Previous Article | Next Article 
Antimicrobial Agents and Chemotherapy, July 2009, p. 2949-2954, Vol. 53, No. 7
0066-4804/09/$08.00+0 doi:10.1128/AAC.00081-09
Copyright © 2009, American Society for Microbiology. All Rights Reserved.
Data Mining Validation of Fluconazole Breakpoints Established by the European Committee on Antimicrobial Susceptibility Testing
Isabel Cuesta,1
Concha Bielza,2
Pedro Larrañaga,2
Manuel Cuenca-Estrella,1
Fernando Laguna,3
Dolors Rodriguez-Pardo,4
Benito Almirante,4
Albert Pahissa,4 and
Juan L. Rodríguez-Tudela1*
Servicio de Micologia, Centro Nacional de Microbiologia, Instituto de Salud Carlos III, Majadahonda, Madrid,1 Departamento de Inteligencia Artificial, Facultad de Informática, Universidad Politécnica, Madrid,2 Servicio de Medicina Interna, Hospital Carlos III, Madrid,3 Servicio de Enfermedades Infecciosas, Hospital Universitario Valle de Hebrón, Barcelona, Spain4
Received 21 January 2009/ Returned for modification 26 March 2009/ Accepted 5 May 2009
European Committee on Antimicrobial Susceptibility Testing (EUCAST) breakpoints classify Candida strains with a fluconazole MIC 
2 mg/liter as susceptible, those with a fluconazole MIC of 4 mg/liter as representing intermediate susceptibility, and those with a fluconazole MIC > 4 mg/liter as resistant. Machine learning models are supported by complex statistical analyses assessing whether the results have statistical relevance. The aim of this work was to use supervised classification algorithms to analyze the clinical data used to produce EUCAST fluconazole breakpoints. Five supervised classifiers (J48, Correlation and Regression Trees [CART], OneR, Naïve Bayes, and Simple Logistic) were used to analyze two cohorts of patients with oropharyngeal candidosis and candidemia. The target variable was the outcome of the infections, and the predictor variables consisted of values for the MIC or the proportion between the dose administered and the MIC of the isolate (dose/MIC). Statistical power was assessed by determining values for sensitivity and specificity, the false-positive rate, the area under the receiver operating characteristic (ROC) curve, and the Matthews correlation coefficient (MCC). CART obtained the best statistical power for a MIC > 4 mg/liter for detecting failures (sensitivity, 87%; false-positive rate, 8%; area under the ROC curve, 0.89; MCC index, 0.80). For dose/MIC determinations, the target was >75, with a sensitivity of 91%, a false-positive rate of 10%, an area under the ROC curve of 0.90, and an MCC index of 0.80. Other classifiers gave similar breakpoints with lower statistical power. EUCAST fluconazole breakpoints have been validated by means of machine learning methods. These computer tools must be incorporated in the process for developing breakpoints to avoid researcher bias, thus enhancing the statistical power of the model.
* Corresponding author. Mailing address: Servicio de Micología, Centro Nacional de Microbiología, Instituto de Salud Carlos III, Ctra. Majadahonda Pozuelo Km. 2, 28220 Majadahonda, Spain. Phone: 34 91 8223919. Fax: 34 91 5097966: E-mail: jlrtudela{at}isciii.es
Published ahead of print on 11 May 2009.
Antimicrobial Agents and Chemotherapy, July 2009, p. 2949-2954, Vol. 53, No. 7
0066-4804/09/$08.00+0 doi:10.1128/AAC.00081-09
Copyright © 2009, American Society for Microbiology. All Rights Reserved.
Copyright © 2009 by the American Society for Microbiology. For an alternate route to Journals.ASM.org, visit: http://intl-journals.asm.org | More Info»