Logic regression-derived algorithms for syndromic management of vaginal infections.


Rathod, SD; Li, T; Klausner, JD; Hubbard, A; Reingold, AL; Madhivanan, P; (2015) Logic regression-derived algorithms for syndromic management of vaginal infections. BMC Med Inform Decis Mak, 15 (1). p. 106. ISSN 1472-6947 DOI: https://doi.org/10.1186/s12911-015-0228-5

[img] Text - Published Version
License:

Download (643kB)

Abstract

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. 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). 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. 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.

Item Type: Article
Faculty and Department: Faculty of Epidemiology and Population Health > Dept of Population Health (2012- ) > Dept of Nutrition and Public Health Interventions Research (2003-2012)
Faculty of Epidemiology and Population Health > Dept of Population Health (2012- )
PubMed ID: 26674351
Web of Science ID: 366456600001
URI: http://researchonline.lshtm.ac.uk/id/eprint/2478738

Statistics


Download activity - last 12 months
Downloads since deposit
59Downloads
115Hits
Accesses by country - last 12 months
Accesses by referrer - last 12 months
Impact and interest
Additional statistics for this record are available via IRStats2

Actions (login required)

Edit Item Edit Item