The recent technological advances have led to the availability of a huge amount of biomedical data, that are heterogeneous, complex, and distributed in biological databases. In particular, in neurodegenerative diseases area, last years have witnessed the increasing of specialized databases such as Alzheimer's Disease Neuroimaging Initiative (ADNI) [1], which covers psychometric tests, biospecimen, imaging, and laboratory results. Analyzing these data is a challenging task and machine learning (ML) may offer methods and tools for knowledge discovery from them. However, ADNI suffers from a scarce conceptualization behind the collected data, which prevents a fully intuitive access to the data themselves and a direct analysis through ML methods. This fact suggests that a better semantic description of the domain must be proposed. Therefore, in order to take advantage of this big data repository, we are working on two directions: 1) develop a detailed ontology to give a more conceptual organization to the data, to ease data access and interpretation, and to facilitate data integration approaches with other data sources; 2) apply logic data mining methodologies to extract knowledge and generate probabilistic diagnostic models from the ontology, in order to classify patients into disease categories.
Combining knowledge-based approach with logic data mining techniques to improve data querying and analysis on Alzheimer's Disease data
Paola Bertolazzi;Federica Conte;Fabio Cumbo;Giulia Fiscon;Gabriella Mavelli;Francesco Taglino;
2019
Abstract
The recent technological advances have led to the availability of a huge amount of biomedical data, that are heterogeneous, complex, and distributed in biological databases. In particular, in neurodegenerative diseases area, last years have witnessed the increasing of specialized databases such as Alzheimer's Disease Neuroimaging Initiative (ADNI) [1], which covers psychometric tests, biospecimen, imaging, and laboratory results. Analyzing these data is a challenging task and machine learning (ML) may offer methods and tools for knowledge discovery from them. However, ADNI suffers from a scarce conceptualization behind the collected data, which prevents a fully intuitive access to the data themselves and a direct analysis through ML methods. This fact suggests that a better semantic description of the domain must be proposed. Therefore, in order to take advantage of this big data repository, we are working on two directions: 1) develop a detailed ontology to give a more conceptual organization to the data, to ease data access and interpretation, and to facilitate data integration approaches with other data sources; 2) apply logic data mining methodologies to extract knowledge and generate probabilistic diagnostic models from the ontology, in order to classify patients into disease categories.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.