Machine learning models are increasingly being employed to predict the dynamics of acute pancreatitis progression. Traditional methods utilising scales based on predefined parameters have limited applicability in processing all potentially important patient parameters with acute pancreatitis. The aim of this review was to examine the use of artificial intelligence for predicting the progression of acute pancreatitis, assessing complications and organ failure, determining the need for surgical interventions, and predicting mortality. Method. This is a narrative study that explored the use of artificial intelligence and machine learning methods for predicting the progression of acute pancreatitis. PubMed^® and Google Scholar were searched using keywords such as «machine learning acute pancreatitis», «deep learning acute pancreatitis», «artificial intelligence acute pancreatitis», «artificial neural networks acute pancreatitis» and «machine learning acute pancreatitis — complications forecasting». Results. Recent studies have investigated the use of artificial intelligence models for predicting the progression of acute pancreatitis. These studies confirm the effectiveness of machine learning in handling large datasets. Machine learning models can identify patient complications, assess the need for surgical intervention, and predict mortality. Radiomics also shows promise as an auxiliary tool for assessing local changes in patients with acute pancreatitis. Conclusion. The use of various machine learning models, such as random forests, recurrent neural networks, and deep learning algorithms, allows accurate identification of risks and enhances the clinical management of acute pancreatitis. Exploring nonobvious interactions with ML tools for assessing systemic changes and individual criteria will expand the ability to determine treatment tactics and surgical interventions.