Dmitry G. Lagerev
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Dmitry G. Lagerev has a total of 41 co-authors. Here are the top co-authors by number of shared publications:
- Anton V. Korsakov
Pirogov Russian National Research Medical University
9 shared publications - Leonid I. Pugach
Bryansk State Technical University
7 shared publications - E. A. Makarova
Bryansk State Technical University
5 shared publications - Aleksandr G. Podvesovskii
Bryansk State Technical University
4 shared publications - Olga Yurjevna Milushkina
Pirogov Russian National Research Medical University
4 shared publications - Vladislav P. Troshin
Bryansk State Technical University
3 shared publications
Latest Publications
- Open Access
- 28 June 2024
- Published by Bryansk State Technical University BSTU in Automation and modeling in design and management
- Vol. 2024 (2) , 35-44
USING DATA MINING TO ESTIMATE UNMANNED AERIAL VEHICLE BATTERY CONSUMPTION
Assessing and predicting the dynamic flight performance of an unmanned aerial vehicle is associated with the complexity of constructing and applying strict mathematical models that take into account many heterogeneous parameters. The paper examines the problem of estimating the battery consumption of an unmanned aerial vehicle when flying along a given route, considering weather conditions and geospatial characteristics. An approach to its solution is proposed, based on clarifying the estimate obtained using an approximate dependence by finding the interval with the highest probability containing the actual flow value. To find the specified interval, it is proposed to use the binary classification method applying logistic regression models based on the training data set. A pipeline is built that combines the mechanisms of constructing, training, and applying the assessment model. Implementing this pipeline using the Loginom analytical platform, which is included in the Russian software register, is described. The features of preparing training data, as well as the results of teaching the model and checking it on the test data set are considered.
- 28 June 2024
- Published by Bryansk State Technical University BSTU in Automation and modeling in design and management
- Vol. 2024 (2) , 35-44
Open AccessUSING DATA MINING TO ESTIMATE UNMANNED AERIAL VEHICLE BATTERY CONSUMPTION
Assessing and predicting the dynamic flight performance of an unmanned aerial vehicle is associated with the complexity of constructing and applying strict mathematical models that take into account many heterogeneous parameters. The paper examines the problem of estimating the battery consumption of an unmanned aerial vehicle when flying along a given route, considering weather conditions and geospatial characteristics. An approach to its solution is proposed, based on clarifying the estimate obtained using an approximate dependence by finding the interval with the highest probability containing the actual flow value. To find the specified interval, it is proposed to use the binary classification method applying logistic regression models based on the training data set. A pipeline is built that combines the mechanisms of constructing, training, and applying the assessment model. Implementing this pipeline using the Loginom analytical platform, which is included in the Russian software register, is described. The features of preparing training data, as well as the results of teaching the model and checking it on the test data set are considered.
- Open Access
- 27 December 2023
- Published by Bryansk State Technical University BSTU in Automation and modeling in design and management
- Vol. 2023 (4) , 64-73
FEATURES OF APPLYING INFORMATION TECHNOLOGY FOR MANAGING THE COMPETENCY DEVELOPMENT PROCESS OF A PROJECT-ORIENTED IT COMPANY
- 27 December 2023
- Published by Bryansk State Technical University BSTU in Automation and modeling in design and management
- Vol. 2023 (4) , 64-73
Open AccessFEATURES OF APPLYING INFORMATION TECHNOLOGY FOR MANAGING THE COMPETENCY DEVELOPMENT PROCESS OF A PROJECT-ORIENTED IT COMPANY
- Open Access
- 15 February 2023
- Published by Federal Scientific Center for Hygiene F.F.Erisman in Hygiene and sanitation
- Vol. 102 (1) , 14-21
Primary incidence of cervical cancer in the population living in ecologically disadvantaged areas (2000–2020)
Introduction. Thirty six years after the Chernobyl disaster about 5 million people live in the radioactively contaminated territories of Ukraine, Belarus and Russia, and the density of radioactive contamination, determined mainly by long-lived Cesium-137 and Strontium-90, will remain radiologically significant for several decades. Purpose of the study. Based on official statistics for 2000-2020, to analyze the trend in the incidence of cervical cancer in females living in conditions of radioactive, chemical, and combined environmental contamination in the Bryansk region. Materials and methods. Poisson regression, Shapiro-Wilk test, Mann-Whitney U-test, Spearman test. Data sources - Bryansk Regional Oncological Dispensary, Rospotrebnadzor, Rostekhnadzor, Bryanskstat. Results. There were no statistically significant differences in the incidence of the cervical cancer, regardless of the level of radioactive, chemical, and combined environmental contamination. Also, we have found no significant correlations between the frequency of primary morbidity of the cervical cancer with neither the density of 137Cs and 90Sr contamination, nor air pollution with gaseous pollutants (VOCs, SO2, CO and NOx). A statistically significant (p<0.00001) gain in the long-term trend in the incidence of the cervical cancer over 2000-2019 was revealed in all the studied groups, regardless of the environmental conditions of the residence. The forecast for the incidence of the cervical cancer on average in the Bryansk region during 2020 shows a decrease by 20.7% in real values compared to the forecast data. Limitations. Incidence of the cervical cancer without regard to age groups, distribution at the stage of the disease, histological, and immunohistochemical profile. Conclusion. The obtained results indicate to the need for further work to understand the trends in the presence/absence of independent and combined effects of pollutants on the growth of oncogynecological pathology from the standpoint of assessing distant and regional metastasis, the histological, and immunohistichemical profile of a specific cervical cancer with levels of radioactive, chemical, and combined environmental contamination.
