 AI-based methods have been developed for automatic pain assessment, APA, which is essential for providing accurate and reliable pain levels in different clinical contexts. Behavioral-based approaches, such as facial recognition and body posture analysis, have been explored for APA. Additionally, neurophysiological-based pain detection methods, such as electroencephalogram, electromyography, and electrodermal activity, have also been studied. Recently, multimodal strategies have been proposed, combining behaviors with neurophysiological findings. Machine learning algorithms, such as support vector machines, decision trees, and random forest classifiers, have been used in earlier studies, while more recent developments include artificial neural networks, such as convolutional and recurrent neural networks. It is important to structure and process robust datasets for use in various settings, including acute and chronic pain conditions. Furthermore, collaboration between computer scientists and clinicians should be encouraged to ensure explainability and ethical considerations. This article was authored by Marco Cacchella, Daniela Schiovo, Arturo Cuomo, and others. We are article.tv, links in the description below.