NMRES

An artificial intelligence expert system for quantification of cardiac metabolites from31phosphorus nuclear magnetic resonance spectroscopy

John L. Chow, Karl N. Levitt, Gerald J Kost

Research output: Contribution to journalArticle

3 Citations (Scopus)

Abstract

The application of high-resolution31Phosphorus Nuclear Magnetic Resonance (31P NMR) Spectroscopy in biology and medicine has provided new insights into biochemical processes and also a unique assessment of metabolites. However, accurate quantification of biological NMR spectra is frequently complicated by: (a) non-Lorentzian form of peak lineshapes, (b) contamination of peak signals by neighboring peaks, (c) presence of broad resonances, (d) low signal-to-noise ratios, and (e) poorly defined sloping baselines. Our objectives were to develop an expert system that captures and formalizes31P NMR spectroscopists' expert knowledge, and to provide a reliable, efficient, and automated system for the interpretation of biological spectra. The NMR Expert System (NMRES) was written in the C and OPS5 programming languages and implemented on a Unix-based (Ultrix) mainframe system with XWindows bitmap graphics display. Expert knowledge was acquired from NMR spectroscopists and represented as production rules in the knowledge base. A heuristic weights method was employed to determine the confidence levels of potential peaks. Statistical and numerical methods were used to facilitate processing decisions. NMR spectra obtained from studies of ischemic neonatal and immature hearts were used to assess the performance of the expert system. The expert system performed signal extraction, noise treatment, resonance assignment, intracellular pH determination, and metabolite intensity quantitation in about 10 s per 4 KB (kilobyte) spectrum. The peak identification success rate was 98.2%. Peak areas and pH estimated by the expert system compared favorably with those determined by human experts. We conclude that the expert system has provided a framework for reliable and efficient quantification of complex biological31P NMR spectra.

Original languageEnglish (US)
Pages (from-to)247-258
Number of pages12
JournalAnnals of Biomedical Engineering
Volume21
Issue number3
DOIs
StatePublished - May 1993

Fingerprint

Metabolites
Expert systems
Nuclear magnetic resonance spectroscopy
Artificial intelligence
Nuclear magnetic resonance
Magnetic resonance spectroscopy
Computer programming languages
Medicine
Numerical methods
Signal to noise ratio
Statistical methods
Contamination
Display devices
Processing

Keywords

  • Artificial intelligence
  • Cardiac metabolism
  • Expert system
  • Nuclear magnetic resonance
  • Spectral analysis

ASJC Scopus subject areas

  • Biomedical Engineering

Cite this

@article{80475558d8d5481897dc8829c4c5171f,
title = "NMRES: An artificial intelligence expert system for quantification of cardiac metabolites from31phosphorus nuclear magnetic resonance spectroscopy",
abstract = "The application of high-resolution31Phosphorus Nuclear Magnetic Resonance (31P NMR) Spectroscopy in biology and medicine has provided new insights into biochemical processes and also a unique assessment of metabolites. However, accurate quantification of biological NMR spectra is frequently complicated by: (a) non-Lorentzian form of peak lineshapes, (b) contamination of peak signals by neighboring peaks, (c) presence of broad resonances, (d) low signal-to-noise ratios, and (e) poorly defined sloping baselines. Our objectives were to develop an expert system that captures and formalizes31P NMR spectroscopists' expert knowledge, and to provide a reliable, efficient, and automated system for the interpretation of biological spectra. The NMR Expert System (NMRES) was written in the C and OPS5 programming languages and implemented on a Unix-based (Ultrix) mainframe system with XWindows bitmap graphics display. Expert knowledge was acquired from NMR spectroscopists and represented as production rules in the knowledge base. A heuristic weights method was employed to determine the confidence levels of potential peaks. Statistical and numerical methods were used to facilitate processing decisions. NMR spectra obtained from studies of ischemic neonatal and immature hearts were used to assess the performance of the expert system. The expert system performed signal extraction, noise treatment, resonance assignment, intracellular pH determination, and metabolite intensity quantitation in about 10 s per 4 KB (kilobyte) spectrum. The peak identification success rate was 98.2{\%}. Peak areas and pH estimated by the expert system compared favorably with those determined by human experts. We conclude that the expert system has provided a framework for reliable and efficient quantification of complex biological31P NMR spectra.",
keywords = "Artificial intelligence, Cardiac metabolism, Expert system, Nuclear magnetic resonance, Spectral analysis",
author = "Chow, {John L.} and Levitt, {Karl N.} and Kost, {Gerald J}",
year = "1993",
month = "5",
doi = "10.1007/BF02368180",
language = "English (US)",
volume = "21",
pages = "247--258",
journal = "Annals of Biomedical Engineering",
issn = "0090-6964",
publisher = "Springer Netherlands",
number = "3",

}

TY - JOUR

T1 - NMRES

T2 - An artificial intelligence expert system for quantification of cardiac metabolites from31phosphorus nuclear magnetic resonance spectroscopy

AU - Chow, John L.

