Interpretation method for continuous glucose monitoring with subsequence time-series clustering

Masaki Ono; Takayuki Katsuki; Masaki Makino; Kyoichi Haida; Atsushi Suzuki

doi:10.3233/SHTI200166

Interpretation method for continuous glucose monitoring with subsequence time-series clustering

Masaki Ono, Takayuki Katsuki, Masaki Makino, Kyoichi Haida, Atsushi Suzuki

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

We propose mini-batch top-n k-medoids to sequential pattern mining to improve CGM interpretation. Mecical workers can treat specific patient groups better by understanding the time series variation of blood glucose results. For 10 years, continuous glucose monitoring (CGM) has provided time-series data of blood glucose thanks to the invention of devices with low measurement errors. We conducted two experiments. In the first experiment, we evaluated the proposed method with a manually created dataset and confirmed that the method provides more accurate patterns than other clustering methods. In the second experiment, we applied the proposed method to a CGM dataset consisting of real data from 163 patients. We created two labels based on blood glucose (BG) statistics and found patterns that correlated with a specific label in each case.

Original language	English
Title of host publication	Digital Personalized Health and Medicine - Proceedings of MIE 2020
Editors	Louise B. Pape-Haugaard, Christian Lovis, Inge Cort Madsen, Patrick Weber, Per Hostrup Nielsen, Philip Scott
Publisher	IOS Press
Pages	277-281
Number of pages	5
ISBN (Electronic)	9781643680828
DOIs	https://doi.org/10.3233/SHTI200166
Publication status	Published - 16-06-2020
Externally published	Yes
Event	30th Medical Informatics Europe Conference, MIE 2020 - Geneva, Switzerland Duration: 28-04-2020 → 01-05-2020

Publication series

Name	Studies in Health Technology and Informatics
Volume	270
ISSN (Print)	0926-9630
ISSN (Electronic)	1879-8365

Conference

Conference	30th Medical Informatics Europe Conference, MIE 2020
Country	Switzerland
City	Geneva
Period	28-04-20 → 01-05-20

All Science Journal Classification (ASJC) codes

Biomedical Engineering
Health Informatics
Health Information Management

Access to Document

10.3233/SHTI200166

Fingerprint Dive into the research topics of 'Interpretation method for continuous glucose monitoring with subsequence time-series clustering'. Together they form a unique fingerprint.

Cite this

Ono, M., Katsuki, T., Makino, M., Haida, K., & Suzuki, A. (2020). Interpretation method for continuous glucose monitoring with subsequence time-series clustering. In L. B. Pape-Haugaard, C. Lovis, I. C. Madsen, P. Weber, P. H. Nielsen, & P. Scott (Eds.), Digital Personalized Health and Medicine - Proceedings of MIE 2020 (pp. 277-281). (Studies in Health Technology and Informatics; Vol. 270). IOS Press. https://doi.org/10.3233/SHTI200166

Ono, Masaki ; Katsuki, Takayuki ; Makino, Masaki ; Haida, Kyoichi ; Suzuki, Atsushi. / Interpretation method for continuous glucose monitoring with subsequence time-series clustering. Digital Personalized Health and Medicine - Proceedings of MIE 2020. editor / Louise B. Pape-Haugaard ; Christian Lovis ; Inge Cort Madsen ; Patrick Weber ; Per Hostrup Nielsen ; Philip Scott. IOS Press, 2020. pp. 277-281 (Studies in Health Technology and Informatics).

@inproceedings{99459abf6ea44c7c9a086d7ec0439d43,

title = "Interpretation method for continuous glucose monitoring with subsequence time-series clustering",

abstract = "We propose mini-batch top-n k-medoids to sequential pattern mining to improve CGM interpretation. Mecical workers can treat specific patient groups better by understanding the time series variation of blood glucose results. For 10 years, continuous glucose monitoring (CGM) has provided time-series data of blood glucose thanks to the invention of devices with low measurement errors. We conducted two experiments. In the first experiment, we evaluated the proposed method with a manually created dataset and confirmed that the method provides more accurate patterns than other clustering methods. In the second experiment, we applied the proposed method to a CGM dataset consisting of real data from 163 patients. We created two labels based on blood glucose (BG) statistics and found patterns that correlated with a specific label in each case.",

author = "Masaki Ono and Takayuki Katsuki and Masaki Makino and Kyoichi Haida and Atsushi Suzuki",

year = "2020",

month = jun,

day = "16",

doi = "10.3233/SHTI200166",

language = "English",

series = "Studies in Health Technology and Informatics",

publisher = "IOS Press",

pages = "277--281",

editor = "Pape-Haugaard, {Louise B.} and Christian Lovis and Madsen, {Inge Cort} and Patrick Weber and Nielsen, {Per Hostrup} and Philip Scott",

booktitle = "Digital Personalized Health and Medicine - Proceedings of MIE 2020",

address = "Netherlands",

note = "30th Medical Informatics Europe Conference, MIE 2020 ; Conference date: 28-04-2020 Through 01-05-2020",

