Date of this Version
12-16-2015
Document Type
Article
Abstract
Background: Syndromic management of vaginal infections is known to have poor diagnostic accuracy. Logic regression is a machine-learning procedure which allows for the identification of combinations of variables to predict an outcome, such as the presence of a vaginal infection.
Methods: We used logic regression to develop predictive models for syndromic management of vaginal infection among symptomatic, reproductive-age women in south India. We assessed the positive predictive values, negative predictive values, sensitivities and specificities of the logic regression procedure and a standard WHO algorithm against laboratory-confirmed diagnoses of two conditions: metronidazole-sensitive vaginitis [bacterial vaginosis or trichomoniasis (BV/TV)], and vulvovaginal candidiasis (VVC).
Results: The logic regression procedure created algorithms which had a mean positive predictive value of 61 % and negative predictive value of 80 % for management of BV/TV, and a mean positive predictive value of 26 % and negative predictive value of 98 % for management of VVC. The results using the WHO algorithm were similarly mixed.
Conclusions: The logic regression procedure identified the most predictive measures for management of vaginal infections from the candidate clinical and laboratory measures. However, the procedure provided further evidence as to the limits of syndromic management for vaginal infections using currently available clinical measures.
Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 License.
Recommended Citation
Rathod, Sujit D.; Li, Tan; Klausner, Jeffery D.; Hubbard, Alan; Reingold, Arthur L.; and Madhivanan, Purnima, "Logic regression-derived algorithms for syndromic management of vaginal infections" (2015). Department of Biostatistics Faculty Publications. 6.
https://digitalcommons.fiu.edu/biostatistics_fac/6
Rights Statement
In Copyright. URI: http://rightsstatements.org/vocab/InC/1.0/
This Item is protected by copyright and/or related rights. You are free to use this Item in any way that is permitted by the copyright and related rights legislation that applies to your use. For other uses you need to obtain permission from the rights-holder(s).
Comments
© 2015 Rathod et al. Open Access This article is distributed under the terms of the Creative Commons Attribution 4.0 International License (http://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution, and reproduction in any medium, provided you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license, and indicate if changes were made. The Creative Commons Public Domain Dedication waiver (http://creativecommons.org/publicdomain/zero/1.0/) applies to the data made available in this article, unless otherwise stated.