AU - Levitt, Karl N.

AU - Kost, Gerald J

PY - 1993/5

Y1 - 1993/5

N2 - The application of high-resolution31Phosphorus Nuclear Magnetic Resonance (31P NMR) Spectroscopy in biology and medicine has provided new insights into biochemical processes and also a unique assessment of metabolites. However, accurate quantification of biological NMR spectra is frequently complicated by: (a) non-Lorentzian form of peak lineshapes, (b) contamination of peak signals by neighboring peaks, (c) presence of broad resonances, (d) low signal-to-noise ratios, and (e) poorly defined sloping baselines. Our objectives were to develop an expert system that captures and formalizes31P NMR spectroscopists' expert knowledge, and to provide a reliable, efficient, and automated system for the interpretation of biological spectra. The NMR Expert System (NMRES) was written in the C and OPS5 programming languages and implemented on a Unix-based (Ultrix) mainframe system with XWindows bitmap graphics display. Expert knowledge was acquired from NMR spectroscopists and represented as production rules in the knowledge base. A heuristic weights method was employed to determine the confidence levels of potential peaks. Statistical and numerical methods were used to facilitate processing decisions. NMR spectra obtained from studies of ischemic neonatal and immature hearts were used to assess the performance of the expert system. The expert system performed signal extraction, noise treatment, resonance assignment, intracellular pH determination, and metabolite intensity quantitation in about 10 s per 4 KB (kilobyte) spectrum. The peak identification success rate was 98.2%. Peak areas and pH estimated by the expert system compared favorably with those determined by human experts. We conclude that the expert system has provided a framework for reliable and efficient quantification of complex biological31P NMR spectra.

AB - The application of high-resolution31Phosphorus Nuclear Magnetic Resonance (31P NMR) Spectroscopy in biology and medicine has provided new insights into biochemical processes and also a unique assessment of metabolites. However, accurate quantification of biological NMR spectra is frequently complicated by: (a) non-Lorentzian form of peak lineshapes, (b) contamination of peak signals by neighboring peaks, (c) presence of broad resonances, (d) low signal-to-noise ratios, and (e) poorly defined sloping baselines. Our objectives were to develop an expert system that captures and formalizes31P NMR spectroscopists' expert knowledge, and to provide a reliable, efficient, and automated system for the interpretation of biological spectra. The NMR Expert System (NMRES) was written in the C and OPS5 programming languages and implemented on a Unix-based (Ultrix) mainframe system with XWindows bitmap graphics display. Expert knowledge was acquired from NMR spectroscopists and represented as production rules in the knowledge base. A heuristic weights method was employed to determine the confidence levels of potential peaks. Statistical and numerical methods were used to facilitate processing decisions. NMR spectra obtained from studies of ischemic neonatal and immature hearts were used to assess the performance of the expert system. The expert system performed signal extraction, noise treatment, resonance assignment, intracellular pH determination, and metabolite intensity quantitation in about 10 s per 4 KB (kilobyte) spectrum. The peak identification success rate was 98.2%. Peak areas and pH estimated by the expert system compared favorably with those determined by human experts. We conclude that the expert system has provided a framework for reliable and efficient quantification of complex biological31P NMR spectra.

KW - Artificial intelligence

KW - Cardiac metabolism

KW - Expert system

KW - Nuclear magnetic resonance

KW - Spectral analysis

UR - http://www.scopus.com/inward/record.url?scp=0027594488&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0027594488&partnerID=8YFLogxK

U2 - 10.1007/BF02368180

DO - 10.1007/BF02368180

M3 - Article

VL - 21

SP - 247

EP - 258

JO - Annals of Biomedical Engineering

JF - Annals of Biomedical Engineering

SN - 0090-6964

IS - 3

ER -