}

Ono, M, Katsuki, T, Makino, M, Haida, K & Suzuki, A 2020, Interpretation method for continuous glucose monitoring with subsequence time-series clustering. in LB Pape-Haugaard, C Lovis, IC Madsen, P Weber, PH Nielsen & P Scott (eds), Digital Personalized Health and Medicine - Proceedings of MIE 2020. Studies in Health Technology and Informatics, vol. 270, IOS Press, pp. 277-281, 30th Medical Informatics Europe Conference, MIE 2020, Geneva, Switzerland, 28-04-20. https://doi.org/10.3233/SHTI200166

Interpretation method for continuous glucose monitoring with subsequence time-series clustering. / Ono, Masaki; Katsuki, Takayuki; Makino, Masaki; Haida, Kyoichi; Suzuki, Atsushi.

Digital Personalized Health and Medicine - Proceedings of MIE 2020. ed. / Louise B. Pape-Haugaard; Christian Lovis; Inge Cort Madsen; Patrick Weber; Per Hostrup Nielsen; Philip Scott. IOS Press, 2020. p. 277-281 (Studies in Health Technology and Informatics; Vol. 270).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - Interpretation method for continuous glucose monitoring with subsequence time-series clustering

AU - Ono, Masaki

AU - Katsuki, Takayuki

AU - Makino, Masaki

AU - Haida, Kyoichi

AU - Suzuki, Atsushi

PY - 2020/6/16

Y1 - 2020/6/16

N2 - We propose mini-batch top-n k-medoids to sequential pattern mining to improve CGM interpretation. Mecical workers can treat specific patient groups better by understanding the time series variation of blood glucose results. For 10 years, continuous glucose monitoring (CGM) has provided time-series data of blood glucose thanks to the invention of devices with low measurement errors. We conducted two experiments. In the first experiment, we evaluated the proposed method with a manually created dataset and confirmed that the method provides more accurate patterns than other clustering methods. In the second experiment, we applied the proposed method to a CGM dataset consisting of real data from 163 patients. We created two labels based on blood glucose (BG) statistics and found patterns that correlated with a specific label in each case.

AB - We propose mini-batch top-n k-medoids to sequential pattern mining to improve CGM interpretation. Mecical workers can treat specific patient groups better by understanding the time series variation of blood glucose results. For 10 years, continuous glucose monitoring (CGM) has provided time-series data of blood glucose thanks to the invention of devices with low measurement errors. We conducted two experiments. In the first experiment, we evaluated the proposed method with a manually created dataset and confirmed that the method provides more accurate patterns than other clustering methods. In the second experiment, we applied the proposed method to a CGM dataset consisting of real data from 163 patients. We created two labels based on blood glucose (BG) statistics and found patterns that correlated with a specific label in each case.

UR - http://www.scopus.com/inward/record.url?scp=85086907067&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85086907067&partnerID=8YFLogxK

U2 - 10.3233/SHTI200166

DO - 10.3233/SHTI200166

M3 - Conference contribution

C2 - 32570390

AN - SCOPUS:85086907067

T3 - Studies in Health Technology and Informatics

SP - 277

EP - 281

BT - Digital Personalized Health and Medicine - Proceedings of MIE 2020

A2 - Pape-Haugaard, Louise B.

A2 - Lovis, Christian

A2 - Madsen, Inge Cort

A2 - Weber, Patrick

A2 - Nielsen, Per Hostrup

A2 - Scott, Philip

PB - IOS Press

T2 - 30th Medical Informatics Europe Conference, MIE 2020

Y2 - 28 April 2020 through 1 May 2020

ER -

Ono M, Katsuki T, Makino M, Haida K, Suzuki A. Interpretation method for continuous glucose monitoring with subsequence time-series clustering. In Pape-Haugaard LB, Lovis C, Madsen IC, Weber P, Nielsen PH, Scott P, editors, Digital Personalized Health and Medicine - Proceedings of MIE 2020. IOS Press. 2020. p. 277-281. (Studies in Health Technology and Informatics). https://doi.org/10.3233/SHTI200166