algorithm

Introduction

Currently, extensive research has shown that almost all published prediction models are poorly studied and have significant limitations, leading to their predictive performance often being overestimated. Additionally, there is still no universally accepted scoring system, primarily due to the need for adaptation to heterogeneous patient samples (including patient numbers, clinical profiles, and risk factors) and/or ongoing differences in the organization of healthcare systems across various countries.

Material and methods

This is a narrative literature review. A bibliographic search was conducted in the PubMed, Hinari, SpringerLink, National Center for Biotechnology Information, and Medline databases. Articles published between 2000 and 2024 were selected based on keyword combinations such as "artificial intelligence", "prediction model", "algorithm", "machine learning", and "COVID-19". Information on machine learning predictive models was selected and processed to identify characteristics that can be used to predict diagnosis, severity, length of hospital stay, ICU admission, treatment, vaccination, and mortality in COVID-19 patients. After processing the data according to the search criteria, 125 full-text articles were identified. The final bibliography includes 52 relevant sources, which were considered representative of the literature on this synthesis article topic.

Results

Artificial intelligence techniques are increasingly being used to predict outcomes in COVID-19 patients, particularly in estimating mortality among individuals infected with SARS-CoV-2, which can rapidly and effectively support clinical decision-making. According to the analysis of multiple studies, strong predictors of mortality in COVID-19 patients include advanced age, male gender, comorbidities, reduced levels of calcium, albumin, red blood cells, and oxygen saturation, as well as lymphopenia, elevated blood urea nitrogen, creatinine, lactate dehydrogenase, D-dimers, neutrophils, interleukin-6, procalcitonin, bilirubin, ferritin, aspartate aminotransferase, and troponin.

Conclusions

Artificial intelligence techniques provide potential advantages over conventional assessment methods. The information obtained from machine learning and deep learning algorithms, including easily accessible and interpretable data, can assist healthcare workers in making accurate decisions for the appropriate and timely care of COVID- 19 patients. This can improve patient outcomes, reduce the burden on healthcare systems, and ultimately decrease mortality rates.

Introduction

Chronic pancreatitis (CP) is a common disease with a complex pathogenesis, characterized by difficulties in its diagnosis and treatment.

Purpose of the study

To determine the main pathogenetic links of clinical and morphological forms of CP, markers of disease progression, to develop a diagnostic algorithm and principles of treatment of patients.

Material and methods

210 patients with CP were examined, who were divided into 4 groups: I - obstructive, II - calcifying, III - fibrous-parenchymal, IV – CP, complicated by pseudocyst. Instrumental, functional, morphological, biochemical, immunological, microbiological methods were used. To study the main morphological and biological changes in the pancreas during the development of CP and to study the effectiveness of the proposed treatment, we conducted experimental studies on 45 laboratory white Wistar male rats weighing 180-230 g.

Results

Imbalance of the immune system, oxidative stress, toxic-metabolic disorders, and diseases of the biliary system are important in the development of various forms of CP. However, there are differences in the severity of these changes. The most pronounced activity of fibrotic processes in the pancreas is typical for patients with a long course of the disease and in the presence of complications (pseudocyst). The most unfavorable course and prognosis are seen in the calcifying form of CP. The markers of CP progression are the value of the calcification coefficient of 0.5-1.0, the translocation of DNase I from the cytoplasm to the nucleus of the acinar cell, the activation of collagen formation, the increase in the level of fibrosis activators (TGF-β1, TNF-a), and the intensification of lipid peroxidation processes. An early marker of apoptosis is the translocation of DNase I from the cytoplasm to the nucleus of an acinar cell.

Conclusions

The developed diagnostic algorithm allows assessing the pathophysiological features of functional and organic disorders of the pancreas, predicting the course of the disease and choosing the optimal treatment. The proposed treatment of patients with CP effectively reduces the severity of pain and oxidative stress, normalizes the cytokine profile, improves the general condition and quality of life of patients.