- 15 February 2023
- Published by Federal Scientific Center for Hygiene F.F.Erisman in Hygiene and sanitation
- Vol. 102 (1) , 14-21
Open AccessPrimary incidence of cervical cancer in the population living in ecologically disadvantaged areas (2000–2020)
Introduction. Thirty six years after the Chernobyl disaster about 5 million people live in the radioactively contaminated territories of Ukraine, Belarus and Russia, and the density of radioactive contamination, determined mainly by long-lived Cesium-137 and Strontium-90, will remain radiologically significant for several decades. Purpose of the study. Based on official statistics for 2000-2020, to analyze the trend in the incidence of cervical cancer in females living in conditions of radioactive, chemical, and combined environmental contamination in the Bryansk region. Materials and methods. Poisson regression, Shapiro-Wilk test, Mann-Whitney U-test, Spearman test. Data sources - Bryansk Regional Oncological Dispensary, Rospotrebnadzor, Rostekhnadzor, Bryanskstat. Results. There were no statistically significant differences in the incidence of the cervical cancer, regardless of the level of radioactive, chemical, and combined environmental contamination. Also, we have found no significant correlations between the frequency of primary morbidity of the cervical cancer with neither the density of 137Cs and 90Sr contamination, nor air pollution with gaseous pollutants (VOCs, SO2, CO and NOx). A statistically significant (p<0.00001) gain in the long-term trend in the incidence of the cervical cancer over 2000-2019 was revealed in all the studied groups, regardless of the environmental conditions of the residence. The forecast for the incidence of the cervical cancer on average in the Bryansk region during 2020 shows a decrease by 20.7% in real values compared to the forecast data. Limitations. Incidence of the cervical cancer without regard to age groups, distribution at the stage of the disease, histological, and immunohistochemical profile. Conclusion. The obtained results indicate to the need for further work to understand the trends in the presence/absence of independent and combined effects of pollutants on the growth of oncogynecological pathology from the standpoint of assessing distant and regional metastasis, the histological, and immunohistichemical profile of a specific cervical cancer with levels of radioactive, chemical, and combined environmental contamination.
- 1 January 2023
- Published by Keldysh Institute of Applied Mathematics
Using Interactive Visualization in the Problem of Feature Extraction from Semi-structured Text Data
The article deals with the visualization of semi-structured text data (SSTD) in order to solve the problems of exploratory analysis and build a model for processing text data for their further use in data analysis models. The problems faced by researchers when adding SSTS to the data analysis model are considered. Existing approaches to visualization of text data for solving various problems of natural language processing are considered. A model of intelligent processing of SSTD and approaches to data transformation within the data processing. A visual model used to visualize the process of transformation of SSTD is based on the Sankey charts. The proposed visual model allows to reduce the expert's time for data processing by increasing the visibility of the process of extracting features from SSTD using interactive visual tools. The developed approach was tested on data from the information system of the employment service.
- 1 January 2023
- Published by Keldysh Institute of Applied Mathematics
Using Interactive Visualization in the Problem of Feature Extraction from Semi-structured Text Data
The article deals with the visualization of semi-structured text data (SSTD) in order to solve the problems of exploratory analysis and build a model for processing text data for their further use in data analysis models. The problems faced by researchers when adding SSTS to the data analysis model are considered. Existing approaches to visualization of text data for solving various problems of natural language processing are considered. A model of intelligent processing of SSTD and approaches to data transformation within the data processing. A visual model used to visualize the process of transformation of SSTD is based on the Sankey charts. The proposed visual model allows to reduce the expert's time for data processing by increasing the visibility of the process of extracting features from SSTD using interactive visual tools. The developed approach was tested on data from the information system of the employment service.
