a Sigmoid-like function is employed to establish a dissatisfaction function. With the time series, an obsolescence index measuring the severity of obsolescence for each function is defined to identify obsolete functions. A case study was implemented on a smart phone to identify its obsolete functions to demonstrate the effectiveness of the proposed methodology. The results show that some potentially obsolete functions can be identified by the proposed method considering the evolution of CRs.

A non-parametric, data-driven approach to despiking ocean surface wave time series

2021 ◽  
Author(s):  
Mika P. Malila ◽  
Patrik Bohlinger ◽  
Susanne Støle-Hentschel ◽  
Øyvind Breivik ◽  
Gaute Hope ◽  
...  
Keyword(s):  
Time Series ◽  
Surface Wave ◽  
Missing Values ◽  
Computational Cost ◽  
Ocean Surface ◽  
Data Driven ◽  
Storm Event ◽  
Wide Range ◽  
Data Driven Approach ◽  
Ocean Surface Wave

AbstractWe propose a methodology for despiking ocean surface wave time series based on a Bayesian approach to data-driven learning known as Gaussian Process (GP) regression. We show that GP regression can be used for both robust detection of erroneous measurements and interpolation over missing values, while also obtaining a measure of the uncertainty associated with these operations. In comparison with a recent dynamical phase space-based despiking method, our data-driven approach is here shown to lead to improved wave signal correlation and spectral tail consistency, although at a significant increase in computational cost. Our results suggest that GP regression is thus especially suited for offline quality control requiring robust noise detection and replacement, where the subsequent analysis of the despiked data is sensitive to the accidental removal of extreme or rare events such as abnormal or rogue waves. We assess our methodology on measurements from an array of four co-located 5-Hz laser altimeters during a much-studied storm event the North Sea covering a wide range of sea states.

Sign in / Sign up

Export Citation Format

Share Document