1. Identification of clusters of rapid and slow decliners among subjects at risk for Alzheimer’s diseaseDragan Gamberger, Nada Lavrač, Shantanu Srivatsa, Rudolph E. Tanzi, Murali Doraiswamy, 2017, izvirni znanstveni članek Opis: The heterogeneity of Alzheimer’s disease contributes to the high failure rate of prior clinical trials. We analyzed 5-year longitudinal outcomes and biomarker data from 562 subjects with mild cognitive impairment (MCI) from two national studies (ADNI) using a novel multilayer clustering algorithm. The algorithm identified homogenous clusters of MCI subjects with markedly different prognostic cognitive
trajectories. A cluster of 240 rapid decliners had 2-fold greater atrophy and progressed to dementia at almost 5 times the rate of a cluster of 184 slow decliners. A classifier for identifying rapid decliners in one study showed high sensitivity and specificity in the second study. Characterizing subgroups of at risk subjects, with diverse prognostic outcomes, may provide novel mechanistic insights and facilitate clinical trials of drugs to delay the onset of AD.
Ključne besede: Alzheimer's disease, Rapid decliners, Data clustering, Mild cognitive impairment
Objavljeno v RUNG: 17.08.2017; Ogledov: 5224; Prenosov: 355
 Celotno besedilo (1,78 MB) |
2. Explicit Feature Construction and Manipulation for Covering Rule Learning AlgorithmsNada Lavrač, Johannes Fuernkranz, Dragan Gamberger, 2010, samostojni znanstveni sestavek ali poglavje v monografski publikaciji Opis: Features are the main rule building blocks for rule learning algorithms. They can be simple tests for attribute values or complex logical terms representing available domain knowledge. In contrast to common practice in classification rule learning, we argue that separation of the feature construction and rule construction processes has theoretical and practical justification. Explicit usage of features enables a unifying framework of both propositional and relational rule learning and we present and analyze procedures for feature construction in both types of domains. It is demonstrated that the presented procedure for constructing a set of simple features has the property that the resulting set enables construction of complete and consistent rules whenever it is possible, and that the set does not include obviously irrelevant features. Additionally, the concept of feature relevancy is important for the effectiveness of rule learning. It this work, we illustrate the concept in the coverage space and
prove that the relative relevancy has the quality-preserving property in respect to the resulting rules. Moreover, we show that the transformation from the attribute to the feature space enables a novel, theoretically justified way of handling unknown attribute values. The same approach
enables that estimated imprecision of continuous attributes can be taken into account, resulting in construction of robust features in respect to this imprecision.
Ključne besede: Machine learning, Feature construction, Rule learning, Unknown attribute values
Objavljeno v RUNG: 14.07.2017; Ogledov: 5104; Prenosov: 0
Gradivo ima več datotek! Več... |
3. Outlier based literature exploration for cross-domain linking of Alzheimer's disease and gut microbiotaDonatella Gubiani, Elsa Fabbretti, Bojan Cestnik, Nada Lavrač, Tanja Urbančič, 2017, izvirni znanstveni članek Opis: In knowledge discovery, experts frequently need to combine knowledge from different domains to get new insights and derive new conclusions. Intelligent systems should support the experts in the search for relationships between concepts from different domains, where huge amounts of possible combinations require the systems to be efficient but also sufficiently general, open and interactive to enable the experts to creatively guide the discovery process. The paper proposes a cross-domain literature mining methodology that achieves this functionality by combining the functionality of two complementary text mining tools: clustering and topic ontology creation tool OntoGen and cross-domain bridging terms exploration tool CrossBee. Focusing on outlier documents identified by OntoGen contributes to the efficiency, while CrossBee allows for flexible and user-friendly bridging concepts exploration and identification. The proposed approach, which is domain independent and can support cross-domain knowledge discovery in any field of science, is illustrated on a biomedical case study dealing with Alzheimer’s dis- ease, one of the most threatening age-related diseases, deteriorating lives of numerous individuals and challenging the ageing society as a whole. By applying the proposed methodology to Alzheimer’s disease and gut microbiota PubMed articles, we have identified Nitric oxide synthase (NOS) as a potentially valuable link between these two domains. The results support the hypothesis of neuroinflammatory nature of Alzheimer’s disease, and is indicative for the quest for identifying strategies to control nitric oxide- associated pathways in the periphery and in the brain. By addressing common mediators of inflammation using literature-based discovery, we have succeeded to uncover previously unidentified molecular links between Alzheimer’s disease and gut microbiota with a multi-target therapeutic potential.
Ključne besede: Literature-based discovery, Outlier detection, Alzheimer's disease, Gut microbiome
Objavljeno v RUNG: 26.05.2017; Ogledov: 5911; Prenosov: 0
Gradivo ima več datotek! Več... |
