Nanoinformatics: developing new computing applications for nanomedicine.

Nanoinformatics has recently emerged to address the need of computing applications at the nano level. In this regard, the authors have participated in various initiatives to identify its concepts, foundations and challenges. While nanomaterials open up the possibility for developing new devices in many industrial and scientific areas, they also offer breakthrough perspectives for the prevention, diagnosis and treatment of diseases. In this paper, we analyze the different aspects of nanoinformatics and suggest five research topics to help catalyze new research and development in the area, particularly focused on nanomedicine. We also encompass the use of informatics to further the biological and clinical applications of basic research in nanoscience and nanotechnology, and the related concept of an extended "nanotype" to coalesce information related to nanoparticles. We suggest how nanoinformatics could accelerate developments in nanomedicine, similarly to what happened with the Human Genome and other -omics projects, on issues like exchanging modeling and simulation methods and tools, linking toxicity information to clinical and personal databases or developing new approaches for scientific ontologies, among many others.

Integrating Microarray Data and GRNs.

With the completion of the Human Genome Project and the emergence of high-throughput technologies, a vast amount of molecular and biological data are being produced. Two of the most important and significant data sources come from microarray gene-expression experiments and respective databanks (e,g., Gene Expression Omnibus-GEO (http://www.ncbi.nlm.nih.gov/geo)), and from molecular pathways and Gene Regulatory Networks (GRNs) stored and curated in public (e.g., Kyoto Encyclopedia of Genes and Genomes-KEGG (http://www.genome.jp/kegg/pathway.html), Reactome (http://www.reactome.org/ReactomeGWT/entrypoint.html)) as well as in commercial repositories (e.g., Ingenuity IPA (http://www.ingenuity.com/products/ipa)). The association of these two sources aims to give new insight in disease understanding and reveal new molecular targets in the treatment of specific phenotypes.Three major research lines and respective efforts that try to utilize and combine data from both of these sources could be identified, namely: (1) de novo reconstruction of GRNs, (2) identification of Gene-signatures, and (3) identification of differentially expressed GRN functional paths (i.e., sub-GRN paths that distinguish between different phenotypes). In this chapter, we give an overview of the existing methods that support the different types of gene-expression and GRN integration with a focus on methodologies that aim to identify phenotype-discriminant GRNs or subnetworks, and we also present our methodology.

Deep assessment of machine learning techniques using patient treatment in acute abdominal pain in children.

Learning from patient records may aid knowledge acquisition and decision making. Existing inductive machine learning (ML) systems such us NewId, CN2, C4.5 and AQ15 learn from past case histories using symbolic and/or numeric values. These systems learn symbolic rules (IF... THEN like) which link an antecedent set of clinical factors to a consequent class or decision. This paper compares the learning performance of alternative ML systems with each other and with respect to a novel approach using logic minimization, called LML, to learn from data. Patient cases were taken from the archives of the Paediatric Surgery Clinic of the University Hospital of Crete, Heraklion, Greece. Comparison of ML system performance is based both on classification accuracy and on informal expert assessment of learned knowledge.

Evaluation of automatic knowledge acquisition techniques in the diagnosis of acute abdominal pain. Acute Abdominal Pain Study Group.

Clinical diagnosis in acute abdominal pain is still a major problem. Computer-aided diagnosis offers some help; however, existing systems still produce high error rates. We therefore tested machine learning techniques in order to improve standard statistical systems. The investigation was based on a prospective clinical database with 1254 cases, 46 diagnostic parameters and 15 diagnoses. Independence Bayes and the automatic rule induction techniques ID3, NewId, PRISM, CN2, C4.5 and ITRULE were trained with 839 cases and separately tested on 415 cases. No major differences in overall accuracy were observed (43-48%), except for NewId, which was below the average. Between the different techniques some similarities were found, but also considerable differences with respect to specific diagnoses. Machine learning techniques did not improve the results of the standard model Independence Bayes. Problem dimensionality, sample size and model complexity are major factors influencing diagnostic accuracy in computer-aided diagnosis of acute abdominal pain.

GAMES II Project: a general architecture for medical knowledge-based systems.

GAMES II aims at developing a comprehensive and commercially viable methodology to avoid problems ordinarily occurring in KBS development. GAMES II methodology proposes to design a KBS starting from an epistemological model of medical reasoning (the Select and Test Model). The design is viewed as a process of adding symbol level information to the epistemological model. The architectural framework provided by GAMES II integrates the use of different formalisms and techniques providing a large set of tools. The user can select the most suitable one for representing a piece of knowledge after a careful analysis of its epistemological characteristics. Special attention is devoted to the tools dealing with knowledge acquisition (both manual and automatic). A panel of practicing physicians are assessing the medical value of such a framework and its related tools by using it in a practical application.

Seamless care in the health region of Crete: the Star* case study. Seamless Telematics Across Regions.

Seamless collaboration and medical information exchange among health care experts is an open question on existing health care systems. The patient record is usually scattered all over the health care network making access to crucial medical information troublesome. The Star* (Seamless Telematics Across Regions) project provides a set of solutions towards this direction which will soon be applied at Crete. Initially two health care structures will be involved in the process but later on and after tests have been completed successfully in real world applications, results will be defused over the whole health care region of Crete.

Role-based access to patients clinical data: the InterCare approach in the region of Crete.

The basics of a particular Integrated Electronic Health Record (I-EHR) implementation are presented, as realised by the Patient Clinical Data Directory (PCDD) system. PCDD operates within the context of HYGEIAnet, the Integrated Healthcare Telematics Network of Crete. PCDD is based on a federation of autonomous information systems and provides to its authorized users alternative views of the health record as well as access and retrieval services to its geographically distributed segments. The data model of the PCDD is based on the Subjective Objective Assessment Plan (SOAP) model that originates from the primary healthcare domain. Access to detailed information on particular patients healthcare encounters is delivered via role-based authorization privileges and controls. The administration of the national healthcare organizations' business rules, for different user-groups, is made via a specially tailored and developed rule-editor.

Modeling susceptibility to periodontitis.

Chronic inflammatory diseases like periodontitis have a complex pathogenesis and a multifactorial etiology, involving complex interactions between multiple genetic loci and infectious agents. We aimed to investigate the influence of genetic polymorphisms and bacteria on chronic periodontitis risk. We determined the prevalence of 12 single-nucleotide polymorphisms (SNPs) in immune response candidate genes and 7 bacterial species of potential relevance to periodontitis etiology, in chronic periodontitis patients and non-periodontitis control individuals (N = 385). Using decision tree analysis, we identified the presence of bacterial species Tannerella forsythia, Porphyromonas gingivalis, Aggregatibacter actinomycetemcomitans, and SNPs TNF -857 and IL-1A -889 as discriminators between periodontitis and non-periodontitis. The model reached an accuracy of 80%, sensitivity of 85%, specificity of 73%, and AUC of 73%. This pilot study shows that, on the basis of 3 periodontal pathogens and SNPs, patterns may be recognized to identify patients at risk for periodontitis. Modern bioinformatics tools are valuable in modeling the multifactorial and complex nature of periodontitis.