A Dynamic Bayesian Network model for long-term simulation of clinical complications in type 1 diabetes.

The increasing prevalence of diabetes and its related complications is raising the need for effective methods to predict patient evolution and for stratifying cohorts in terms of risk of developing diabetes-related complications. In this paper, we present a novel approach to the simulation of a type 1 diabetes population, based on Dynamic Bayesian Networks, which combines literature knowledge with data mining of a rich longitudinal cohort of type 1 diabetes patients, the DCCT/EDIC study. In particular, in our approach we simulate the patient health state and complications through discretized variables. Two types of models are presented, one entirely learned from the data and the other partially driven by literature derived knowledge. The whole cohort is simulated for fifteen years, and the simulation error (i.e. for each variable, the percentage of patients predicted in the wrong state) is calculated every year on independent test data. For each variable, the population predicted in the wrong state is below 10% on both models over time. Furthermore, the distributions of real vs. simulated patients greatly overlap. Thus, the proposed models are viable tools to support decision making in type 1 diabetes.

Bag of Naïve Bayes: biomarker selection and classification from genome-wide SNP data.

BACKGROUND: Multifactorial diseases arise from complex patterns of interaction between a set of genetic traits and the environment. To fully capture the genetic biomarkers that jointly explain the heritability component of a disease, thus, all SNPs from a genome-wide association study should be analyzed simultaneously. RESULTS: In this paper, we present Bag of Naïve Bayes (BoNB), an algorithm for genetic biomarker selection and subjects classification from the simultaneous analysis of genome-wide SNP data. BoNB is based on the Naïve Bayes classification framework, enriched by three main features: bootstrap aggregating of an ensemble of Naïve Bayes classifiers, a novel strategy for ranking and selecting the attributes used by each classifier in the ensemble and a permutation-based procedure for selecting significant biomarkers, based on their marginal utility in the classification process. BoNB is tested on the Wellcome Trust Case-Control study on Type 1 Diabetes and its performance is compared with the ones of both a standard Naïve Bayes algorithm and HyperLASSO, a penalized logistic regression algorithm from the state-of-the-art in simultaneous genome-wide data analysis. CONCLUSIONS: The significantly higher classification accuracy obtained by BoNB, together with the significance of the biomarkers identified from the Type 1 Diabetes dataset, prove the effectiveness of BoNB as an algorithm for both classification and biomarker selection from genome-wide SNP data. AVAILABILITY: Source code of the BoNB algorithm is released under the GNU General Public Licence and is available at http://www.dei.unipd.it/~sambofra/bonb.html.

A new index to optimally design and compare continuous glucose monitoring glucose prediction algorithms.

BACKGROUND: Continuous glucose monitoring (CGM) data can be exploited to prevent hypo-/hyperglycemic events in real time by forecasting future glucose levels. In the last few years, several glucose prediction algorithms have been proposed, but how to compare them (e.g., methods based on polynomial rather than autoregressive time-series models) and even how to determine the optimal parameter set for a given method (e.g., prediction horizon and forgetting) are open problems. METHODS: A new index, J, is proposed to optimally design a prediction algorithm by taking into account two key components: the regularity of the predicted profile and the time gained thanks to prediction. Effectiveness of J is compared with previously proposed criteria such as the root mean square error (RMSE) and continuous glucose-error grid analysis (CG-EGA) on 20 Menarini (Florence, Italy) Glucoday® CGM data sets. RESULTS: For a given prediction algorithm, the new index J is able to suggest a more consistent and better parameter set (e.g., prediction horizon and forgetting factor of choice) than RMSE and CG-EGA. In addition, the minimization of J can reliably be used as a selection criterion in comparing different prediction methods. CONCLUSIONS: The new index can be used to compare different prediction strategies and to optimally design their parameters.