2021, issue 2, p. 57-62
Received 20.04.2021; Revised 30.04.2021; Accepted 24.06.2021
Published 30.06.2021; First Online 01.07.2021
Modification of the Use of Bayesian Recognition Procedures for Inflammatory Processes in Gliomas, Metastasis and Meningiomas by Indicators of Erythrocyte Sedimentation Rate
1 V.M. Glushkov Institute of Cybernetics of the NAS of Ukraine, Kyiv
2 A.P. Romodanov Insitute of Neurosurgery of NAS of Ukraine, Kyiv
Introduction. The article discusses the application of Bayesian recognition procedures with one independent feature in relation to the erythrocyte sedimentation rate data taken from patients with gliomas, metastases, meningiomas, traumatic brain injury and from a group of healthy people.
Purpose of the article. Analysis of erythrocyte sedimentation rate indicators using optimal recognition procedures.
Results. In earlier articles by the authors, a similar work was described, however, due to the fact that the erythrocyte sedimentation rate was measured in different concentrations of pharmaceuticals and due to the receipt of new data structures, it was possible to increase the efficiency of the recognition procedures by 3-4%. The maximum recognition efficiency of almost 90% was achieved in the differential diagnosis of gliomas in relation to traumatic brain injury and the use of a substance supplemented with chlorpromazine. When recognizing inflammatory processes in patients with metatsases in relation to a group of healthy people, the efficiency of the recognition procedure was 88% using NaATF with a dilution of 1:10. We also note a 4% increase in the recognition efficiency of conditionally benign grade II gliomas, i.e. the efficiency of recognition of the development of gliomas in the early stages increased. Also in this work, it was possible to identify inflammatory processes in benign extracerebral tumors - meningiomas. The effectiveness of this recognition in relation to a group of healthy people was 83%.
Conclusions. New results of recognition of inflammatory processes in brain gliomas have been obtained, on the basis of which an auxiliary diagnostic tool has been improved in gliomas, metastases and meningiomas. This diagnostic method becomes especially valuable in cases where modern imaging diagnostic methods are not able to determine the presence of a tumor in a patient, as well as in the postoperative period with indulgent tumor growth.
Keywords: Bayesian recognition procedure, gliomas, metastases, meningiomas, erythrocyte sedimentation rate, complex parameter.
Cite as: Tarasov A.L., Gupal A.M., Gridina N.Ya. Modification of the Use of Bayesian Recognition Procedures for Inflammatory Processes in Gliomas, Metastasis and Meningiomas by Indicators of Erythrocyte Sedimentation Rate. Cybernetics and Computer Technologies. 2021. 2. P. 57–62. (in Ukrainian) https://doi.org/10.34229/2707-451X.21.2.5
1. Gridina N.Ya., Gupal A.M., Sergienko I.V., Tarasov A.L. Analysis of Speed Indexes of Erythrocyte Sedimentation for Cerebral Gliomas. Journal of Automation and Information Sciences. 2007. 39 (12). P. 52–59. https://doi.org/10.1615/JAutomatInfScien.v39.i12.50
2. Sergienko I.V., Gridina N.Ya., Gupal A.M., Tarasov A.L. The Use of Bayesian Recognition Procedure by Erythrocyte Sedimentation Rate when Brain Gliomas. Journal of Automation and Information Sciences. 2009. 41 (1). P. 8–14. https://doi.org/10.1615/JAutomatInfScien.v41.i1.20
3. Palagin A.V., Gridina N.Ya., Gupal A.M., Tarasov A.L. Computer-Based System of Analysis of Erythrocyte Sedimentation Rate Factors at Brain Gliomas. Journal of Automation and Information Sciences. 2009. 41 (5). P. 70–79. https://doi.org/10.1615/JAutomatInfScien.v41.i5.80
4. Sergienko I.V., Gridina N.Ya., Gupal A.M., Tarasov A.L. Bayesian Procedure of Brain Gliomas Recognition. Journal of Automation and Information Sciences. 2009. 41 (9). P. 74–79. https://doi.org/10.1615/JAutomatInfScien.v41.i9.60
5. Gridina N.Ya., Gupal A.M., Tarasov A.L. Comparative Analysis of Recognition Methods of Inflammatory Processes at the Gliomas of Brain. Journal of Automation and Information Sciences. 2010. 42 (5). P. 45–52. https://doi.org/10.1615/JAutomatInfScien.v42.i5.50
6. Gridina N.Ya., Vagis A.A., Tarasov A.L. Recognition procedures on Bayesian networks for erythrocyte sedimentation rate indicators. Computer mathematics. 2013. 2. P. 97–104. (in Russian) http://dspace.nbuv.gov.ua/handle/123456789/84753
7. Gridina N.Ja., Gupal A.M., Tarasov A.L. Bayesian Recognition of Inflammatory Processes in Brain Gliomas. Cybernetics and Systems Analysis. 2017. 53. P. 366–372. https://doi.org/10.1007/s10559-017-9936-4
ISSN 2707-451X (Online)
ISSN 2707-4501 (Print)