dc.contributorOchoa Gómez, John Fredy
dc.creatorPuche Sarmiento, Aura Cristinia
dc.date2022-02-04T16:09:17Z
dc.date2022-02-04T16:09:17Z
dc.date2022
dc.date.accessioned2023-08-28T20:38:54Z
dc.date.available2023-08-28T20:38:54Z
dc.identifierhttp://hdl.handle.net/10495/25799
dc.identifier.urihttps://repositorioslatinoamericanos.uchile.cl/handle/2250/8482279
dc.descriptionABSTRACT : Alzheimer’s disease is the most common cause of dementia. It has been found that the Default Mode Network (DMN), one of the so-called resting state networks, is important in the study of Alzheimer’s Disease (AD) given the loss of its integrity during its progression. Signals from the DMN were obtained from resting state functional Magnetic Resonance Imaging (rs-fMRI). The objective of this study was to develop a pipeline to classify subjects with neurodegenerative diseases using techniques from biomedical signal processing and machine learning over resting state fMRI BOLD signals. We implemented a static and dynamic approach to evaluate the brain function in cognitively normal individuals and subjects with Alzheimer’s Disease over the default mode network. Metrics used for the estimation of brain function included spectral estimations, information theory measures and graph theory analysis. Machine learning techniques were applied to find the best model to classify AD subjects. Information theory analysis performed by the permutation entropy showed a statistically significant increase in AD compared to cognitively normal (CN) subjects, the difference was found in the Left Retrosplenial Cortex, Posterior Cingulate Cortex. The classification provided a recall of 0.74 ± 0.34, a ROC-AUC of 0.83±0.07 and a specificity of 0.62 ± 0.05.
dc.format132
dc.formatapplication/pdf
dc.formatapplication/pdf
dc.formatapplication/pdf
dc.languageeng
dc.publisherGrupo de Investigación en Bioinstrumentación e Ingeniería Clínica (GIBIC)
dc.publisherMedellín
dc.rightsinfo:eu-repo/semantics/openAccess
dc.rightshttp://creativecommons.org/licenses/by-nc-sa/2.5/co/
dc.rightshttp://purl.org/coar/access_right/c_abf2
dc.rightshttps://creativecommons.org/licenses/by-nc-sa/4.0/
dc.subjectNeurodegenerative Diseases
dc.subjectMagnetic Resonance Imaging
dc.subjectBrain Mapping
dc.subjectDefault Mode Network
dc.subjectSignal Processing
dc.subjectAlzheimer Disease
dc.subjectNeurodegenerative Diseases
dc.subjectResting state functional magnetic resonance imaging
dc.subjectBrain networks
dc.subjectDefault mode network
dc.subjectBiomedical signal analysis
dc.titlePipeline for the Classification of Subjects with Neurodegenerative Diseases Based on Biomedical Signal Processing and Machine Learning Techniques
dc.typeinfo:eu-repo/semantics/masterThesis
dc.typeinfo:eu-repo/semantics/draft
dc.typehttp://purl.org/coar/resource_type/c_bdcc
dc.typehttps://purl.org/redcol/resource_type/TM
dc.typeTesis/Trabajo de grado - Monografía - Maestría


Este ítem pertenece a la siguiente institución