REPLY
Publication Criteria for Statistical Prediction Models
Kerry L. Lee;
Nina A. Bickell; and
Karen S. Pieper
1 February 1993 | Volume 118 Issue 3 | Pages 231-232
IN RESPONSE:
Our perspective on the publication of regression coefficients and the disclosure of modeling details to allow others to apply predictive models has evolved over time, and our current position is in complete accord with the philosophy expressed by Drs. Palmas, Denton, and Diamond. Thus, the coefficients for several different diagnostic and prognostic models developed using data from the Duke Cardiovascular Disease Database will appear in a forthcoming article in this journal [1]. The particular prognostic models that were used to calculate the hazard score and the difference between medical and surgical survival probabilities, which in turn were used as adjustment variables in the regression analyses of referral to surgery, will be presented in a forthcoming publication that will document our validation studies [2].
In the meantime, we will gladly share these materials with anyone wishing to have further details of our models or of the analyses done in the gender bias article.
1. Pryor DB, Shaw LK, McCants CB, Lee KL, Mark DB, Harrell FE, et al. Value of the history and physical examination in identifying patients at increased risk for coronary artery disease. Ann Intern Med. 1993; 118:81-90.
2. Pryor DB, Shaw LK, Lee KL, Harrell FE, Mark DB, Califf RM. Validation of models for predicting survival in patients with coronary artery disease. Ann. Intern. Med. 1993 (In press).
About Letters
The Editors welcome submissions for possible publication in the Letters section. Authors of letters should:
•Include no more than 300 words of text, three authors, and five references
•Type with double-spacing
•Send three copies of the letter, an authors' form signed by all authors, and a cover letter describing any conflicts of interest related to the contents of the letter.
Letters commenting on an Annals article will be considered if they are received within 6 weeks of the time the article was published. Only some of the letters received can be published. Published letters are edited and may be shortened; tables and figures are included only selectively. Authors will be notified that the letter has been received. If the letter is selected for publication, the author will be notified about 3 weeks before the publication date. Unpublished letters cannot be returned.
Annals welcomes electronically submitted letters.
Top
References
Article
