| dc.contributor | Ochoa Gómez, John Fredy | |
| dc.creator | Puche Sarmiento, Aura Cristinia | |
| dc.date | 2022-02-04T16:09:17Z | |
| dc.date | 2022-02-04T16:09:17Z | |
| dc.date | 2022 | |
| dc.date.accessioned | 2023-08-28T20:38:54Z | |
| dc.date.available | 2023-08-28T20:38:54Z | |
| dc.identifier | http://hdl.handle.net/10495/25799 | |
| dc.identifier.uri | https://repositorioslatinoamericanos.uchile.cl/handle/2250/8482279 | |
| dc.description | ABSTRACT : 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.format | 132 | |
| dc.format | application/pdf | |
| dc.format | application/pdf | |
| dc.format | application/pdf | |
| dc.language | eng | |
| dc.publisher | Grupo de Investigación en Bioinstrumentación e Ingeniería Clínica (GIBIC) | |
| dc.publisher | Medellín | |
| dc.rights | info:eu-repo/semantics/openAccess | |
| dc.rights | http://creativecommons.org/licenses/by-nc-sa/2.5/co/ | |
| dc.rights | http://purl.org/coar/access_right/c_abf2 | |
| dc.rights | https://creativecommons.org/licenses/by-nc-sa/4.0/ | |
| dc.subject | Neurodegenerative Diseases | |
| dc.subject | Magnetic Resonance Imaging | |
| dc.subject | Brain Mapping | |
| dc.subject | Default Mode Network | |
| dc.subject | Signal Processing | |
| dc.subject | Alzheimer Disease | |
| dc.subject | Neurodegenerative Diseases | |
| dc.subject | Resting state functional magnetic resonance imaging | |
| dc.subject | Brain networks | |
| dc.subject | Default mode network | |
| dc.subject | Biomedical signal analysis | |
| dc.title | Pipeline for the Classification of Subjects with Neurodegenerative Diseases Based on Biomedical Signal Processing and Machine Learning Techniques | |
| dc.type | info:eu-repo/semantics/masterThesis | |
| dc.type | info:eu-repo/semantics/draft | |
| dc.type | http://purl.org/coar/resource_type/c_bdcc | |
| dc.type | https://purl.org/redcol/resource_type/TM | |
| dc.type | Tesis/Trabajo de grado - Monografía - Maestría | |
