Temporal clustering for blood glucose analysis in the ICU: Identification of groups of patients with different risk profile

Lucia Sacchi, Giuseppe D'Ancona, Federico Bertuzzi, Riccardo Bellazzi

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Blood Glucose (BG) analysis and control in critically ill patients became an important research challenge in the last few years. Despite the big improvements that have been achieved both in research and in clinical practice, there are still many aspects that need to be elucidated. A first step towards a better comprehension of the phenomena underlying BG dynamics is represented by the study of retrospectively collected data. In this paper we propose an analysis of blood glucose time series through a combined temporal clustering and standard statistical analysis approach. The ultimate goal of the analysis is the identification of groups of patients showing different BG dynamics and evaluate their risk profiles, which is a very important issue in the Intensive Care Units. The method is applied to a set of patients treated at the Mediterranean Institute for Transplantation and Advanced Specialized Therapies in Palermo, Italy. We show that it is possible to identify two groups based on the initial blood glucose trends, and that the two groups significantly differ in terms of their future BG behaviour.

Original languageEnglish
Title of host publicationStudies in Health Technology and Informatics
Pages1150-1154
Number of pages5
Volume160
EditionPART 1
DOIs
Publication statusPublished - 2010
Event13th World Congress on Medical and Health Informatics, Medinfo 2010 - Cape Town, South Africa
Duration: Sep 12 2010Sep 15 2010

Other

Other13th World Congress on Medical and Health Informatics, Medinfo 2010
CountrySouth Africa
CityCape Town
Period9/12/109/15/10

Fingerprint

Intensive care units
Social Identification
Cluster Analysis
Glucose
Blood Glucose
Blood
Research
Critical Illness
Italy
Intensive Care Units
Time series
Statistical methods
Transplantation

Keywords

  • Blood glucose analysis
  • Clustering
  • Intensive care units
  • Temporal data mining

ASJC Scopus subject areas

  • Biomedical Engineering
  • Health Informatics
  • Health Information Management

Cite this

Sacchi, L., D'Ancona, G., Bertuzzi, F., & Bellazzi, R. (2010). Temporal clustering for blood glucose analysis in the ICU: Identification of groups of patients with different risk profile. In Studies in Health Technology and Informatics (PART 1 ed., Vol. 160, pp. 1150-1154) https://doi.org/10.3233/978-1-60750-588-4-1150

Temporal clustering for blood glucose analysis in the ICU : Identification of groups of patients with different risk profile. / Sacchi, Lucia; D'Ancona, Giuseppe; Bertuzzi, Federico; Bellazzi, Riccardo.

