Constructing Clinical Decision Support Systems for Adverse Drug Event Prevention: A Knowledge-based Approach.

A knowledge-based approach is proposed that is employed for the construction of a framework suitable for the management and effective use of knowledge on Adverse Drug Event (ADE) prevention. The framework has as its core part a Knowledge Base (KB) comprised of rule-based knowledge sources, that is accompanied by the necessary inference and query mechanisms to provide healthcare professionals and patients with decision support services in clinical practice, in terms of alerts and recommendations on preventable ADEs. The relevant Knowledge Based System (KBS) is developed in the context of the EU-funded research project PSIP (Patient Safety through Intelligent Procedures in Medication). In the current paper, we present the foundations of the framework, its knowledge model and KB structure, as well as recent progress as regards the population of the KB, the implementation of the KBS, and results on the KBS verification in decision support operation.

Enhancing the quality of phylogenetic analysis using fuzzy hidden Markov model alignments.

Any effective phylogeny inference based on molecular data begins by performing efficient multiple sequence alignments. So far, the Hidden Markov Model (HMM) method for multiple sequence alignment has been proved competitive to the classical deterministic algorithms with respect to phylogenetic analysis; nevertheless, its stochastic nature does not help it cope with the existing dependence among the sequence elements. This paper deals with phylogenetic analysis of protein and gene data using multiple sequence alignments produced by fuzzy profile Hidden Markov Models. Fuzzy profile HMMs are a novel type of profile HMMs based on fuzzy sets and fuzzy integrals, which generalize the classical stochastic HMM by relaxing its independence assumptions. In this paper, alignments produced by the fuzzy HMM model are used in phylogenetic analysis of protein data, enhancing the quality of phylogenetic trees. The new methodology is implemented in HPV virus phylogenetic inference. The results of the analysis are compared against those obtained by the classical profile HMM model and depict the superiority of the fuzzy profile HMM in this field.

Fuzzy Hidden Markov Models: a new approach in multiple sequence alignment.

This paper proposes a novel method for aligning multiple genomic or proteomic sequences using a fuzzyfied Hidden Markov Model (HMM). HMMs are known to provide compelling performance among multiple sequence alignment (MSA) algorithms, yet their stochastic nature does not help them cope with the existing dependence among the sequence elements. Fuzzy HMMs are a novel type of HMMs based on fuzzy sets and fuzzy integrals which generalizes the classical stochastic HMM, by relaxing its independence assumptions. In this paper, the fuzzy HMM model for MSA is mathematically defined. New fuzzy algorithms are described for building and training fuzzy HMMs, as well as for their use in aligning multiple sequences. Fuzzy HMMs can also increase the model capability of aligning multiple sequences mainly in terms of computation time. Modeling the multiple sequence alignment procedure with fuzzy HMMs can yield a robust and time-effective solution that can be widely used in bioinformatics in various applications, such as protein classification, phylogenetic analysis and gene prediction, among others.