Neural-network classification of cardiac disease from 31p cardiovascular magnetic resonance spectroscopy measures of creatine kinase energy metabolism

Research output: Contribution to journalArticle

Abstract

Background: The heart's energy demand per gram of tissue is the body's highest and creatine kinase (CK) metabolism, its primary energy reserve, is compromised in common heart diseases. Here, neural-network analysis is used to test whether noninvasive phosphorus (31P) cardiovascular magnetic resonance spectroscopy (CMRS) measurements of cardiac adenosine triphosphate (ATP) energy, phosphocreatine (PCr), the first-order CK reaction rate kf, and the rate of ATP synthesis through CK (CK flux), can predict specific human heart disease and clinical severity. Methods: The data comprised the extant 178 complete sets of PCr and ATP concentrations, kf, and CK flux data from human CMRS studies performed on clinical 1.5 and 3 Tesla scanners. Healthy subjects and patients with nonischemic cardiomyopathy, dilated (DCM) or hypertrophic disease, New York Heart Association (NYHA) class I-IV heart failure (HF), or with anterior myocardial infarction are included. Three-layer neural-networks were created to classify disease and to differentiate DCM, hypertrophy and clinical NYHA class in HF patients using leave-one-out training. Network performance was assessed using 'confusion matrices' and 'area-under-the-curve' (AUC) analyses of 'receiver operating curves'. Possible methodological bias and network imbalance were tested by segregating 1.5 and 3 Tesla data, and by data augmentation by random interpolation of nearest neighbors, respectively. Results: The network differentiated healthy, HF and non-HF cardiac disease with an overall accuracy of 84% and AUC > 90% for each category using the four CK metabolic parameters, alone. HF patients with DCM, hypertrophy, and different NYHA severity were differentiated with ~ 80% overall accuracy independent of CMRS methodology. Conclusions: While sample-size was limited in some sub-classes, a neural network classifier applied to noninvasive cardiac 31P CMRS data, could serve as a metabolic biomarker for common disease types and HF severity with clinically-relevant accuracy. Moreover, the network's ability to individually classify disease and HF severity using CK metabolism alone, implies an intimate relationship between CK metabolism and disease, with subtle underlying phenotypic differences that enable their differentiation. Trial registration: ClinicalTrials.gov Identifier: NCT00181259.

Original languageEnglish (US)
Article number49
JournalJournal of Cardiovascular Magnetic Resonance
Volume21
Issue number1
DOIs
StatePublished - Aug 12 2019

Fingerprint

Creatine Kinase
Energy Metabolism
Heart Diseases
Magnetic Resonance Spectroscopy
Heart Failure
Phosphocreatine
Adenosine Triphosphate
Hypertrophy
Area Under Curve
Hypertrophic Cardiomyopathy
Dilated Cardiomyopathy
Sample Size
Phosphorus
Healthy Volunteers
Biomarkers
Myocardial Infarction

Keywords

  • Biomarker
  • Cardiac metabolism
  • Heart failure
  • Neural network
  • Phosphorus spectroscopy
  • Translational studies

ASJC Scopus subject areas

  • Radiological and Ultrasound Technology
  • Radiology Nuclear Medicine and imaging
  • Cardiology and Cardiovascular Medicine
  • Family Practice

Cite this

@article{58835b41bb004de18ad089c0a9b2ff70,
title = "Neural-network classification of cardiac disease from 31p cardiovascular magnetic resonance spectroscopy measures of creatine kinase energy metabolism",
abstract = "Background: The heart's energy demand per gram of tissue is the body's highest and creatine kinase (CK) metabolism, its primary energy reserve, is compromised in common heart diseases. Here, neural-network analysis is used to test whether noninvasive phosphorus (31P) cardiovascular magnetic resonance spectroscopy (CMRS) measurements of cardiac adenosine triphosphate (ATP) energy, phosphocreatine (PCr), the first-order CK reaction rate kf, and the rate of ATP synthesis through CK (CK flux), can predict specific human heart disease and clinical severity. Methods: The data comprised the extant 178 complete sets of PCr and ATP concentrations, kf, and CK flux data from human CMRS studies performed on clinical 1.5 and 3 Tesla scanners. Healthy subjects and patients with nonischemic cardiomyopathy, dilated (DCM) or hypertrophic disease, New York Heart Association (NYHA) class I-IV heart failure (HF), or with anterior myocardial infarction are included. Three-layer neural-networks were created to classify disease and to differentiate DCM, hypertrophy and clinical NYHA class in HF patients using leave-one-out training. Network performance was assessed using 'confusion matrices' and 'area-under-the-curve' (AUC) analyses of 'receiver operating curves'. Possible methodological bias and network imbalance were tested by segregating 1.5 and 3 Tesla data, and by data augmentation by random interpolation of nearest neighbors, respectively. Results: The network differentiated healthy, HF and non-HF cardiac disease with an overall accuracy of 84{\%} and AUC > 90{\%} for each category using the four CK metabolic parameters, alone. HF patients with DCM, hypertrophy, and different NYHA severity were differentiated with ~ 80{\%} overall accuracy independent of CMRS methodology. Conclusions: While sample-size was limited in some sub-classes, a neural network classifier applied to noninvasive cardiac 31P CMRS data, could serve as a metabolic biomarker for common disease types and HF severity with clinically-relevant accuracy. Moreover, the network's ability to individually classify disease and HF severity using CK metabolism alone, implies an intimate relationship between CK metabolism and disease, with subtle underlying phenotypic differences that enable their differentiation. Trial registration: ClinicalTrials.gov Identifier: NCT00181259.",
keywords = "Biomarker, Cardiac metabolism, Heart failure, Neural network, Phosphorus spectroscopy, Translational studies",
author = "Meiyappan Solaiyappan and Weiss, {Robert George} and Bottomley, {Paul A}",
year = "2019",
month = "8",
day = "12",
doi = "10.1186/s12968-019-0560-5",
language = "English (US)",
volume = "21",
journal = "Journal of Cardiovascular Magnetic Resonance",
issn = "1097-6647",
publisher = "BioMed Central",
number = "1",

