Learning Susceptibility of a Pathogen to Antibiotics Using Data from Similar Pathogens

Summary

Objectives: Selection of empirical antibiotic therapy relies on knowledge of the in vitro susceptibilities of potential pathogens to antibiotics. In this paper the limitations of this knowledge are outlined and a method that can reduce some of the problems is developed.

Methods: We propose hierarchical Dirichlet learning for estimation of pathogen susceptibilities to antibiotics, using data from a group of similar pathogens in a bacteremia database.

Results: A threefold cross-validation showed that maximum likelihood (ML) estimates of susceptibilities based on individual pathogens gave a distance between estimates obtained from the training set and observed frequencies in the validation set of 16.3%. Estimates based on the initial grouping of pathogens gave a distance of 16.7%. Dirichlet learning gave a distance of 15.6%. Inspection of the pathogen groups led to subdivision of three groups, Citrobacter, Other Gram Negatives and Acinetobacter, out of 26 groups. Estimates based on the subdivided groups gave a distance of 15.4% and Dirichlet learning further reduced this to 15.0%. The optimal size of the imaginary sample inherited from the group was 3.

Conclusion: Dirichlet learning improved estimates of susceptibilities relative to ML estimators based on individual pathogens and to classical grouped estimators. The initial pathogen grouping was well founded and improvement by subdivision of the groups was only obtained in three groups. Dirichlet learning was robust to these revisions of the grouping, giving improved estimates in both cases, while the group-based estimates only gave improved estimates after the revision of the groups.

Keywords

Antimicrobial susceptibility - Dirichlet estimator - Brier score - cross-validation

• References

• 1 Andreassen S, Kristensen B, Zalounina A, Leibovici L, Frank U, Schønheyder H. Hierarchical Dirichlét learning – filling in the thin spots in a database. In: Proceedings of the 9th Conference on Artificial Intelligence in Medicine; 2003 Oct; Cyprus. Springer: 2003. pp 274-283.
• 2 Heckerman D. Tutorial on Learning with Bayesian Networks. In: Jordan M. editor. Learning in Graphical Models. Cambridge, MA: MIT Press; 1999
• 3 Filho J, Wainer J. Using a hierarchical Bayesian model to handle high cardinality attributes with relevant interactions in a classification problem. In: Proceedings of the 12th Iinternational Joint Conference on Artificial Intelligence; Jan 2007; Hyderabad, India: pp 2504-2509.
• 4 Cestnik B. Estimating probabilities: A crucial task in machine learning. In: Proceedings of the 9th European Conference on Artificial Intelligence; 1990; Stockholm, Sweden: pp 147-149.
• 5 Andreassen S, Leibovici L, Paul M, Nielsen A, Zalounina A, Kristensen L, Falborg K, Kristensen B, Frank U, Schønheyder H. A probabilistic network for fusion of data and knowledge in clinical microbiology. In: Husmeier, Dybowski, Roberts, editors. Probabilistic Modeling in Bioinformatics and Medical Informatics. London: Springer; 2005. pp 451-72.
• 6 Brier G. Verification of forecasts expressed in terms of probability. Monthly Weather Rev 1950; 78: 1-3.
• 7 Hastie T, Tibshirani R, Friedman J. The elements of statistical learning. Heidelberg: Springer; 2001