Document Detail

Looking back at prospective studies.
MedLine Citation:
PMID:  18995197     Owner:  NLM     Status:  MEDLINE    
Gur's perspective article raises important points about analytic methods and the clinical inferences drawn from retrospective statistical analyses of prospective studies. Specifically, he associates three problems with the scientific methods of retrospective analyses: (1) using the parametric receiver-operating characteristic (ROC) curve and the area under the ROC curve (AUC) as a performance measure, (2) using Bonferroni adjustments to account for multiple comparisons, and (3) failing to evaluate the variability of results across sites and observers. Gur demonstrates these problems with a case study: a recent paper analyzing the Digital Mammographic Imaging Screening Trial (DMIST) (1). The issues he raises are not specific to either retrospective study designs or secondary exploratory analyses of large studies but are important issues to consider in many design settings. I address each of these issues in the following and relate them to the information provided by DMIST papers.
Carolyn M Rutter
Related Documents :
23732917 - Biological treatment and modeling aspect of btex abatement process in a biofilter.
9863677 - Extra-cellular volume estimation by electrical impedance--phase measurement or curve fi...
24057917 - A general method for modeling population dynamics and its applications.
962877 - Methods for fitting equations with two or more non-linear parameters.
1800847 - Optimization of glass microelectrode properties by response surface methodology.
17147817 - Fast estimation of the difference between two pam/jtt evolutionary distances in triplet...
Publication Detail:
Type:  Comment; Journal Article; Review    
Journal Detail:
Title:  Academic radiology     Volume:  15     ISSN:  1878-4046     ISO Abbreviation:  Acad Radiol     Publication Date:  2008 Nov 
Date Detail:
Created Date:  2008-11-10     Completed Date:  2009-01-08     Revised Date:  2014-09-24    
Medline Journal Info:
Nlm Unique ID:  9440159     Medline TA:  Acad Radiol     Country:  United States    
Other Details:
Languages:  eng     Pagination:  1463-6     Citation Subset:  IM    
Export Citation:
APA/MLA Format     Download EndNote     Download BibTex
MeSH Terms
Breast Neoplasms / epidemiology*
Mammography / statistics & numerical data*
Prospective Studies*
ROC Curve
Retrospective Studies
Statistics as Topic*
Grant Support
U01 CA097427/CA/NCI NIH HHS; U01 CA097427-07/CA/NCI NIH HHS
Comment On:
Acad Radiol. 2008 Nov;15(11):1458-62   [PMID:  18995196 ]

From MEDLINE®/PubMed®, a database of the U.S. National Library of Medicine

Previous Document:  Retrospective analyses of pivotal prospective studies with population segmentation: statistically ba...
Next Document:  Urinary oxygen tension measurement in humans using magnetic resonance imaging.