- Open Access
Cervical and Endometrial Cancer Incidence in the Female Population from the Bryansk Region Living in Conditions of Chemical, Radioactive and Combined Environmental Contamination (2000–2020)
At the end of 36 years after the Chernobyl disaster, about 5 million people still live in the radioactively contaminated territories of Russia, Ukraine, and Belarus, and the density of radioactive contamination by Cesium-137 and Strontium-90 will remain radiologically significant for decades. We assessed cervical and endometrial cancer primary incidence (new cases) in the female population from the Bryansk region living in conditions of chemical, radioactive, and combined environmental contamination for 2000–2020. We found a significant increase in the long-term trend in the primary incidence of cervical and endometrial cancer in all the studied groups, regardless of the environmental conditions of residence (p < 0.00001). We did not find statistically significant differences in the incidence of cervical and endometrial cancer in women, regardless of the level of chemical, radioactive, and combined environmental contamination. However, women living in environmentally unfavorable areas (in total, in the territories of chemical, radioactive, and combined contamination) are statistically significantly more likely to develop endometrial cancer in terms of relative risk compared to environmentally safe (control) areas (RR 1.17 (1.08–1.27)). No such pattern was found for cervix cancer. It should be noted, since environmentally safe (control) areas have a certain level of contamination (albeit low), RR is underestimated.
Open AccessCervical and Endometrial Cancer Incidence in the Female Population from the Bryansk Region Living in Conditions of Chemical, Radioactive and Combined Environmental Contamination (2000–2020)
At the end of 36 years after the Chernobyl disaster, about 5 million people still live in the radioactively contaminated territories of Russia, Ukraine, and Belarus, and the density of radioactive contamination by Cesium-137 and Strontium-90 will remain radiologically significant for decades. We assessed cervical and endometrial cancer primary incidence (new cases) in the female population from the Bryansk region living in conditions of chemical, radioactive, and combined environmental contamination for 2000–2020. We found a significant increase in the long-term trend in the primary incidence of cervical and endometrial cancer in all the studied groups, regardless of the environmental conditions of residence (p < 0.00001). We did not find statistically significant differences in the incidence of cervical and endometrial cancer in women, regardless of the level of chemical, radioactive, and combined environmental contamination. However, women living in environmentally unfavorable areas (in total, in the territories of chemical, radioactive, and combined contamination) are statistically significantly more likely to develop endometrial cancer in terms of relative risk compared to environmentally safe (control) areas (RR 1.17 (1.08–1.27)). No such pattern was found for cervix cancer. It should be noted, since environmentally safe (control) areas have a certain level of contamination (albeit low), RR is underestimated.
- 1 January 2022
- Published by Keldysh Institute of Applied Mathematics
Using Visual Modelsfor Exploratory Analysis of Semi-structured Text Data
The processing of semi-structured textual data for further use in DM models is a labor-intensive process, which, in addition to material costs, can increase the time required to build a model, and, as a result, worsen the efficiency of decision-making. This article presents visual models of semistructured text data and methods for their processing at the stage of exploratory analysis. Exploratory analysis will reduce the time to select significant variables at the initial stage of the study and, in the future, avoid the processing of redundant or insignificant variables. The use of visualization will help to include in DM model and process only data that will improve DM model quality. The process of using visualization of textual data in the process of exploratory analysis and the construction of two types of visual models is described - interactive "quantitative" visualization and visualization of relationships between words and other variables in the data under study. Approbation of the developed models is described on the example of labor market analysis. Examples of visualization of the content of the "soft skills" field from the CV and vacancies are presented, displaying both the skills most often mentioned by applicants from various professional fields, and the impact of mentioning these skills on inviting applicants for interviews. The experiment showed that the use of the developed visual models makes it possible to determine whether it is necessary to include a text variable in the DM model at the stage of exploratory analysis.
- 1 January 2022
- Published by Keldysh Institute of Applied Mathematics
Using Visual Modelsfor Exploratory Analysis of Semi-structured Text Data
The processing of semi-structured textual data for further use in DM models is a labor-intensive process, which, in addition to material costs, can increase the time required to build a model, and, as a result, worsen the efficiency of decision-making. This article presents visual models of semistructured text data and methods for their processing at the stage of exploratory analysis. Exploratory analysis will reduce the time to select significant variables at the initial stage of the study and, in the future, avoid the processing of redundant or insignificant variables. The use of visualization will help to include in DM model and process only data that will improve DM model quality. The process of using visualization of textual data in the process of exploratory analysis and the construction of two types of visual models is described - interactive "quantitative" visualization and visualization of relationships between words and other variables in the data under study. Approbation of the developed models is described on the example of labor market analysis. Examples of visualization of the content of the "soft skills" field from the CV and vacancies are presented, displaying both the skills most often mentioned by applicants from various professional fields, and the impact of mentioning these skills on inviting applicants for interviews. The experiment showed that the use of the developed visual models makes it possible to determine whether it is necessary to include a text variable in the DM model at the stage of exploratory analysis.
