Multistage fusion approaches based on a generative model and multivariate exponentially weighted moving average for diagnosis of cardiovascular autonomic nerve dysfunction

Mohammad Mehedi Hassan, Shamsul Huda, John Yearwood, Herbert F. Jelinek, Ahmad Almogren

Research output: Contribution to journalArticle

  • 5 Citations

Abstract

Like many medical diagnoses, clinical decision support system (CDSS) is essential to diagnose the cardiovascular autonomic neuropathy (CAN). However, diagnosis of CAN using the traditional ‘Ewing battery test’ becomes very difficult due to the inherent imbalanced and incompleteness condition in the collected clinical data. This influences the health professionals to investigate other related diagnostic reports of patients, including Electrocardiogram (ECG) data from ECG sensors, blood chemistry, podiatry and endocrinology features. However, additional components increase the dimensionality of the feature set as well as its heterogeneity and modality in the clinical data which may limit the applications of traditional data mining approaches for an accurate diagnosis of CAN in the CDSS. To address the aforementioned problem, in this paper, we have proposed, a novel multistage fusion approach based on a generative model and a statistical process control (SPC) technique to diagnose CAN more accurately. The proposed approach develops two different generative models by using a shared and a separated Independent Component Analysis (ICA) to overcome the incompleteness and modality of the data. Due to the heterogeneous and non-normality features, statistical correlations and multivariate control limits in relation to the CAN diagnosis parameters are determined by fusioning of a series of exponentially weighted moving average (MEWMA) control processes. Fusioned features from both component analyses and SPC are applied in an ensemble classification system. The proposed multistage fusion approach is experimentally verified to justify its performance by using a large dataset collected from the diabetes screening research initiative (DiScRi) project at Charles Sturt University, NSW, Australia. Our comprehensive experimental results show that the proposed fusion approach performs better than the standard classifier for both ‘Ewing’ feature set and ‘Ewing and additional feature set’ with significant improvement in accuracy.

LanguageEnglish
Pages105-118
Number of pages14
JournalInformation Fusion
Volume41
Early online dateAug 2017
DOIs
Publication statusPublished - 01 May 2018

Fingerprint

Fusion reactions
Statistical process control
Decision support systems
Electrocardiography
Endocrinology
Independent component analysis
Medical problems
Data mining
Screening
Blood
Classifiers
Health
Sensors

Cite this

@article{aa4dc45861e04a8fa89a8e3b54886fd4,
title = "Multistage fusion approaches based on a generative model and multivariate exponentially weighted moving average for diagnosis of cardiovascular autonomic nerve dysfunction",
abstract = "Like many medical diagnoses, clinical decision support system (CDSS) is essential to diagnose the cardiovascular autonomic neuropathy (CAN). However, diagnosis of CAN using the traditional ‘Ewing battery test’ becomes very difficult due to the inherent imbalanced and incompleteness condition in the collected clinical data. This influences the health professionals to investigate other related diagnostic reports of patients, including Electrocardiogram (ECG) data from ECG sensors, blood chemistry, podiatry and endocrinology features. However, additional components increase the dimensionality of the feature set as well as its heterogeneity and modality in the clinical data which may limit the applications of traditional data mining approaches for an accurate diagnosis of CAN in the CDSS. To address the aforementioned problem, in this paper, we have proposed, a novel multistage fusion approach based on a generative model and a statistical process control (SPC) technique to diagnose CAN more accurately. The proposed approach develops two different generative models by using a shared and a separated Independent Component Analysis (ICA) to overcome the incompleteness and modality of the data. Due to the heterogeneous and non-normality features, statistical correlations and multivariate control limits in relation to the CAN diagnosis parameters are determined by fusioning of a series of exponentially weighted moving average (MEWMA) control processes. Fusioned features from both component analyses and SPC are applied in an ensemble classification system. The proposed multistage fusion approach is experimentally verified to justify its performance by using a large dataset collected from the diabetes screening research initiative (DiScRi) project at Charles Sturt University, NSW, Australia. Our comprehensive experimental results show that the proposed fusion approach performs better than the standard classifier for both ‘Ewing’ feature set and ‘Ewing and additional feature set’ with significant improvement in accuracy.",
keywords = "Autonomic nerve dysfunction classification, Blind source separation, Fusion of features and decisions, Fusion of multiple statistical process control techniques, Multivariate exponentially weighted moving average",
author = "Hassan, {Mohammad Mehedi} and Shamsul Huda and John Yearwood and Jelinek, {Herbert F.} and Ahmad Almogren",
year = "2018",
month = "5",
day = "1",
doi = "10.1016/j.inffus.2017.08.004",
language = "English",
volume = "41",
pages = "105--118",
journal = "Information Fusion",
issn = "1566-2535",
publisher = "Elsevier",

}

Multistage fusion approaches based on a generative model and multivariate exponentially weighted moving average for diagnosis of cardiovascular autonomic nerve dysfunction. / Hassan, Mohammad Mehedi; Huda, Shamsul; Yearwood, John; Jelinek, Herbert F.; Almogren, Ahmad.

