The aim of this study was to analyze the basic epidemiological parameters of MM in the Kirov region based on own regional population register data.Materials and methods. Five hundred and sixty-seven patients with newly diagnosed MM between 1994 and 2016 were included. The median age was 64 years (range, 29–90). The age-standardized incidence of MM in Kirov region was 1.8 cases per 100.000/year.Results. During research period (23 years) we have the positive trend of the incidence and prevalence of MM and negative tendency of mortality every year. Our prognosis of the intensive incidence in Kirov region is 2.2–2.3 cases per 100.000 in 2017–2019 years. The 5-year overall survival rate (5y-OS) was 18 % (1994–1999); 24 % (2000–2005) and 36 % (2006–2011) respectively. The median OS was 28; 26 and 38 month respectively. The median OS for patients who diagnosed in the period 2012–2016 was not achieved. The reason for the increase in the prevalence of the disease and the reduction in mortality is the greater effectiveness of new bortezomib-containing chemotherapy regimens.Conclusion. Аmong the Kirov region population standardized incidence of MM is 1.8 cases per 100.000/year. The prevalence of MM in the Kirov region has a linear growth trend from 3 to 11 patients per 100.000 peoples within the analyzed period of observation 1994–2016. OS increased from 18 to 36 % in the period from 1994 to 2011. OS of MM patients has been increasing since 2006, due to using bortezomib-containing treatment options and autologous stem cell transplantation. In general, the 5-year OS increased from 18 to 36% in the period from 1994 to 2011.

Medical prognostic (prediction) models (MPM) are essential in modern healthcare. They determine health and disease risks and are created to improve diagnosis and treatment outcomes. All MPMs fall into two categories. Diagnostic medical models (DMM) aim at assessing individual risk for a disease present, whereas predictive medical models (PMM) evaluate the risk for development of a disease and its complications in future. This review discusses DMM and PMM characteristics, conditions for their elaboration, criteria for medical application, also in hematology, as well as challenges of their creation and quality check.

Data generated from modern applications and the internet in healthcare is extensive and rapidly expanding. Therefore, one of the significant success factors for any application is understanding and extracting meaningful information using digital analytics tools. These tools will positively impact the application's performance and handle the challenges that can be faced to create highly consistent, logical, and information-rich summaries. This paper contains three main objectives: First, it provides several analytics methodologies that help to analyze datasets and extract useful information from them as preprocessing steps in any classification model to determine the dataset characteristics. Also, this paper provides a comparative study of several classification algorithms by testing 12 different classifiers using two international datasets to provide an accurate indicator of their efficiency and the future possibility of combining efficient algorithms to achieve better results. Finally, building several CBC datasets for the first time in Iraq helps to detect blood diseases from different hospitals. The outcome of the analysis step is used to help researchers to select the best system structure according to the characteristics of each dataset for more organized and thorough results. Also, according to the test results, four algorithms achieved the best accuracy (Logitboost, Random Forest, XGBoost, Multilayer Perceptron). Then use the Logitboost algorithm that achieved the best accuracy to classify these new datasets. In addition, as future directions, this paper helps to investigate the possibility of combining the algorithms to utilize benefits and overcome their disadvantages.

Background.The European Population Register EUTOS for CML includes data on adult patients (n = 2904) diagnosed with Ph-positive (Ph+) and/or BCR-ABL1-positive (BCR-ABL1+) chronic myeloid leukemia (CML) in 20 European countries during the period from 2008 to December 2012. Russia took part in this study, having contributed 6.8 % of CML patients to the total number of patients in the Register.Aim.To estimate long-term treatment outcomes in patients with newly diagnosed CML in the Russian Federation in comparison with the data obtained for a pan-European population cohort of patients.Patients and methods.The cohort under study consisted of 197 patients from 6 Russia regions, all of whom were diagnosed with a Ph+ / BCR-ABL1 + CML during the period from October, 1, 2009 to December, 31, 2012. The patients’ median age was 50 (18–82) years, with men and women being represented in approximately equal proportions.Results.In the first line, 97 % and 3 % of the patients received Imatinib and 2nd generation tyrosine kinase (TKI) inhibitors, respectively. The response dynamics was as follows: 12 months after the treatment, a complete cytogenetic response and a major molecular response were achieved in 40 % and 20 % of the patients. The overall survival (OS) and progression-free survival rates in patients in Russia following 12, 24 and 30 months were 93 %, 87 % and 84 %, and 92 %, 87 % and 87 %, respectively. In Russia, the study was prolonged. By 80 months of observation, the OS of patients in the chronic CML phase with a low and high risk of the disease progression had been 88 % and 56 %, respectively. In the acceleration phase, the 5-year overall survival rate was 39 %.Conclusion.An analysis of treatment outcomes in CML patients in a population-based non-selected sample indicates an increase in the survival of CML patients. However, problematic aspects of the therapy have been identified, along with a need for intensification of the treatment in patients with an unfavourable CML prognosis.

Objective. To identify predictors of ICU mortality in patients with hemoblastosis and infectious complications. Material and methods. The study included 202 ICU patients with hemoblastosis and infectious complications between 2018 and 2021. We evaluated SIRS, qSOFA and SOFA scores, as well as other potential significant predictors. Binomial multiple logistic regression approach was used to create prognostic model. Results. Mortality rate was 33% (67 out of 202), odds ratio — 0.49 (67 to 136). The median of the follow-up period was 6 (3-14) days. Univariate analysis revealed tachypnea, hypoxemia, hemodynamic instability (blood pressure decrease, need for vasopressor support), liver damage (hyperbilirubinemia, hypoproteinemia, hypoalbuminemia) and impaired consciousness as predictors of ICU mortality. Multivariate analysis revealed 3 significant predictors of mortality: impaired consciousness, platelet count and serum protein. Model quality was evaluated on a test set with a threshold of high probability of death ≥32%. Accuracy was 0.816 (95% CI 0.679-0.912), sensitivity — 0.80, specificity — 0.82. Conclusion. Impaired consciousness, decreased platelet count and serum protein are the most important predictors of mortality in ICU patients with hemoblastosis and infectious complications. These data can be used in clinical practice.

The ICU department’s mortality rate is one of the most important indicators of quality of care. Based on real clinical data, we attempted to build a prognostic model for patients with blood diseases in the ICU with using of the logistic regression method. The study included 202 patients in total. The median age was 57 (19–82) years. There were 112 (55 %) males and 90 (45 %) females. The statistical analysis was performed by using R software, version 3.4.2. The absolute risk of death (mortality rate) was 67 from 202 (33 %), odds — 0.496. The odds of death in ICU grow up to ~20 times if the patient has a Glasgow score of less than 15. Also, the odds of death increase by 1.3 and 11 times of PLT, or serum total protein level decreases by 2 times accordingly. Our model for “high-risk of death” detection classified patients in the test dataset with 0.816 accuracy (95 % CI 0.679–0.912), with sensitivity 0.823, and specificity 0.80. Despite the simple method for data analysis, we got a pretty accurate model of mortality prognosis with efficacy more than qSOFA and MEWS scales. Research in this area should continue.