Acute pancreatitis (AP) is a serious and potentially life-threatening condition characterized by a broad spectrum of disease severity, ranging from mild, self-limiting cases to severe, destructive forms associated with significant morbidity and mortality. Accurate prediction of clinical outcomes in AP is essential for timely intervention, effective resource allocation, and improved patient care. Recent advancements in artificial intelligence (AI) and machine learning (ML) have demonstrated significant potential in enhancing the accuracy of outcome prediction for acute pancreatitis. This article reviews the literature concerning the role of predictive models powered by artificial intelligence in acute pancreatitis (AP) focusing on their methods, evaluation criteria, and clinical usefulness. In addition, the review draws attention to data-related issues with the authors saying that the data is of insufficient quality, and the models cannot be properly explained, as well as other forms of bias in the algorithms used. Other ways are discussed, such as the use of real-time monitoring via wearable devices and the construction of explainable AI models, which shed light on the ways artificial intelligence is capable of changing the clinical approach to acute pancreatitis in the future.
11 November 2024 in Bulletin of Science and Practice
Acute pancreatitis occurs as a result of autolysis of pancreatic tissue by lipolytic and activated proteolytic enzymes, which leads to a wide range of changes from edema to focal and extensive necrosis and ranks third in the development of the surgical structure of the abdominal cavity. Destructive forms occur in 30-60% of cases, and mortality fluctuates between 30-85%. The frequency of purulent results reaches 21%. The article presents a technique for the surgical treatment of patients with acute necrotizing pancreatitis.
15 December 2022 in Bulletin of Science and Practice