A new semi-parametric mixture model for interval censored data, with applications in the field of antimicrobial resistance

Antimicrobial resistance has become one of the main public health burdens of the last decades, and monitoring the development and spread of non-wild-type isolates has therefore gained increased interest. Monitoring is performed, based on the minimum inhibitory concentration (MIC) values, which are collected through the application of dilution experiments. For a given antimicrobial, it is common practice to dichotomize the obtained MIC distribution according to a cut-off value, in order to distinguish between susceptible wild-type isolates and non-wild-type isolates exhibiting reduced susceptibility to the substance. However, this approach hampers the ability to further study the characteristics of the non-wild type component of the distribution as information on the MIC distribution above the cut-off value is lost. As an alternative, a semi-parametric mixture model is presented, which is able to estimate the full continuous MIC distribution, thereby taking all available information into account. The model is based on an extended and censored-adjusted version of the penalized mixture approach often used in density estimation. A simulation study was carried out, indicating a promising behaviour of the new semi-parametric mixture model in the field of antimicrobial susceptibility testing.

[1]  Geert Verbeke,et al.  A Semi‐Parametric Shared Parameter Model to Handle Nonmonotone Nonignorable Missingness , 2009, Biometrics.

[2]  Lynne Strasfeld,et al.  Antiviral drug resistance: mechanisms and clinical implications. , 2010, Infectious disease clinics of North America.

[3]  E. Lesaffre,et al.  Smooth Random Effects Distribution in a Linear Mixed Model , 2004, Biometrics.

[4]  S. T. Buckland,et al.  An Introduction to the Bootstrap. , 1994 .

[5]  Laurent Bordes,et al.  A stochastic EM algorithm for a semiparametric mixture model , 2007, Comput. Stat. Data Anal..

[6]  G Kahlmeter,et al.  Statistical characterisation of bacterial wild-type MIC value distributions and the determination of epidemiological cut-off values. , 2006, Clinical microbiology and infection : the official publication of the European Society of Clinical Microbiology and Infectious Diseases.

[7]  G. McLachlan,et al.  Fitting mixture models to grouped and truncated data via the EM algorithm. , 1988, Biometrics.

[8]  D E Low,et al.  Decreased susceptibility of Streptococcus pneumoniae to fluoroquinolones in Canada. Canadian Bacterial Surveillance Network. , 1999, The New England journal of medicine.

[9]  Johan W Mouton,et al.  European harmonization of MIC breakpoints for antimicrobial susceptibility testing of bacteria. , 2003, The Journal of antimicrobial chemotherapy.

[10]  Geert Verbeke,et al.  A comparison of methods for estimating the random effects distribution of a linear mixed model , 2010, Statistical methods in medical research.

[11]  Paul H. C. Eilers,et al.  Flexible smoothing with B-splines and penalties , 1996 .

[12]  David R. Anderson,et al.  Model selection and multimodel inference : a practical information-theoretic approach , 2003 .

[13]  P. Hewett,et al.  A comparison of several methods for analyzing censored data. , 2007, The Annals of occupational hygiene.

[14]  B A Craig.  Modeling approach to diameter breakpoint determination. , 2000, Diagnostic microbiology and infectious disease.

[15]  H. Akaike.  A new look at the statistical model identification , 1974 .

[16]  Robert Gray,et al.  Flexible Methods for Analyzing Survival Data Using Splines, with Applications to Breast Cancer Prognosis , 1992 .

[17]  Dankmar Böhning,et al.  A vertex-exchange-method in D-optimal design theory , 1986 .

[18]  Gyemin Lee,et al.  EM algorithms for multivariate Gaussian mixture models with truncated and censored data , 2012, Comput. Stat. Data Anal..

[19]  Fred C Tenover,et al.  Mechanisms of antimicrobial resistance in bacteria. , 2006, The American journal of medicine.

[20]  Bruce A Craig,et al.  Statistical properties and inference of the antimicrobial MIC test , 2005, Statistics in medicine.

[21]  Jean-Jacques Daudin,et al.  A semi-parametric approach for mixture models: Application to local false discovery rate estimation , 2007, Computational Statistics & Data Analysis.

[22]  Emmanuel Lesaffre,et al.  Generalized linear mixed model with a penalized Gaussian mixture as a random effects distribution , 2008, Comput. Stat. Data Anal..

[23]  Göran Kauermann,et al.  Density estimation and comparison with a penalized mixture approach , 2012, Comput. Stat..