Agent-oriented data clustering for medical monitoring

Strilets, Viktoriia; Donets, Volodymyr; Ugryumov, Mykhaylo; Artiukh, Sergii; Zelenskyi, Roman; Goncharova, Tamara

doi:10.32620/reks.2022.1.08

Cited by 5 publications

(10 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…1 is an adaptation of the stratification subsystem to a computer medical monitoring system. The stratification subsystem in the proposed implementation contains a Cluster Analysis (CA) module based on a modified multi-agent fuzzy clustering method [9]. The system also includes a Neural Network Classifier (NNC) module, based on a modified neural network learning procedure [10], and a Sensitivity Analysis (SA) module, which will be discussed in more detail in this work.…”

Section: Methodsmentioning

confidence: 99%

“…The works [9,10] consider testing methods and models for modules of cluster analysis and data classification in the field of medical monitoring. The advantage is that it shows how the proposed methods and models can improve the accuracy of healthcare professionals' work and healthcare quality.…”

Section: Literature Review and Problem Statementmentioning

confidence: 99%

“…The cluster analysis module uses the multi-agent fuzzy clustering method [9]. The method was obtained by combining the modified c-means and multi-agent methods [9].…”

Section: Fig 2 Autoencoder Architecturementioning

confidence: 99%

See 2 more Smart Citations

Application of a data stratification approach in computer medical monitoring systems

Donets,

Shevchenko,

Holikov

et al. 2024

EEJET

View full text Add to dashboard Cite

The research object is the processes occurring in the data stratification subsystem in the medical monitoring computer system, which is part of the decision support system. Such a subsystem aims to solve data analysis and processing problems in the medical monitoring system. Among them, the problems of anomaly detection, data marking, state determination, selection of the most informative variables, and justification of decision-making are selected for solving. The paper proposes the structure and implementation of the data stratification subsystem in the decision support system. The subsystem contains modules for anomaly detection and an autoencoder, a clustering module using an advanced multi-agent clustering method, and a state detection module with a modified neural network training procedure. Modules of the stratification subsystem have been tested using diabetes monitoring data. The results showed that the clustering module provides 25.7 % lower accuracy than the achieved neural network. The accuracy difference is explained by the complexity of the data and the lack of adaptability of the proposed method to solving such problems. It is shown that the method of determining the overall informativeness of variables covers 90 % informativeness with 10 variables, comparable to the variability data. In general, the flexible nature of the proposed stratification subsystem allows for solving the problems. The proposed stratification subsystem offers a robust solution for improving treatment strategies and decision-making in computer medical monitoring systems. Its versatility allows it to be used in any system where decision support is needed, providing valuable information about informative variables and decision-making features for clinicians and researchers

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Literature Review and Problem Statementmentioning

confidence: 99%

See 1 more Smart Citation

Application of a data stratification approach in computer medical monitoring systems

Donets,

Shevchenko,

Holikov

et al. 2024

EEJET

View full text Add to dashboard Cite

show abstract

“…Every year, information technologies (ITs) in medicine find more and more applications. The need to use large and constantly growing amounts of information when solving diagnostic, therapeutic, statistical, managerial, and other tasks is the reason for the intensification of the use of information technologies in medical institutions today [1,2].…”

Section: Introduction 1motivationmentioning

confidence: 99%

Methodology for the development and application of clinical decisions support information technologies with consideration of civil-legal grounds

