Purpose: The paper investigates the use of Machine Learning (ML) algorithms to analyse diffusion nuclear magnetic resonance imaging (dMRI) models. It presents an overview of the various machine learning techniques used for dMRI analysis. The work also evaluates the performance of these methods on real-world dMRI datasets and compares their results with traditional methods. Methods: After standard fitting, the following ML algorithms are compared; Extra-Tree Classifier (ETC), Logistic Regression, C-Support Vector, Extra-Gradient Boost and Multilayer Perceptron (MLP), evaluating precision and AUC tests. In addition, computer timing was evaluated. Results: The ETC and the MLP showed the best classifiers with 94.1 % and 91.7 % accuracy. Once the set is trained, a significant computing time reduction is achieved. Conclusions: The findings suggest that machine learning algorithms can improve accuracy and efficiency in dMRI model analysis, offering new insights into biological tissues' underlying microstructural and functional organisation. Additionally, the paper discusses the limitations and future directions for machine learning-based dMRI analysis.