The article presents the review of the literature data covering the most common causes of obstructive jaundice, methods for its differential diagnosis, as well as sonographic criteria for making a diagnosis. Based on the review, it was found that in practical surgery, ultrasound has a number of advantages in the differential diagnosis of obstructive jaundice. Sonography is an affordable, non-invasive method with high information content, allowing to make a diagnosis in the shortest possible time. The main reliable sonographic criteria for the obstructive genesis of icterus is prestenotic dilatation of the bile ducts. However, since the interpretation of ultrasound results is subjective and depends on the qualifications of the ultrasound specialist, verification of sonographic information by other research methods is necessary.

The work carried out by analyzes of the literature data on assessing the severity of acute pancreatitis and predicting its course and mortality. A comparison of traditional point scales for assessing the severity of AP was made.As a result of a comparative analysis, it was found that the most objective instrumental method for diagnosing acute pancreatitis and its complications was MSCT with the determination of the CT index of severity. Balthazar scale allows assessing the severity of the disease and forming a prognosis for the development of complications. However, computed or magnetic resonance imaging with intravenous contrast enhancement allows an accurate assessment of the severity of the disease not earlier than 72 hours and has some contraindications.Estimating and predictive systems Ranson, APACHE, Krasnorogov, Bozhenkov systems, Pugaeva and Achkasova, BISAP and HAPS allow identyfying the severity of the clinical course of acute pancreatitis, have a high sensitivity, but at the same time require significant time and resources for execution. Glasgow-Imrie, SAPS, MODS, and SOFA scales mainly calculate mortality and degree of multiple organ failure in critically ill patients; these severity assessment systems are not specific for patients with acute pancreatitis.The optimal scale for assessing the severity of AP should allow assessing the patient's condition and prognosis from the moment of admission to the outcome of the disease. The practicing surgeon will be interested in an affordable, inexpensive, easy-to-use system for determining the severity of acute pancreatitis. For surgeons, the time factor plays a key role in determining tactics, and, therefore, improves the prognosis of the disease.

The database of studies of 82 patients with acute pancreatitis are presented. Using neural network analysis, the most indicative parameters for predicting acute pancreatitis were revealed: indexes of Kalf-Kalif intoxication modified by Kostyuchenko and Khomich, Reis, Garkavi, the ratio of leukocytes to ESR, leukocyte index, general intoxication index; sonographic parameters – the size of the head of the pancreas, the diameter of the splenic vein, the presence of free fluid in the abdominal cavity; biochemical parameters – blood amylase concentration, urine diastase. When conducting clustering in a multidimensional feature space, a Kohonen neural network was created. All analyzed objects were effectively divided into 3 clusters. The most severe and prognostically unfavorable is cluster 1, which included data from 30 patients, with the maximum mortality rate and maximum hospital stay.