Ανάπτυξη μοντέλου και εφαρμογής για την πρόγνωση της γνωστικής ανεπάρκειας
Date Issued
October 19, 2023
Type
Πτυχιακή Εργασία
Abstract
Mild Cognitive Ιmpairment (MCI) is a cognitive condition frequently observed in older adults, characterized by significant alterations in memory, thinking, and reasoning abilities that extend beyond typical cognitive decline. It is worth noting that around 10%-15% of individuals with MCI are projected to develop Alzheimer's disease, effectively positioning MCI as an early stage of Alzheimer's.In this thesis, a novel approach is presented involving the utilization of eXtreme Gradient Boosting to predict the onset of Alzheimer's disease during the MCI stage. The methodology entails harnessing data from the Alzheimer's Disease Neuroimaging Initiative (ADNI). Through the analysis of longitudinal data spanning from the baseline visit to the 12-month follow-up, a predictive model was constructed. This model calculates, over a 36-month period, the likelihood of progression from MCI to Alzheimer's disease, achieving accuracy rate of 70%.To further enhance the precision of the model, the study implements feature selection using the recursive feature elimination technique. Additionally, Shapley method is employed to provide insights into the model's decision-making process, thereby augmenting the transparency and interpretability of the predictions. As a practical application of the developed model, an interactive web application was crafted. This application simulates an environment in which experts can input test values pertaining to a patient. Subsequently, the model processes these inputs and furnishes a prediction regarding the patient's probability of transitioning from MCI to Alzheimer's disease
Subjects