Plasma fatty acid profile as biomarker of coronary artery disease: A pilot study using fourth generation artificial neural networks

E. Dozio, E. Vianello, E. Grossi, L. Menicanti, G. Schmitz, M. M. Corsi Romanelli

Research output: Contribution to journalArticle

Abstract

Many studies, focused on identifying new biomarkers for coronary artery disease (CAD) risk computation and monitoring, suggested a potential diagnostic role for fatty acids (FA). In the present study, we explored the potential diagnostic role of FA by using a data mining approach based on fourth generation artificial neural networks (ANN). Forty-one male subjects were enrolled. According to coronary angiography, 31 displayed CAD and 10 did not (non-CAD, control group). FA analysis was performed on plasma samples using a gas chromatography-mass spectrometry system and analyses were performed by an ANN method. The variables most closely related to CAD were low levels of alpha-linolenic acid, eicosapentaenoic acid, eicosatetraenoic and docosahexaenoic acids. High levels of 1,1-dimethoxyhexadecane, total dimethyl acetals and docosatetraenoic acid were related to non-CAD condition. This subset of variables, which were most closely correlated to the target diagnosis, achieved a consistent predictive rate. The average accuracy obtained was 76.5%, with 93% of sensitivity and 60% of specificity. The area under the ROC curve was equal to 0.79. In conclusion, our study highlighted the association between different plasma FA species, CAD and non-CAD conditions. The specific subset of variables could be of interest as a new diagnostic tool for CAD management.

Original languageEnglish
Pages (from-to)1007-1013
Number of pages7
JournalJournal of Biological Regulators and Homeostatic Agents
Volume32
Issue number4
Publication statusPublished - Jul 1 2018

Fingerprint

Coronary Artery Disease
Fatty Acids
Biomarkers
Arteries
Arachidonic Acids
alpha-Linolenic Acid
Eicosapentaenoic Acid
Data Mining
Docosahexaenoic Acids
Disease Management
Systems Analysis
Coronary Angiography
ROC Curve
Gas Chromatography-Mass Spectrometry
Area Under Curve
Sensitivity and Specificity
Control Groups
Acids

ASJC Scopus subject areas

  • Endocrinology, Diabetes and Metabolism
  • Immunology and Allergy
  • Physiology
  • Immunology
  • Oncology
  • Endocrinology
  • Physiology (medical)
  • Cancer Research

Cite this

@article{582752eca65d42b389d84a5cc4d77afa,
title = "Plasma fatty acid profile as biomarker of coronary artery disease: A pilot study using fourth generation artificial neural networks",
abstract = "Many studies, focused on identifying new biomarkers for coronary artery disease (CAD) risk computation and monitoring, suggested a potential diagnostic role for fatty acids (FA). In the present study, we explored the potential diagnostic role of FA by using a data mining approach based on fourth generation artificial neural networks (ANN). Forty-one male subjects were enrolled. According to coronary angiography, 31 displayed CAD and 10 did not (non-CAD, control group). FA analysis was performed on plasma samples using a gas chromatography-mass spectrometry system and analyses were performed by an ANN method. The variables most closely related to CAD were low levels of alpha-linolenic acid, eicosapentaenoic acid, eicosatetraenoic and docosahexaenoic acids. High levels of 1,1-dimethoxyhexadecane, total dimethyl acetals and docosatetraenoic acid were related to non-CAD condition. This subset of variables, which were most closely correlated to the target diagnosis, achieved a consistent predictive rate. The average accuracy obtained was 76.5{\%}, with 93{\%} of sensitivity and 60{\%} of specificity. The area under the ROC curve was equal to 0.79. In conclusion, our study highlighted the association between different plasma FA species, CAD and non-CAD conditions. The specific subset of variables could be of interest as a new diagnostic tool for CAD management.",
author = "E. Dozio and E. Vianello and E. Grossi and L. Menicanti and G. Schmitz and {Corsi Romanelli}, {M. M.}",
year = "2018",
month = "7",
day = "1",
language = "English",
volume = "32",
pages = "1007--1013",
journal = "Journal of Biological Regulators and Homeostatic Agents",
issn = "0393-974X",
publisher = "Biolife s.a.s.",
number = "4",

}

TY - JOUR

T1 - Plasma fatty acid profile as biomarker of coronary artery disease

T2 - A pilot study using fourth generation artificial neural networks

AU - Dozio, E.

AU - Vianello, E.

AU - Grossi, E.

AU - Menicanti, L.

AU - Schmitz, G.

AU - Corsi Romanelli, M. M.

PY - 2018/7/1

Y1 - 2018/7/1

N2 - Many studies, focused on identifying new biomarkers for coronary artery disease (CAD) risk computation and monitoring, suggested a potential diagnostic role for fatty acids (FA). In the present study, we explored the potential diagnostic role of FA by using a data mining approach based on fourth generation artificial neural networks (ANN). Forty-one male subjects were enrolled. According to coronary angiography, 31 displayed CAD and 10 did not (non-CAD, control group). FA analysis was performed on plasma samples using a gas chromatography-mass spectrometry system and analyses were performed by an ANN method. The variables most closely related to CAD were low levels of alpha-linolenic acid, eicosapentaenoic acid, eicosatetraenoic and docosahexaenoic acids. High levels of 1,1-dimethoxyhexadecane, total dimethyl acetals and docosatetraenoic acid were related to non-CAD condition. This subset of variables, which were most closely correlated to the target diagnosis, achieved a consistent predictive rate. The average accuracy obtained was 76.5%, with 93% of sensitivity and 60% of specificity. The area under the ROC curve was equal to 0.79. In conclusion, our study highlighted the association between different plasma FA species, CAD and non-CAD conditions. The specific subset of variables could be of interest as a new diagnostic tool for CAD management.

AB - Many studies, focused on identifying new biomarkers for coronary artery disease (CAD) risk computation and monitoring, suggested a potential diagnostic role for fatty acids (FA). In the present study, we explored the potential diagnostic role of FA by using a data mining approach based on fourth generation artificial neural networks (ANN). Forty-one male subjects were enrolled. According to coronary angiography, 31 displayed CAD and 10 did not (non-CAD, control group). FA analysis was performed on plasma samples using a gas chromatography-mass spectrometry system and analyses were performed by an ANN method. The variables most closely related to CAD were low levels of alpha-linolenic acid, eicosapentaenoic acid, eicosatetraenoic and docosahexaenoic acids. High levels of 1,1-dimethoxyhexadecane, total dimethyl acetals and docosatetraenoic acid were related to non-CAD condition. This subset of variables, which were most closely correlated to the target diagnosis, achieved a consistent predictive rate. The average accuracy obtained was 76.5%, with 93% of sensitivity and 60% of specificity. The area under the ROC curve was equal to 0.79. In conclusion, our study highlighted the association between different plasma FA species, CAD and non-CAD conditions. The specific subset of variables could be of interest as a new diagnostic tool for CAD management.

UR - http://www.scopus.com/inward/record.url?scp=85050605090&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85050605090&partnerID=8YFLogxK

M3 - Article

AN - SCOPUS:85050605090

VL - 32

SP - 1007

EP - 1013

JO - Journal of Biological Regulators and Homeostatic Agents

JF - Journal of Biological Regulators and Homeostatic Agents

SN - 0393-974X

IS - 4

ER -