2. Common methods and tools for diagnosis, prognosis and estimation of DEFAD

Since the beginning of the 21st century, and particularly since the 1950s, when artificial intelligence emerged, tens of thousands of publications, books, specialized conferences and industrial applications have been devoted to the development of a huge number of diagnostic and prognostic methods. This diversity of approaches makes an exhaustive description impossible within the scope of this article. However, we can classify them into two main families: methods based on statistical data processing and those based on the various branches of artificial intelligence (pattern recognition, neural networks, machine learning, etc.).

This section is devoted to a brief description of the principles of the most commonly used methods in these two categories, following a review of machine learning techniques