- Open Access
Ovarian Malignancies Frequency in the Female Population from the Bryansk Region Living in Conditions of Radioactive, Chemical and Combine Contamination (2000–2020)
Background: Radioactive contamination and chemical pollution of the environment can affect the processes of carcinogenesis, including the formation of malignant neoplasms of the ovaries in women. We used the data of official state statistics for 2000–2020 to test the hypothesis about the effect of radioactive contamination (following the Chernobyl disaster) and chemical pollutants on the incidence of ovarian malignancies in the female population of the Bryansk region. Methods: A variety of statistical approaches were used to estimate the incidence of ovarian malignancies, including the Shapiro–Wilk test, Mann–Whitney U test, Spearman’s rank correlation test and linear regression. Results: We did not establish statistically significant differences in the frequency of primary morbidity of women with malignant neoplasms of the ovaries, regardless of the environmental conditions of living. Furthermore, no significant correlations were found between the frequency of primary morbidity of ovarian malignancies, both with the level of contamination by Cesium-137 and Strontium-90, and air pollution with volatile organic compounds, carbon monoxide, sulfur dioxide and nitrogen oxides. A statistically significant increase in the long-term trend in the frequency of ovarian malignant neoplasms was revealed in the areas of chemical pollution (p = 0.02), however, in other territories, no statistically significant regularities were established. The forecast of the frequency of newly diagnosed malignant neoplasms of the ovaries on average in the Bryansk region shows an increase of 12.4% in 2020 in comparison with the real data for 2020, while the largest increase in predicted values is recorded in the territories of radioactive contamination (by 79.6%), and the least in the combined territories (by 6.9%). Conclusions: The results obtained indicate the need for further work to understand the trends in the presence/absence of independent and combined effects of pollutants and the growth of oncogynecological pathology from the perspective of assessing the distant and regional metastasis, histological and immunohistochemical profile of a specific malignant ovarian neoplasm with levels of environmental contamination.
Open AccessOvarian Malignancies Frequency in the Female Population from the Bryansk Region Living in Conditions of Radioactive, Chemical and Combine Contamination (2000–2020)
Background: Radioactive contamination and chemical pollution of the environment can affect the processes of carcinogenesis, including the formation of malignant neoplasms of the ovaries in women. We used the data of official state statistics for 2000–2020 to test the hypothesis about the effect of radioactive contamination (following the Chernobyl disaster) and chemical pollutants on the incidence of ovarian malignancies in the female population of the Bryansk region. Methods: A variety of statistical approaches were used to estimate the incidence of ovarian malignancies, including the Shapiro–Wilk test, Mann–Whitney U test, Spearman’s rank correlation test and linear regression. Results: We did not establish statistically significant differences in the frequency of primary morbidity of women with malignant neoplasms of the ovaries, regardless of the environmental conditions of living. Furthermore, no significant correlations were found between the frequency of primary morbidity of ovarian malignancies, both with the level of contamination by Cesium-137 and Strontium-90, and air pollution with volatile organic compounds, carbon monoxide, sulfur dioxide and nitrogen oxides. A statistically significant increase in the long-term trend in the frequency of ovarian malignant neoplasms was revealed in the areas of chemical pollution (p = 0.02), however, in other territories, no statistically significant regularities were established. The forecast of the frequency of newly diagnosed malignant neoplasms of the ovaries on average in the Bryansk region shows an increase of 12.4% in 2020 in comparison with the real data for 2020, while the largest increase in predicted values is recorded in the territories of radioactive contamination (by 79.6%), and the least in the combined territories (by 6.9%). Conclusions: The results obtained indicate the need for further work to understand the trends in the presence/absence of independent and combined effects of pollutants and the growth of oncogynecological pathology from the perspective of assessing the distant and regional metastasis, histological and immunohistochemical profile of a specific malignant ovarian neoplasm with levels of environmental contamination.
