PMID- 31401975
OWN - NLM
STAT- MEDLINE
DCOM- 20200504
LR  - 20240117
IS  - 1532-429X (Electronic)
IS  - 1097-6647 (Print)
IS  - 1097-6647 (Linking)
VI  - 21
IP  - 1
DP  - 2019 Aug 12
TI  - Neural-network classification of cardiac disease from (31)P cardiovascular 
      magnetic resonance spectroscopy measures of creatine kinase energy metabolism.
PG  - 49
LID - 10.1186/s12968-019-0560-5 [doi]
LID - 49
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 ((31)P) cardiovascular magnetic resonance spectroscopy 
      (CMRS) measurements of cardiac adenosine triphosphate (ATP) energy, 
      phosphocreatine (PCr), the first-order CK reaction rate k(f), 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, k(f), 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 (31)P 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.
FAU - Solaiyappan, Meiyappan
AU  - Solaiyappan M
AD  - Division of MR Research, Department of Radiology, Johns Hopkins School of 
      Medicine, Park Bldg. 310, 600 N Wolfe St, Baltimore, MD, 21287, USA.
FAU - Weiss, Robert G
AU  - Weiss RG
AD  - Division of Cardiology, Department of Medicine, Johns Hopkins University, School 
      of Medicine, Baltimore, MD, USA.
FAU - Bottomley, Paul A
AU  - Bottomley PA
AUID- ORCID: 0000-0002-0071-0155
AD  - Division of MR Research, Department of Radiology, Johns Hopkins School of 
      Medicine, Park Bldg. 310, 600 N Wolfe St, Baltimore, MD, 21287, USA. 
      bottoml@mri.jhu.edu.
LA  - eng
SI  - ClinicalTrials.gov/NCT00181259
GR  - R01 HL061912/HL/NHLBI NIH HHS/United States
GR  - R01HL61912/GF/NIH HHS/United States
PT  - Journal Article
PT  - Research Support, N.I.H., Extramural
PT  - Research Support, Non-U.S. Gov't
DEP - 20190812
PL  - England
TA  - J Cardiovasc Magn Reson
JT  - Journal of cardiovascular magnetic resonance : official journal of the Society 
      for Cardiovascular Magnetic Resonance
JID - 9815616
RN  - 0 (Biomarkers)
RN  - 0 (Phosphorus Isotopes)
RN  - 020IUV4N33 (Phosphocreatine)
RN  - 8L70Q75FXE (Adenosine Triphosphate)
RN  - EC 2.7.3.2 (Creatine Kinase)
SB  - IM
MH  - Adenosine Triphosphate/metabolism
MH  - Adult
MH  - Aged
MH  - Aged, 80 and over
MH  - Biomarkers/blood
MH  - Creatine Kinase/*metabolism
MH  - *Energy Metabolism
MH  - Female
MH  - Heart Diseases/classification/*diagnosis/enzymology
MH  - Humans
MH  - Kinetics
MH  - *Machine Learning
MH  - *Magnetic Resonance Spectroscopy
MH  - Male
MH  - Middle Aged
MH  - Myocardium/*enzymology
MH  - *Neural Networks, Computer
MH  - Phosphocreatine/metabolism
MH  - Phosphorus Isotopes
MH  - Predictive Value of Tests
MH  - Reproducibility of Results
MH  - Severity of Illness Index
MH  - Young Adult
PMC - PMC6689869
OTO - NOTNLM
OT  - Biomarker
OT  - Cardiac metabolism
OT  - Heart failure
OT  - Neural network
OT  - Phosphorus spectroscopy
OT  - Translational studies
COIS- The authors declare that they have no competing interests.
EDAT- 2019/08/14 06:00
MHDA- 2020/05/06 06:00
PMCR- 2019/08/12
CRDT- 2019/08/13 06:00
PHST- 2018/11/05 00:00 [received]
PHST- 2019/07/01 00:00 [accepted]
PHST- 2019/08/13 06:00 [entrez]
PHST- 2019/08/14 06:00 [pubmed]
PHST- 2020/05/06 06:00 [medline]
PHST- 2019/08/12 00:00 [pmc-release]
AID - S1097-6647(23)00222-3 [pii]
AID - 560 [pii]
AID - 10.1186/s12968-019-0560-5 [doi]
PST - epublish
SO  - J Cardiovasc Magn Reson. 2019 Aug 12;21(1):49. doi: 10.1186/s12968-019-0560-5.