Alzheimer's disease is a neurological disorder that causes loss of autonomy and memory in people who suffer from it. Due to the increase of cases of this disease and the lack of accuracy of diagnostic tools, new tools capable of reducing this problem are being developed.The main objective is to implement a three-dimensional convolutional neural network model with AlexNet3D type base structure to obtain the prediction of a possible diagnosis of Alzheimer's disease (AD) from the analysis of magnetic resonance images, using as an early stage the mild cognitive impairment syndrome (MCI).This project will provide an explanation of each proposed phase, which were divided into database selection, feature selection, data processing, model development for training and validation, and finally, results obtained from the prediction tests.