Controlling for chance agreement in the validation of medical expert systems with no gold standard: PNEUMON-IA and RENOIR revisited

Computers and Biomedical Research

Volumn 33, Issue 6, 2000, Pages 380-397

  Martin Baranera M ^a   Sancho, J J ^a   Sanz, F ^a  

^a UNIVERSITAT AUTÒNOMA DE BARCELONA   (Spain)

Author keywords

[No Author keywords available]

Indexed keywords

ARTICLE; CLUSTER ANALYSIS; COMPUTER PROGRAM; EXPERT SYSTEM; INFORMATION SCIENCE; MEDICAL EXPERT; MEDICAL SPECIALIST; PRIORITY JOURNAL; QUALITY CONTROL; STANDARDIZATION; VALIDATION PROCESS;

EID: 0034518727     PISSN: 00104809     EISSN: None     Source Type: Journal    
DOI: 10.1006/cbmr.2000.1552     Document Type: Article

References (51)

1. Clinical data systems. 3. Development and evaluation
2. Decision support in healthcare
3. Summary recommendations for responsible monitoring and regulation of clinical software systems
4. Effects of computer-based clinical decision support systems on physician performance and patient outcomes. A systematic review
5. Validation of expert systems - With applications to auditing and accounting expert systems
6. Verification and validation
7. Evaluation of decision support systems in medicine
8. Evaluating medical expert systems: What to test and how?
9. Models for measuring performance of medical expert systems
10. The evaluation of artificial intelligence systems in medicine
11. Evaluation procedure in the TELEGASTRO project
12. Validating expert system performance
13. Reproducibility of the histologic diagnosis of pneumonia among a panel of four pathologists. Analysis of a gold standard
14. Medical data: Their acquisition, storage and use
15. Performance evaluation of Medical Expert Systems using ROC curves
16. The logistic modeling of sensitivity, specificity and predictive value of a diagnostic test
17. General methodology. 1. Advances in statistical methodology for the evaluation of diagnostic and laboratory tests
18. Validation studies using an alloyed gold standard
19. Use of methodological standards in diagnostic test research. Getting better but still not good
20. Evaluating the performance of a computer-based consultant
21. A performance evaluation of the expert system ANEMIA
22. Comparison of computer-aided and human review of general practitioners' management of hypertension
23. Differential diagnosis of dementia: A comparison between the expert system EVINCE and clinicians
24. Evaluation of Epilepsy Expert - A decision support system
25. Validation of the medical expert system PNEUMON-IA
26. Validation of the medical expert system RENOIR
27. Graphical display of categorical data
28. Clinical biostatistics. L.V.I. The biostatistics of concordance
29. Assessment of scales of disability and handicap for stroke patients
30. Sources of interobserver variation in histopathological grading of cervical dysplasia
31. Recollected versus contemporary patient reports of pre-operative symptoms in men undergoing transurethral porstatic resection for benign disease
32. Issues in comparison between meta-analyses and large trials
33. Reliability in the interpretation of the course of serum enzyme concentration changes in suspected acute myocardial infarction
34. The classification of AIDS cases: Concordance between two AIDS surveillance systems in Italy
35. Accuracy of clinical assessment of deep-vein thrombosis
36. Differences between local investigator and core laboratory interpretation of the admission electrocardiogram in patients with unstable angina pectoris or non-Q-wave myocardial infarction (a thrombin inhibition in myocardial ischemia [TRIM] substudy)
37. Kappa coefficients in epidemiology: An appraisal of a reappraisal
38. High agreement but low kappa. 1. The problems of two paradoxes
39. High agreement but low kappa. 1I. Resolving the paradoxes
40. Bias prevalence kappa
41. Behavior and interpretation of the statistic: Resolution of the two paradoxes
42. Misinterpretation and misuse of the kappa statistic
43. Validity studies in clustering methodologies
44. Hierarchical grouping methods and stopping rules: An evaluation
45. Cluster analysis
46. A coefficient of agreement for nominal scales