Logistic regression in the medical literature: Standards for use and reporting, with particular attention to one medical domain

Logistic regression (LR) is a widely used multivariable method for modeling dichotomous outcomes. This article examines use and reporting of LR in the medical literature by comprehensively assessing its use in a selected area of medical study. Medline, followed by bibliography searches, identified 1 5 peer-reviewed English-language articles with original data, employing LIZ , published between 1985 and 1999, pertaining to patient interest in geneti c testing for cancer susceptibility. Articles were examined for each of 10 criteria for proper use and reporting of LR models, Substantial shortcoming s were found in both use of LIZ and reporting of results. For many studies, the ratio of the number of outcome events to predictor variables (events p er variable) was sufficiently small to call into question the accuracy of t he regression model. Additionally, no studies reported validation analysis, regression diagnostics, or goodness-of-fit measures. It is recommended tha t authors, reviewers, and editors pay greater attention to guidelines conce rning the use and reporting of LR models. (C) 2001 Elsevier Science Inc. Al l rights reserved.