Návrh predikčního modelu pro diagnostiku Alzheimerovy choroby a jeho implementace praxi

This thesis focuses on the use of different methods for creating a prediction model for the diagnosis of Alzheimer's disease and their subsequent comparison. The aim of the thesis is to propose a prediction model for the diagnosis of Alzheimer's disease and to suggest the implementation of the solution in practice. The thesis focuses on prediction of the stage of the disease over a period of one year. First, the thesis analyzes the current state of the art of the use of artificial intelligence and machine learning in healthcare and then focuses on the description of the Alzheimer's disease to present the context relevant to the development of the prediction model. The main part of the thesis focuses on the selection of machine learning tools and methods, including a description of each technique and its implementation in Python. Furthermore, the thesis processes the data before using it to train the models. The analysis of different predictive models reveals that the xgboost model gives the best results for predicting the stage of the disease. Finally, the technological, legal and ethical aspects of implementing the model into practice in a healthcare setting are discussed. This thesis summarizes the findings in the field of possible diagnosis of Alzheimer's disease using artificial intelligence and shows the potential of machine learning as a useful tool for improving the care of patients with this disease.