Literature DB >> 17332625

A software engine to justify the conclusions of an expert system for detecting renal obstruction on 99mTc-MAG3 scans.

Ernest V Garcia1, Andrew Taylor, Daya Manatunga, Russell Folks.   

Abstract

UNLABELLED: The purposes of this study were to describe and evaluate a software engine to justify the conclusions reached by a renal expert system (RENEX) for assessing patients with suspected renal obstruction and to obtain from this evaluation new knowledge that can be incorporated into RENEX to attempt to improve diagnostic performance.
METHODS: RENEX consists of 60 heuristic rules extracted from the rules used by a domain expert to generate the knowledge base and a forward-chaining inference engine to determine obstruction. The justification engine keeps track of the sequence of the rules that are instantiated to reach a conclusion. The interpreter can then request justification by clicking on the specific conclusion. The justification process then reports the English translation of all concatenated rules instantiated to reach that conclusion. The justification engine was evaluated with a prospective group of 60 patients (117 kidneys). After reviewing the standard renal mercaptoacetyltriglycine (MAG3) scans obtained before and after the administration of furosemide, a masked expert determined whether each kidney was obstructed, whether the results were equivocal, or whether the kidney was not obstructed and identified and ranked the main variables associated with each interpretation. Two parameters were then tabulated: the frequency with which the main variables associated with obstruction by the expert were also justified by RENEX and the frequency with which the justification rules provided by RENEX were deemed to be correct by the expert. Only when RENEX and the domain expert agreed on the diagnosis (87 kidneys) were the results used to test the justification.
RESULTS: RENEX agreed with 91% (184/203) of the rules supplied by the expert for justifying the diagnosis. RENEX provided 103 additional rules justifying the diagnosis; the expert agreed that 102 (99%) were correct, although the rules were considered to be of secondary importance.
CONCLUSION: We have described and evaluated a software engine to justify the conclusions of RENEX for detecting renal obstruction with MAG3 renal scans obtained before and after the administration of furosemide. This tool is expected to increase physician confidence in the interpretations provided by RENEX and to assist physicians and trainees in gaining a higher level of expertise.

Entities:  

Mesh:

Substances:

Year:  2007        PMID: 17332625      PMCID: PMC3695612     

Source DB:  PubMed          Journal:  J Nucl Med        ISSN: 0161-5505            Impact factor:   10.057


  9 in total

1.  Multicenter trial validation of a camera-based method to measure Tc-99m mercaptoacetyltriglycine, or Tc-99m MAG3, clearance.

Authors:  A Taylor; A Manatunga; K Morton; L Reese; F S Prato; E Greenberg; R Folks; B J Kemp; M E Jones; P E Corrigan; J Galt; L Eshima
Journal:  Radiology       Date:  1997-07       Impact factor: 11.105

2.  Image analysis and categorization of ventilation-perfusion scans for the diagnosis of pulmonary embolism using an expert system.

Authors:  F V Gabor; F L Datz; P E Christian
Journal:  J Nucl Med       Date:  1994-05       Impact factor: 10.057

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

Authors:  E V Garcia; C D Cooke; R D Folks; C A Santana; E G Krawczynska; L De Braal; N F Ezquerra
Journal:  J Nucl Med       Date:  2001-08       Impact factor: 10.057

4.  Diuretic renography with the addition of quantitative gravity-assisted drainage in infants and children.

Authors:  D C Wong; M A Rossleigh; R H Farnsworth
Journal:  J Nucl Med       Date:  2000-06       Impact factor: 10.057

5.  NORA: a simple and reliable parameter for estimating renal output with or without frusemide challenge.

Authors:  A Piepsz; M Tondeur; H Ham
Journal:  Nucl Med Commun       Date:  2000-04       Impact factor: 1.690

6.  RENEX: an expert system for the interpretation of 99mTc-MAG3 scans to detect renal obstruction.

Authors:  Ernest V Garcia; Andrew Taylor; Raghuveer Halkar; Russell Folks; Meghna Krishnan; C David Cooke; Eva Dubovsky
Journal:  J Nucl Med       Date:  2006-02       Impact factor: 10.057

7.  Measuring technetium-99m-MAG3 clearance with an improved camera-based method.

Authors:  A Taylor; P L Corrigan; J Galt; E V Garcia; R Folks; M Jones; A Manatunga; D Eshima
Journal:  J Nucl Med       Date:  1995-09       Impact factor: 10.057

8.  Detection of CBF deficits in neuropsychiatric disorders by an expert system: a 99Tcm-HMPAO brain SPET study using automated image registration.

Authors:  M B Imran; R Kawashima; K Sato; S Kinomura; S Ono; A Qureshy; H Fukuda
Journal:  Nucl Med Commun       Date:  1999-01       Impact factor: 1.690

9.  Increasing the dose of furosemide in patients with azotemia and suspected obstruction.

Authors:  Angela Hunsche; Hejung Press; Andrew Taylor
Journal:  Clin Nucl Med       Date:  2004-03       Impact factor: 7.794

  9 in total
  7 in total

1.  iRENEX: a clinically informed decision support system for the interpretation of ⁹⁹mTc-MAG3 scans to detect renal obstruction.

Authors:  Ernest V Garcia; Andrew Taylor; Russell Folks; Daya Manatunga; Raghuveer Halkar; Bital Savir-Baruch; Eva Dubovsky
Journal:  Eur J Nucl Med Mol Imaging       Date:  2012-05-30       Impact factor: 9.236

Review 2.  Computer-assisted diagnosis in renal nuclear medicine: rationale, methodology, and interpretative criteria for diuretic renography.

Authors:  Andrew T Taylor; Ernest V Garcia
Journal:  Semin Nucl Med       Date:  2014-03       Impact factor: 4.446

Review 3.  Integrating artificial intelligence and natural language processing for computer-assisted reporting and report understanding in nuclear cardiology.

Authors:  Ernest V Garcia
Journal:  J Nucl Cardiol       Date:  2022-06-20       Impact factor: 5.952

4.  Decision support systems in diuresis renography.

Authors:  Andrew Taylor; Amita Manatunga; Ernest V Garcia
Journal:  Semin Nucl Med       Date:  2008-01       Impact factor: 4.446

Review 5.  Radionuclides in nephrourology, Part 2: pitfalls and diagnostic applications.

Authors:  Andrew T Taylor
Journal:  J Nucl Med       Date:  2014-03-03       Impact factor: 10.057

6.  Diagnostic performance of an expert system for interpretation of 99mTc MAG3 scans in suspected renal obstruction.

Authors:  Andrew Taylor; Ernest V Garcia; Jose Nilo G Binongo; Amita Manatunga; Raghuveer Halkar; Russell D Folks; Eva Dubovsky
Journal:  J Nucl Med       Date:  2008-01-16       Impact factor: 10.057

7.  Diagnostic performance of an artificial intelligence-driven cardiac-structured reporting system for myocardial perfusion SPECT imaging.

Authors:  Ernest V Garcia; J Larry Klein; Valeria Moncayo; C David Cooke; Christian Del'Aune; Russell Folks; Liudmila Verdes Moreiras; Fabio Esteves
Journal:  J Nucl Cardiol       Date:  2018-09-12       Impact factor: 5.952

  7 in total

北京卡尤迪生物科技股份有限公司 © 2022-2023.