- Open Access
- 1 January 2021
- Published by Keldysh Institute of Applied Mathematics
- p. 917-929
Exploratory Analysis of Biomedical Data in Order to Construct Intelligent Analytical Models for Assessing the Risk of Cancer
This article substantiates the need to use data from an integrated electronic medical record of a patient to assess the risk of cancer. An exploratory analysis of the data of the integrated electronic medical record of patients in the Bryansk region who received a diagnosis of "malignant neoplasm" is being carried out. The influence of the patient's age on the risk of oncological diseases is evaluated by the example of the nosologies C50, C61. Provides an overview of the capabilities of the Auto ML Libraries and their limitations. The article describes the result of constructing models for assessing the risk of oncological diseases based on the ML.NET and Auto-WEKA libraries. It is concluded that it is impossible to constructing models for assessing the risk of oncological diseases based on the data of an integrated electronic medical record using Auto ML libraries without preliminary preparation and preprocessing of data. And since it is required to constructing separate models for each nosology and regular retraining of these models, it is advisable to develop an add-on over the Auto ML libraries that will extract and convert the data of the integrated electronic medical record into a form suitable for analysis. In addition, to improve the quality of the model, it is advisable to use patient history data, data obtained after vectorization of laboratory tests, aggregated data on visits to specialized specialists and related diagnoses, data from online patient questionnaires filled out during the course of medical examination, as well as data on environmental pollution.
- 1 January 2021
- Published by Keldysh Institute of Applied Mathematics
- p. 917-929
Open AccessExploratory Analysis of Biomedical Data in Order to Construct Intelligent Analytical Models for Assessing the Risk of Cancer
This article substantiates the need to use data from an integrated electronic medical record of a patient to assess the risk of cancer. An exploratory analysis of the data of the integrated electronic medical record of patients in the Bryansk region who received a diagnosis of "malignant neoplasm" is being carried out. The influence of the patient's age on the risk of oncological diseases is evaluated by the example of the nosologies C50, C61. Provides an overview of the capabilities of the Auto ML Libraries and their limitations. The article describes the result of constructing models for assessing the risk of oncological diseases based on the ML.NET and Auto-WEKA libraries. It is concluded that it is impossible to constructing models for assessing the risk of oncological diseases based on the data of an integrated electronic medical record using Auto ML libraries without preliminary preparation and preprocessing of data. And since it is required to constructing separate models for each nosology and regular retraining of these models, it is advisable to develop an add-on over the Auto ML libraries that will extract and convert the data of the integrated electronic medical record into a form suitable for analysis. In addition, to improve the quality of the model, it is advisable to use patient history data, data obtained after vectorization of laboratory tests, aggregated data on visits to specialized specialists and related diagnoses, data from online patient questionnaires filled out during the course of medical examination, as well as data on environmental pollution.
- Open Access
- 17 December 2020
- Published by MONOMAX Limited Liability Company
- p. paper78-1
Methodology for Preprocessing Semi-Structured Data for Making Managerial Decisions in the Healthcare
This paper describes the process of supporting management decisionmaking in healthcare based on data mining. The authors described various problems and specifics of data in medical information systems, leading to the complexity of their analysis and integration, such as: the presence of a large number of specific abbreviations, errors in the data and their poor structure. The paper demonstrates an approach to the search and further disclosure of abbreviations in texts, built on a combination of machine and human processing. A method for extracting features from semi-structured fields using an expert in the subject area and using various visualizations is proposed. The proposed abbreviation search and disclosure methods, based on a hybrid approach combining the strengths of processing with the help of a machine and an expert, can increase the number of abbreviations found automatically and significantly reduce the time spent by experts on processing the remaining reductions. In addition, the method for automated feature extraction during integration can significantly increase the amount of useful input data, while reducing the time of the expert.
- 17 December 2020
- Published by MONOMAX Limited Liability Company
- p. paper78-1
Open AccessMethodology for Preprocessing Semi-Structured Data for Making Managerial Decisions in the Healthcare
This paper describes the process of supporting management decisionmaking in healthcare based on data mining. The authors described various problems and specifics of data in medical information systems, leading to the complexity of their analysis and integration, such as: the presence of a large number of specific abbreviations, errors in the data and their poor structure. The paper demonstrates an approach to the search and further disclosure of abbreviations in texts, built on a combination of machine and human processing. A method for extracting features from semi-structured fields using an expert in the subject area and using various visualizations is proposed. The proposed abbreviation search and disclosure methods, based on a hybrid approach combining the strengths of processing with the help of a machine and an expert, can increase the number of abbreviations found automatically and significantly reduce the time spent by experts on processing the remaining reductions. In addition, the method for automated feature extraction during integration can significantly increase the amount of useful input data, while reducing the time of the expert.