Hnatchuk

Hovorushchenko²,

Sergeenko³

2023

reks

View full text Add to dashboard Cite

Currently, there are no clinical decision support information technologies (CDSIT) that would consider civil-legal grounds when forming a decision for clinicians. Therefore, the design, development, and implementation of CDSIT, which considers civil-legal grounds when forming decisions, are actual problems. Methodology for the development and application of knowledge-driven, rule-based, clinical decisions support information technologies with consideration of civil-legal grounds has been developed, which provides a theoretical basis for developing clinical decisions support information technology with consideration of civil-legal grounds and partial CDSITs regarding the possibility of providing medical services of a certain type. In addition to the conclusion about the possibility or impossibility of providing certain medical services, the developed methodology ensures the presence of all essential terms (from the viewpoint of civil law regulation) in the contract for the certain medical service's provision and/or the data on potential patients for the provision of such a service, as well as minimization of the influence of the human factor when making clinical decisions. It is advisable to evaluate the CDSITs with consideration of civil-legal grounds, developed according to the proposed methodology, from the viewpoint of the correctness of the decisions generated by them, as well as from the viewpoint of their usefulness for clinics. In this paper, experiments with the methodology-based CDSIT regarding the possibility of performing a surrogate motherhood procedure with consideration of civil-legal grounds were conducted. Such experiments showed the correctness of the generated decisions at the level of 97 %. Experiments also demonstrated the usefulness of such IT for clinics from the viewpoint of eliminating adverse legal consequences, as they might arise due to violation or disregard of legal, and moral and ethical norms.

show abstract

“…Digital transformations have not bypassed the healthcare sector [9], including fighting the pandemic. Many research groups have joined forces to develop models and methods for studying vaccines [10], diagnostics [11], drugs [12], the virus spread [13], and evaluating the effectiveness of control measures [14].…”

Section: Introductionmentioning

confidence: 99%

Impact of war on COVID-19 pandemic in Ukraine: the simulation study

Chumachenko

Pyrohov

Meniailov

et al. 2022

reks

View full text Add to dashboard Cite

The COVID-19 pandemic has posed a challenge to public health systems worldwide. As of March 2022, almost 500 million cases have been reported worldwide. More than 6.2 million people died. The war that Russia launched for no reason on the territory of Ukraine is not only the cause of the death of thousands of people and the destruction of dozens of cities but also a large-scale humanitarian crisis. The military invasion also affected the public health sector. The impossibility of providing medical care, non-compliance with sanitary conditions in areas where active hostilities are occurring, high population density during the evacuation, and other factors contribute to a new stage in the spread of COVID-19 in Ukraine. Building an adequate model of the epidemic process will make it possible to assess the actual statistics of the incidence of COVID-19 and assess the risks and effectiveness of measures to curb the curse of the disease epidemic process. The article aims to develop a simulation model of the COVID-19 epidemic process in Ukraine and to study the results of an experimental study in war conditions. The research is targeted at the epidemic process of COVID-19 under military conditions. The subjects of the study are models and methods for modeling the epidemic process based on statistical machine learning methods. To achieve the study's aim, we used forecasting methods and built a model of the COVID-19 epidemic process based on the polynomial regression method. Because of the experiments, the accuracy of predicting new cases of COVID-19 in Ukraine for 30 days was 97,98%, and deaths of COVID-19 in Ukraine – was 99,87%. The model was applied to data on the incidence of COVID-19 in Ukraine for the first month of the war (02/24/22 - 03/25/22). The calculated predictive values showed a significant deviation from the registered statistics. Conclusions. This article describes experimental studies of implementing the COVID-19 epidemic process model in Ukraine based on the polynomial regression method. The constructed model was sufficiently accurate in deciding on anti-epidemic measures to combat the COVID-19 pandemic in the selected area. The study of the model in data on the incidence of COVID-19 in Ukraine during the war made it possible to assess the completeness of the recorded statistics, identify the risks of the spread of COVID-19 in wartime, and determine the necessary measures to curb the epidemic curse of the incidence of COVID-19 in Ukraine. The investigation of the experimental study results shows a significant decrease in the registration of the COVID-19 incidence in Ukraine. An analysis of the situation showed difficulty in accessing medical care, a reduction in diagnosis and registration of new cases, and the war led to the intensification of the COVID-19 epidemic process.

show abstract

Agent-oriented data clustering for medical monitoring

Cited by 5 publications

References 7 publications

Application of a data stratification approach in computer medical monitoring systems

Application of a data stratification approach in computer medical monitoring systems

Methodology for the development and application of clinical decisions support information technologies with consideration of civil-legal grounds

Impact of war on COVID-19 pandemic in Ukraine: the simulation study

Contact Info

Product

Resources

About