Statistical methods for automated drug susceptibility testing: Bayesian minimum inhibitory concentration prediction from growth curves

Xi Kathy Zhou, Merlise A. Clyde, James Garrett, Viridiana Lourdes, Michael O'Connell, Giovanni Parmigiani, David J. Turner, Tim Wiles

Research output: Contribution to journalArticle

Abstract

Determination of the minimum inhibitory concentration (MIC) of a drug that prevents microbial growth is an important step for managing patients with infections. In this paper we present a novel probabilistic approach that accurately estimates MICs based on a panel of multiple curves reflecting features of bacterial growth. We develop a probabilistic model for determining whether a given dilution of an antimicrobial agent is the MIC given features of the growth curves over time. Because of the potentially large collection of features, we utilize Bayesian model selection to narrow the collection of predictors to the most important variables. In addition to point estimates of MICs, we are able to provide posterior probabilities that each dilution is the MIC based on the observed growth curves. The methods are easily automated and have been incorporated into the Becton-Dickinson PHOENIX automated susceptibility system that rapidly and accurately classifies the resistance of a large number of microorganisms in clinical samples. Over seventy-five studies to date have shown this new method provides improved estimation of MICs over existing approaches.

Original languageEnglish (US)
Pages (from-to)710-730
Number of pages21
JournalAnnals of Applied Statistics
Volume3
Issue number2
DOIs
StatePublished - Mar 2009

Keywords

  • Bayes
  • BIC
  • Decision theory
  • Logistic regression
  • Model selection
  • Model uncertainty

ASJC Scopus subject areas

  • Statistics, Probability and Uncertainty
  • Modeling and Simulation
  • Statistics and Probability

Fingerprint Dive into the research topics of 'Statistical methods for automated drug susceptibility testing: Bayesian minimum inhibitory concentration prediction from growth curves'. Together they form a unique fingerprint.

  • Cite this

    Zhou, X. K., Clyde, M. A., Garrett, J., Lourdes, V., O'Connell, M., Parmigiani, G., Turner, D. J., & Wiles, T. (2009). Statistical methods for automated drug susceptibility testing: Bayesian minimum inhibitory concentration prediction from growth curves. Annals of Applied Statistics, 3(2), 710-730. https://doi.org/10.1214/08-AOAS217