H-EQPE model and L-checkpoint algorithm: A decision-guidance approach for detecting hypoglycemia of diabetes patients

Chun-kit Ngan, Lin Li

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

The authors propose a Hypoglycemic Expert Query Parametric Estimation (H-EQPE) model and a Linear Checkpoint (L-Checkpoint) algorithm to detect hypoglycemia of diabetes patients. The proposed approach combines the strengths of both domain-knowledge-based and machine-learning-based approaches to learn the optimal decision parameter over time series for monitoring the symptoms, in which the objective function (i.e., the maximal number of detections of hypoglycemia) is dependent on the optimal time point from which the parameter is learned. To evaluate the approach, the authors conducted an experiment on a dataset from the Diabetes Research in Children Network group. The L-Checkpoint algorithm learned the optimal monitoring decision parameter, 99 mg/dL, and achieved the maximal number of detections of hypoglycemic symptoms. The experiment shows that the proposed approach produces the results that are superior to those of the domain-knowledge-based and the machine-learning-based approaches, resulting in a 99.2% accuracy, 100% sensitivity, and 98.8% specificity.

Original languageEnglish (US)
Pages (from-to)20-35
Number of pages16
JournalInternational Journal of Decision Support System Technology
Volume7
Issue number4
DOIs
StatePublished - Oct 1 2015

Fingerprint

Parametric Estimation
Checkpoint
Diabetes
Medical problems
Guidance
Learning systems
Domain Knowledge
Query
Knowledge-based
Monitoring
Machine Learning
Time series
Experiments
Specificity
Experiment
Objective function
Model
Dependent
Evaluate

All Science Journal Classification (ASJC) codes

  • Computer Science(all)
  • Modeling and Simulation

Cite this

@article{1d445f4d89bd42f29b4cb1c45f41bc41,
title = "H-EQPE model and L-checkpoint algorithm: A decision-guidance approach for detecting hypoglycemia of diabetes patients",
abstract = "The authors propose a Hypoglycemic Expert Query Parametric Estimation (H-EQPE) model and a Linear Checkpoint (L-Checkpoint) algorithm to detect hypoglycemia of diabetes patients. The proposed approach combines the strengths of both domain-knowledge-based and machine-learning-based approaches to learn the optimal decision parameter over time series for monitoring the symptoms, in which the objective function (i.e., the maximal number of detections of hypoglycemia) is dependent on the optimal time point from which the parameter is learned. To evaluate the approach, the authors conducted an experiment on a dataset from the Diabetes Research in Children Network group. The L-Checkpoint algorithm learned the optimal monitoring decision parameter, 99 mg/dL, and achieved the maximal number of detections of hypoglycemic symptoms. The experiment shows that the proposed approach produces the results that are superior to those of the domain-knowledge-based and the machine-learning-based approaches, resulting in a 99.2{\%} accuracy, 100{\%} sensitivity, and 98.8{\%} specificity.",
author = "Chun-kit Ngan and Lin Li",
year = "2015",
month = "10",
day = "1",
doi = "10.4018/IJDSST.2015100102",
language = "English (US)",
volume = "7",
pages = "20--35",
journal = "International Journal of Decision Support System Technology",
issn = "1941-6296",
publisher = "IGI Global Publishing",
number = "4",

}

H-EQPE model and L-checkpoint algorithm : A decision-guidance approach for detecting hypoglycemia of diabetes patients. / Ngan, Chun-kit; Li, Lin.

In: International Journal of Decision Support System Technology, Vol. 7, No. 4, 01.10.2015, p. 20-35.

Research output: Contribution to journalArticle

TY - JOUR

T1 - H-EQPE model and L-checkpoint algorithm

T2 - A decision-guidance approach for detecting hypoglycemia of diabetes patients

AU - Ngan, Chun-kit

AU - Li, Lin

PY - 2015/10/1

Y1 - 2015/10/1

N2 - The authors propose a Hypoglycemic Expert Query Parametric Estimation (H-EQPE) model and a Linear Checkpoint (L-Checkpoint) algorithm to detect hypoglycemia of diabetes patients. The proposed approach combines the strengths of both domain-knowledge-based and machine-learning-based approaches to learn the optimal decision parameter over time series for monitoring the symptoms, in which the objective function (i.e., the maximal number of detections of hypoglycemia) is dependent on the optimal time point from which the parameter is learned. To evaluate the approach, the authors conducted an experiment on a dataset from the Diabetes Research in Children Network group. The L-Checkpoint algorithm learned the optimal monitoring decision parameter, 99 mg/dL, and achieved the maximal number of detections of hypoglycemic symptoms. The experiment shows that the proposed approach produces the results that are superior to those of the domain-knowledge-based and the machine-learning-based approaches, resulting in a 99.2% accuracy, 100% sensitivity, and 98.8% specificity.

AB - The authors propose a Hypoglycemic Expert Query Parametric Estimation (H-EQPE) model and a Linear Checkpoint (L-Checkpoint) algorithm to detect hypoglycemia of diabetes patients. The proposed approach combines the strengths of both domain-knowledge-based and machine-learning-based approaches to learn the optimal decision parameter over time series for monitoring the symptoms, in which the objective function (i.e., the maximal number of detections of hypoglycemia) is dependent on the optimal time point from which the parameter is learned. To evaluate the approach, the authors conducted an experiment on a dataset from the Diabetes Research in Children Network group. The L-Checkpoint algorithm learned the optimal monitoring decision parameter, 99 mg/dL, and achieved the maximal number of detections of hypoglycemic symptoms. The experiment shows that the proposed approach produces the results that are superior to those of the domain-knowledge-based and the machine-learning-based approaches, resulting in a 99.2% accuracy, 100% sensitivity, and 98.8% specificity.

UR - http://www.scopus.com/inward/record.url?scp=84958977117&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84958977117&partnerID=8YFLogxK

U2 - 10.4018/IJDSST.2015100102

DO - 10.4018/IJDSST.2015100102

M3 - Article

AN - SCOPUS:84958977117

VL - 7

SP - 20

EP - 35

JO - International Journal of Decision Support System Technology

JF - International Journal of Decision Support System Technology

SN - 1941-6296

IS - 4

ER -