Cognitive diseases are classified as medical ailments within the category of mental disorders. It is marked by diminished cognitive functions and routine tasks, with biological etiology either identified or assumed. Cognitive disorders entail disruptions in thought processes, consideration, thinking, and memory, signifying a significant deviation from the individual’s previous level of functioning. The Alzheimer, Dementia, Parkinson, and Huntington are examples of cognitive diseases and personal suffer any one of these diseases. The classical diagnosis process of cognitive diseases consists of positron emission tomography and magnetic resonance imaging classical neuroimaging techniques. The classical cerebrospinal fluid biomarker is used inside the neuroimaging to identify cognitive related diseases. These classical diagnosis processes suffer from time, cost and accuracy-related challenges. Machine learning and deep learning are the rising predictive modelling techniques that quickly diagnose cognitive related diseases with high accuracy and minimum time consumption. The integration of artificial intelligence with cognitive related diseases diagnoses addresses prevailing technological challenges in problem-solving and decision support. This chapter details and discusses the predictive modelling process and principal components with respect to the cognitive related diseases diagnosis process. The predictive model emphasizes the significance of diverse machine learning and deep learning algorithms. The predictive model utilized neuroimaging techniques, biomarker identification, features and data management, preprocessing, machine learning and deep learning algorithms, data set, and performance matrix. This study examines many traditional predictive models and assesses their effectiveness based on the classifier, preprocessing methods, dataset, and validation criteria.