Search

Objective: Predictive models that generate individualized estimates for medically relevant outcomes are playing increasing roles in clinical care and translational research. However, current methods for calibrating these estimates lose valuable information. Our goal is to develop a new calibration method to conserve as much information as possible, and would compare favorably to existing methods in terms of important performance measures: discrimination and calibration. Material and methods: We propose an adaptive technique that utilizes individualized confidence intervals (CIs) to calibrate predictions. We evaluate this new method, adaptive calibration of predictions (ACP), in artificial and real-world medical classification problems, in terms of areas under the ROC curves, the Hosmer-Lemeshow goodness-of-fit test, mean squared error, and computational complexity. Results: ACP compared favorably to other calibration methods such as binning, Platt scaling, and isotonic regression. In several experiments, binning, isotonic regression, and Platt scaling failed to improve the calibration of a logistic regression model, whereas ACP consistently improved the calibration while maintaining the same discrimination or even improving it in some experiments. In addition, the ACP algorithm is not computationally expensive. Limitations: The calculation of CIs for individual predictions may be cumbersome for certain predictive models. ACP is not completely parameter-free: the length of the CI employed may affect its results. Conclusions: ACP can generate estimates that may be more suitable for individualized predictions than estimates that are calibrated using existing methods. Further studies are necessary to explore the limitations of ACP.

Summary Objectives: In this work, a cellular automaton software package for simulating different infectious diseases, storing the simulation results in a data warehouse system and analyzing the obtained results to generate prediction models as well as contingency plans, is proposed. The Brisbane H3N2 flu virus, which has been spreading during the winter season 2009, was used for simulation in the federal state of Tyrol, Austria. Methods: The simulation-modeling framework consists of an underlying cellular automaton. The cellular automaton model is parameterized by known disease parameters and geographical as well as demographical conditions are included for simulating the spreading. The data generated by simulation are stored in the back room of the data warehouse using the Talend Open Studio software package, and subsequent statistical and data mining tasks are performed using the tool, termed Knowledge Discovery in Database Designer (KD3). Results: The obtained simulation results were used for generating prediction models for all nine federal states of Austria. Conclusion: The proposed framework provides a powerful and easy to handle interface for parameterizing and simulating different infectious diseases in order to generate prediction models and improve contingency plans for future events.

Objective: To evaluate and compare the performance of different rule-ranking algorithms for rule-based classifiers on biomedical datasets. Methodology: Empirical evaluation of five rule ranking algorithms on two biomedical datasets, with performance evaluation based on ROC analysis and 5x2 cross-validation. Results: On a lung cancer dataset, the area under the ROC curve (AUC) of, on average, 14267.1 rules was 0.862. Multi-rule ranking found 13.3 rules with an AUC of 0.852. Four single-rule ranking algorithms, using the same number of rules, achieved average AUC values of 0.830, 0.823, 0.823, and 0.822, respectively. On a prostate cancer dataset, an average of 339265.3 rules had an AUC of 0.934, while 9.4 rules obtained from multi-rule and single-rule rankings had average AUCs of 0.932, 0.926, 0.925, 0.902 and 0.902, respectively. Conclusion: Multi-variate rule ranking performs better than the single-rule ranking algorithms. Both single-rule and multi-rule methods are able to substantially reduce the number of rules while keeping classification performance at a level comparable to the full rule set.

In this paper we give a survey of the combination of classifiers. We briefly describe basic principles of machine learning and the problem of classifier construction and review several approaches to generate different classifiers as well as established methods to combine different classifiers. Then, we introduce our novel approach to assess the appropriateness of different classifiers based on their characteristics for each test point individually

The process of feature selection is an important first step in building machine learning models. Feature selection algorithms can be grouped into wrappers and filters; the former use machine learning models to evaluate feature sets, the latter use other criteria to evaluate features individually. We present a new approach to feature selection that combines advantages of both wrapper as well as filter approaches, by using logistic regression and the area under the ROC curve (AUC) to evaluate pairs of features. After choosing as starting feature the one with the highest individual discriminatory power, we incrementally rank features by choosing as next feature the one that achieves the highest AUC in combination with an already chosen feature. To evaluate our approach, we compared it to standard filter and wrapper algorithms. Using two data sets from the biomedical domain, we are able to demonstrate that the performance of our approach exceeds that of filter methods, while being comparable to wrapper methods at smaller computational cost.

Classifiers based on parametric or non-parametric learning methods have different advantages and disadvantages. To take advantage of the strengths of both methods, we propose an algorithm that combines a parametric model (logistic regression) with a non-parametric classification method (k-nearest neighbors). This combination is based on a measure of appropriateness that uses a heuristic to decide which of the two components should contribute more to the final classification output. We measure the performance of this combination method on two data sets (one from medical informatics, and one consisting of simulated data) in terms of areas under the ROC curves (AUCs). We are able to demonstrate that our method of combining classifiers exceeds the performance of both individual classifiers taken separately.

A core technology in proteomics is mass spectroscopy (MS) that permits the measurement of thousands of proteins/peptides simultanously. Sophisticated data mining methods are necessary to identify highly predictive proteomic biomarker candidates in generated MS spectra that are specific to a certain disease. However, before analysis can be started the preprocessing of raw mass spectra is an essential task, mainly due to the presence of background signals in the spectra such as electrical and chemical noise. In this work we present a new data mining workflow for the identification of proteomic biomarker candidates using mass spectrometry data. The workflow includes two major steps: 1) the preprocessing of raw spectra, and 2) the identification of highly discriminating candidate masses using a 3-step feature selection approach by combining the advantages of efficient filter and effective wrapper techniques. With the proposed workflow we were able to identify putative candidate biomarkers in a lifethreatening human disease using matrix-assisted laser desorption/ionization imaging MS (MALDI-IMS).