}

TY - JOUR

T1 - Neural-network classification of cardiac disease from 31p cardiovascular magnetic resonance spectroscopy measures of creatine kinase energy metabolism

AU - Solaiyappan, Meiyappan

AU - Weiss, Robert George

AU - Bottomley, Paul A

PY - 2019/8/12

Y1 - 2019/8/12

N2 - Background: The heart's energy demand per gram of tissue is the body's highest and creatine kinase (CK) metabolism, its primary energy reserve, is compromised in common heart diseases. Here, neural-network analysis is used to test whether noninvasive phosphorus (31P) cardiovascular magnetic resonance spectroscopy (CMRS) measurements of cardiac adenosine triphosphate (ATP) energy, phosphocreatine (PCr), the first-order CK reaction rate kf, and the rate of ATP synthesis through CK (CK flux), can predict specific human heart disease and clinical severity. Methods: The data comprised the extant 178 complete sets of PCr and ATP concentrations, kf, and CK flux data from human CMRS studies performed on clinical 1.5 and 3 Tesla scanners. Healthy subjects and patients with nonischemic cardiomyopathy, dilated (DCM) or hypertrophic disease, New York Heart Association (NYHA) class I-IV heart failure (HF), or with anterior myocardial infarction are included. Three-layer neural-networks were created to classify disease and to differentiate DCM, hypertrophy and clinical NYHA class in HF patients using leave-one-out training. Network performance was assessed using 'confusion matrices' and 'area-under-the-curve' (AUC) analyses of 'receiver operating curves'. Possible methodological bias and network imbalance were tested by segregating 1.5 and 3 Tesla data, and by data augmentation by random interpolation of nearest neighbors, respectively. Results: The network differentiated healthy, HF and non-HF cardiac disease with an overall accuracy of 84% and AUC > 90% for each category using the four CK metabolic parameters, alone. HF patients with DCM, hypertrophy, and different NYHA severity were differentiated with ~ 80% overall accuracy independent of CMRS methodology. Conclusions: While sample-size was limited in some sub-classes, a neural network classifier applied to noninvasive cardiac 31P CMRS data, could serve as a metabolic biomarker for common disease types and HF severity with clinically-relevant accuracy. Moreover, the network's ability to individually classify disease and HF severity using CK metabolism alone, implies an intimate relationship between CK metabolism and disease, with subtle underlying phenotypic differences that enable their differentiation. Trial registration: ClinicalTrials.gov Identifier: NCT00181259.

AB - Background: The heart's energy demand per gram of tissue is the body's highest and creatine kinase (CK) metabolism, its primary energy reserve, is compromised in common heart diseases. Here, neural-network analysis is used to test whether noninvasive phosphorus (31P) cardiovascular magnetic resonance spectroscopy (CMRS) measurements of cardiac adenosine triphosphate (ATP) energy, phosphocreatine (PCr), the first-order CK reaction rate kf, and the rate of ATP synthesis through CK (CK flux), can predict specific human heart disease and clinical severity. Methods: The data comprised the extant 178 complete sets of PCr and ATP concentrations, kf, and CK flux data from human CMRS studies performed on clinical 1.5 and 3 Tesla scanners. Healthy subjects and patients with nonischemic cardiomyopathy, dilated (DCM) or hypertrophic disease, New York Heart Association (NYHA) class I-IV heart failure (HF), or with anterior myocardial infarction are included. Three-layer neural-networks were created to classify disease and to differentiate DCM, hypertrophy and clinical NYHA class in HF patients using leave-one-out training. Network performance was assessed using 'confusion matrices' and 'area-under-the-curve' (AUC) analyses of 'receiver operating curves'. Possible methodological bias and network imbalance were tested by segregating 1.5 and 3 Tesla data, and by data augmentation by random interpolation of nearest neighbors, respectively. Results: The network differentiated healthy, HF and non-HF cardiac disease with an overall accuracy of 84% and AUC > 90% for each category using the four CK metabolic parameters, alone. HF patients with DCM, hypertrophy, and different NYHA severity were differentiated with ~ 80% overall accuracy independent of CMRS methodology. Conclusions: While sample-size was limited in some sub-classes, a neural network classifier applied to noninvasive cardiac 31P CMRS data, could serve as a metabolic biomarker for common disease types and HF severity with clinically-relevant accuracy. Moreover, the network's ability to individually classify disease and HF severity using CK metabolism alone, implies an intimate relationship between CK metabolism and disease, with subtle underlying phenotypic differences that enable their differentiation. Trial registration: ClinicalTrials.gov Identifier: NCT00181259.

KW - Biomarker

KW - Cardiac metabolism

KW - Heart failure

KW - Neural network

KW - Phosphorus spectroscopy

KW - Translational studies

UR - http://www.scopus.com/inward/record.url?scp=85070636242&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85070636242&partnerID=8YFLogxK

U2 - 10.1186/s12968-019-0560-5

DO - 10.1186/s12968-019-0560-5

M3 - Article

C2 - 31401975

AN - SCOPUS:85070636242

VL - 21

JO - Journal of Cardiovascular Magnetic Resonance

JF - Journal of Cardiovascular Magnetic Resonance

SN - 1097-6647

IS - 1

M1 - 49

ER -