Diagnostic performance of an expert system for the interpretation of myocardial perfusion SPECT studies.

UNLABELLED An expert system (PERFEX) developed for the computer-assisted interpretation of myocardial perfusion SPECT studies is now becoming widely available. To date, a systematic validation of the diagnostic performance of this expert system for the interpretation of myocardial perfusion SPECT studies has not been reported. METHODS To validate PERFEX's ability to detect and locate coronary artery disease (CAD), we analyzed 655 stress/rest myocardial perfusion prospective SPECT studies in patients who also underwent coronary angiography. The patient population comprised CAD patients (n = 480) and healthy volunteers (n = 175) (449 men, 206 women). Data from 461 other patient studies were used to implement and refine 253 heuristic rules that best correlated the presence and location of left ventricular myocardial perfusion defects on SPECT studies with angiographically detected CAD and with human expert visual interpretations. Myocardial perfusion defects were automatically identified as segments with counts below sex-matched normal limits. PERFEX uses the certainty of the location, size, shape, and reversibility of the perfusion defects to infer the certainty of the presence and location of CAD. The visual interpretations of tomograms and polar maps, vessel stenosis from coronary angiography, and PERFEX interpretations were all accessed automatically from databases and were used to automatically generate comparisons between diagnostic approaches. RESULTS Using the physician's reading as a gold standard, PERFEX's sensitivity and specificity levels for detection and localization of disease were, respectively, 83% and 73% for CAD, 76% and 66% for the left anterior descending artery, 90% and 70% for the left circumflex artery, and 74% and 79% for the right coronary artery. These results were extracted from a receiver operating characteristic curve using the average optimal input certainty factor. CONCLUSION This study shows that the diagnostic performance of PERFEX for interpreting myocardial perfusion SPECT studies is comparable with that of nuclear medicine experts in detecting and locating CAD.

[1]  Three-dimensional display of cardiac single photon emission computed tomography. , 1993 .

[2]  E. Depuey,et al.  Quantitative rotational thallium-201 tomography for identifying and localizing coronary artery disease. , 1988, Circulation.

[3]  D. Berman,et al.  Quantitative same-day rest-stress technetium-99m-sestamibi SPECT: definition and validation of stress normal limits and criteria for abnormality. , 1993, Journal of nuclear medicine : official publication, Society of Nuclear Medicine.

[4]  S. Port.  Imaging guidelines for nuclear cardiology procedures , 1999 .

[5]  E G DePuey,et al.  Three-dimensional techniques and artificial intelligence in thallium-201 cardiac imaging. , 1989, AJR. American journal of roentgenology.

[6]  S. Kinomura,et al.  Detection of CBF deficits in neuropsychiatric disorders by an expert system: a 99Tcm-HMPAO brain SPET study using automated image registration. , 1999, Nuclear medicine communications.

[7]  H Fujita,et al.  Application of artificial neural network to computer-aided diagnosis of coronary artery disease in myocardial SPECT bull's-eye images. , 1992, Journal of nuclear medicine : official publication, Society of Nuclear Medicine.

[8]  G Germano,et al.  Technical aspects of myocardial SPECT imaging. , 2001, Journal of nuclear medicine : official publication, Society of Nuclear Medicine.

[9]  TACHY: an expert system for the management of supraventricular tachycardia in the elderly. , 1998, American heart journal.

[10]  José Mira Mira,et al.  DIAVAL, a Bayesian expert system for echocardiography , 1997, Artif. Intell. Medicine.

[11]  D S Berman,et al.  Quantification of rotational thallium-201 myocardial tomography. , 1985, Journal of nuclear medicine : official publication, Society of Nuclear Medicine.

[12]  G. Dorffner,et al.  Automated interpretation of planar thallium-201-dipyridamole stress-redistribution scintigrams using artificial neural networks. , 1994, Journal of nuclear medicine : official publication, Society of Nuclear Medicine.

[13]  Gerold Porenta,et al.  Feasibility analysis of a case-based reasoning system for automated detection of coronary heart disease from myocardial scintigrams , 1997, Artif. Intell. Medicine.

[14]  Edward H. Shortliffe,et al.  Computer-based medical consultations, MYCIN , 1976 .

[15]  J. E. Hansen,et al.  Updated imaging guidelines for nuclear cardiology procedures, part 1. , 2001, Journal of nuclear cardiology : official publication of the American Society of Nuclear Cardiology.

[16]  C. Cooke,et al.  Three-dimensional display of cardiac single photon emission computed tomography. , 1993, American journal of cardiac imaging.

[17]  D. Berman,et al.  The declining specificity of exercise radionuclide ventriculography. , 1983, The New England journal of medicine.

[18]  Norberto F. Ezquerra,et al.  PERFEX: An expert system for interpreting 3D myocardial perfusion , 1993 .

[19]  P E Christian,et al.  Image analysis and categorization of ventilation-perfusion scans for the diagnosis of pulmonary embolism using an expert system. , 1994, Journal of nuclear medicine : official publication, Society of Nuclear Medicine.

[20]  Ana Regina Cavalcanti da Rocha,et al.  An expert system for diagnosis of acute myocardial infarction with ECG analysis , 1997, Artif. Intell. Medicine.