In: Information Fusion, Vol. 41, 01.05.2018, p. 105-118.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Multistage fusion approaches based on a generative model and multivariate exponentially weighted moving average for diagnosis of cardiovascular autonomic nerve dysfunction

AU - Hassan, Mohammad Mehedi

AU - Huda, Shamsul

AU - Yearwood, John

AU - Jelinek, Herbert F.

AU - Almogren, Ahmad

PY - 2018/5/1

Y1 - 2018/5/1

N2 - Like many medical diagnoses, clinical decision support system (CDSS) is essential to diagnose the cardiovascular autonomic neuropathy (CAN). However, diagnosis of CAN using the traditional ‘Ewing battery test’ becomes very difficult due to the inherent imbalanced and incompleteness condition in the collected clinical data. This influences the health professionals to investigate other related diagnostic reports of patients, including Electrocardiogram (ECG) data from ECG sensors, blood chemistry, podiatry and endocrinology features. However, additional components increase the dimensionality of the feature set as well as its heterogeneity and modality in the clinical data which may limit the applications of traditional data mining approaches for an accurate diagnosis of CAN in the CDSS. To address the aforementioned problem, in this paper, we have proposed, a novel multistage fusion approach based on a generative model and a statistical process control (SPC) technique to diagnose CAN more accurately. The proposed approach develops two different generative models by using a shared and a separated Independent Component Analysis (ICA) to overcome the incompleteness and modality of the data. Due to the heterogeneous and non-normality features, statistical correlations and multivariate control limits in relation to the CAN diagnosis parameters are determined by fusioning of a series of exponentially weighted moving average (MEWMA) control processes. Fusioned features from both component analyses and SPC are applied in an ensemble classification system. The proposed multistage fusion approach is experimentally verified to justify its performance by using a large dataset collected from the diabetes screening research initiative (DiScRi) project at Charles Sturt University, NSW, Australia. Our comprehensive experimental results show that the proposed fusion approach performs better than the standard classifier for both ‘Ewing’ feature set and ‘Ewing and additional feature set’ with significant improvement in accuracy.

AB - Like many medical diagnoses, clinical decision support system (CDSS) is essential to diagnose the cardiovascular autonomic neuropathy (CAN). However, diagnosis of CAN using the traditional ‘Ewing battery test’ becomes very difficult due to the inherent imbalanced and incompleteness condition in the collected clinical data. This influences the health professionals to investigate other related diagnostic reports of patients, including Electrocardiogram (ECG) data from ECG sensors, blood chemistry, podiatry and endocrinology features. However, additional components increase the dimensionality of the feature set as well as its heterogeneity and modality in the clinical data which may limit the applications of traditional data mining approaches for an accurate diagnosis of CAN in the CDSS. To address the aforementioned problem, in this paper, we have proposed, a novel multistage fusion approach based on a generative model and a statistical process control (SPC) technique to diagnose CAN more accurately. The proposed approach develops two different generative models by using a shared and a separated Independent Component Analysis (ICA) to overcome the incompleteness and modality of the data. Due to the heterogeneous and non-normality features, statistical correlations and multivariate control limits in relation to the CAN diagnosis parameters are determined by fusioning of a series of exponentially weighted moving average (MEWMA) control processes. Fusioned features from both component analyses and SPC are applied in an ensemble classification system. The proposed multistage fusion approach is experimentally verified to justify its performance by using a large dataset collected from the diabetes screening research initiative (DiScRi) project at Charles Sturt University, NSW, Australia. Our comprehensive experimental results show that the proposed fusion approach performs better than the standard classifier for both ‘Ewing’ feature set and ‘Ewing and additional feature set’ with significant improvement in accuracy.

KW - Autonomic nerve dysfunction classification

KW - Blind source separation

KW - Fusion of features and decisions

KW - Fusion of multiple statistical process control techniques

KW - Multivariate exponentially weighted moving average

UR - http://www.scopus.com/inward/record.url?scp=85028998217&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85028998217&partnerID=8YFLogxK

U2 - 10.1016/j.inffus.2017.08.004

DO - 10.1016/j.inffus.2017.08.004

M3 - Article

VL - 41

SP - 105

EP - 118

JO - Information Fusion

T2 - Information Fusion

JF - Information Fusion

SN - 1566-2535

ER -