Studies in Health Technology and Informatics. Vol. 160 PART 1. ed. 2010. p. 1150-1154.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Sacchi, L, D'Ancona, G, Bertuzzi, F & Bellazzi, R 2010, Temporal clustering for blood glucose analysis in the ICU: Identification of groups of patients with different risk profile. in Studies in Health Technology and Informatics. PART 1 edn, vol. 160, pp. 1150-1154, 13th World Congress on Medical and Health Informatics, Medinfo 2010, Cape Town, South Africa, 9/12/10. https://doi.org/10.3233/978-1-60750-588-4-1150
Sacchi L, D'Ancona G, Bertuzzi F, Bellazzi R. Temporal clustering for blood glucose analysis in the ICU: Identification of groups of patients with different risk profile. In Studies in Health Technology and Informatics. PART 1 ed. Vol. 160. 2010. p. 1150-1154 https://doi.org/10.3233/978-1-60750-588-4-1150
Sacchi, Lucia ; D'Ancona, Giuseppe ; Bertuzzi, Federico ; Bellazzi, Riccardo. / Temporal clustering for blood glucose analysis in the ICU : Identification of groups of patients with different risk profile. Studies in Health Technology and Informatics. Vol. 160 PART 1. ed. 2010. pp. 1150-1154
@inproceedings{a8f99ca1c7444b328a8b76094ca11483,
title = "Temporal clustering for blood glucose analysis in the ICU: Identification of groups of patients with different risk profile",
abstract = "Blood Glucose (BG) analysis and control in critically ill patients became an important research challenge in the last few years. Despite the big improvements that have been achieved both in research and in clinical practice, there are still many aspects that need to be elucidated. A first step towards a better comprehension of the phenomena underlying BG dynamics is represented by the study of retrospectively collected data. In this paper we propose an analysis of blood glucose time series through a combined temporal clustering and standard statistical analysis approach. The ultimate goal of the analysis is the identification of groups of patients showing different BG dynamics and evaluate their risk profiles, which is a very important issue in the Intensive Care Units. The method is applied to a set of patients treated at the Mediterranean Institute for Transplantation and Advanced Specialized Therapies in Palermo, Italy. We show that it is possible to identify two groups based on the initial blood glucose trends, and that the two groups significantly differ in terms of their future BG behaviour.",
keywords = "Blood glucose analysis, Clustering, Intensive care units, Temporal data mining",
author = "Lucia Sacchi and Giuseppe D'Ancona and Federico Bertuzzi and Riccardo Bellazzi",
year = "2010",
doi = "10.3233/978-1-60750-588-4-1150",
language = "English",
isbn = "9781607505877",
volume = "160",
pages = "1150--1154",
booktitle = "Studies in Health Technology and Informatics",
edition = "PART 1",

}

TY - GEN

T1 - Temporal clustering for blood glucose analysis in the ICU

T2 - Identification of groups of patients with different risk profile

AU - Sacchi, Lucia

AU - D'Ancona, Giuseppe

AU - Bertuzzi, Federico

AU - Bellazzi, Riccardo

PY - 2010

Y1 - 2010

N2 - Blood Glucose (BG) analysis and control in critically ill patients became an important research challenge in the last few years. Despite the big improvements that have been achieved both in research and in clinical practice, there are still many aspects that need to be elucidated. A first step towards a better comprehension of the phenomena underlying BG dynamics is represented by the study of retrospectively collected data. In this paper we propose an analysis of blood glucose time series through a combined temporal clustering and standard statistical analysis approach. The ultimate goal of the analysis is the identification of groups of patients showing different BG dynamics and evaluate their risk profiles, which is a very important issue in the Intensive Care Units. The method is applied to a set of patients treated at the Mediterranean Institute for Transplantation and Advanced Specialized Therapies in Palermo, Italy. We show that it is possible to identify two groups based on the initial blood glucose trends, and that the two groups significantly differ in terms of their future BG behaviour.

AB - Blood Glucose (BG) analysis and control in critically ill patients became an important research challenge in the last few years. Despite the big improvements that have been achieved both in research and in clinical practice, there are still many aspects that need to be elucidated. A first step towards a better comprehension of the phenomena underlying BG dynamics is represented by the study of retrospectively collected data. In this paper we propose an analysis of blood glucose time series through a combined temporal clustering and standard statistical analysis approach. The ultimate goal of the analysis is the identification of groups of patients showing different BG dynamics and evaluate their risk profiles, which is a very important issue in the Intensive Care Units. The method is applied to a set of patients treated at the Mediterranean Institute for Transplantation and Advanced Specialized Therapies in Palermo, Italy. We show that it is possible to identify two groups based on the initial blood glucose trends, and that the two groups significantly differ in terms of their future BG behaviour.

KW - Blood glucose analysis

KW - Clustering

KW - Intensive care units

KW - Temporal data mining

UR - http://www.scopus.com/inward/record.url?scp=78649513746&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=78649513746&partnerID=8YFLogxK

U2 - 10.3233/978-1-60750-588-4-1150

DO - 10.3233/978-1-60750-588-4-1150

M3 - Conference contribution

C2 - 20841864

AN - SCOPUS:78649513746

SN - 9781607505877

VL - 160

SP - 1150

EP - 1154

BT - Studies in Health Technology and Informatics

ER -