Even before clinical symptoms appear, learning methods can help in the early diagnosis of Alzheimer's Disease. By analysing patterns and features in large datasets, these approaches can identify subtle changes in brain structure, function, or biomarkers that may indicate the presence of the Disease at an early stage. Early detection allows for timely intervention and treatment, potentially improving patient outcomes. When using neural networks for Alzheimer's disease detection, biomarkers can be incorporated as inputs to the network to aid in the classification or prediction task. This paper presents the different mechanisms available for disease detection and identifies the drawbacks associated with the method. This paper focused on biomarkers with machine learning and neural networks in terms of complexity and data representation. Machine learning algorithms often have simpler models that are easier to interpret and understand. This interpretability can provide insights into the biomarkers’ importance and contribution to the classification. In contrast, neural networks are highly flexible and can model intricate relationships. However, their complexity often results in a lack of interpretability, making it challenging to understand the specific features or biomarkers driving the predictions. In neural networks, the input data (biomarkers) are fed directly into the network without explicit feature selection. Neural networks can learn complex feature representations from high-dimensional data, capturing intricate relationships and nuances that may be challenging to capture through handcrafted feature selection.