Algorithms for Monitoring the Effectiveness of Therapeutic and Rehabilitation Procedures Based on Clinical Blood Analysis Indicators in the Medical Decision Support System

The purpose of research is development of algorithms for a computer system for monitoring the effectiveness of therapeutic procedures in terms of clinical blood analysis.

Methods. A set of algorithms has been developed for a computer system for monitoring the effectiveness of medicinal prescriptions based on the results of a clinical blood test, including an algorithm for analyzing the dynamics of intercellular ratios in a clinical blood test, an algorithm for filling in a database, an algorithm for forming a base of decisive rules, an algorithm for analyzing the sensitivity of a decisive rule.

Results. To determine the effectiveness of the treatment plan, it is proposed to evaluate intercluster distances between clustered pathological conditions using the PNN-FNN-FNN* neural network, built on a hybrid basis using probabilistic neural networks and fuzzy decision-making logic. The proposed structure of the PNN-FNN-FNN* hybrid neural network contains three macrolayers. The number of modules in macrolayers is equal to the number of selected clusters of the monitored disease. The first macrolayer consists of blocks of probabilistic neural networks, the number of which in each module is determined by the number of segments allocated in the space of informative features. The second and third macrolayers consist of two-layer fuzzy neural networks. The fuzzy neural network module with the FNN* structure is a block-type macrolayer, each of the blocks of which consists of two layers.

Conclusion. Approbation of monitoring algorithms was carried out on an experimental group of patients with benign prostatic hyperplasia and patients with prostate cancer. Experimental studies of the classification quality indicators of a hybrid neural network with the PNN-FNN-FNN* structure in monitoring the effectiveness of treatment of urological patients have shown diagnostic indicators that allow us to recommend it for use in medical decision support systems when monitoring the effectiveness of treatment of urological patients. 

1. Filist S. A., Tomakova R. A., Emelyanov S. G. Intellektual'nye tekhnologii segmentatsii i klassifikatsii biomeditsinskikh izobrazhenii [Intelligent technologies of segmentation and classification of biomedical images]. Kursk, Southwest State University Publ., 2012. 222 p.

2. Filist S. A., Tomakova R. A., Zhilin V. V., eds. Programmnoe obespechenie intellektual'noi sistemy klassifikatsii formennykh elementov krovi [Software of the intellectual system of classification of the formed elements of blood]. Fundamental'nye issledovaniya = Fundamental Research, 2013, no. 10, pt. 2, pp. 303–307.

3. Filist S. A., Tomakova R. A. Metod obrabotki i analiza slozhnostrukturirouyemykh izobrazheniy na osnove vstroyennykh funktsiy sredy MATLAB [A method for processing and analyzing complexly structured images based on the built-in functions of the MATLAB environment]. Vestnik Chitinskogo gosudarstvennogo universiteta = Bulletin of the Chita State University, 2012, no. 1 (80), pp. 3–9.

4. Stavitsky R. V., Guslisty V. P., Lebedev L. A., Prokubovsky V. I., Keshelava V. V. Sposob otsenki sostoyaniya zdorov'ya patsienta, effekta provodimogo lecheniya i nakoplennoi dozy izlucheniya po analizu krovi [A method for assessing the patient's health status, the effect of the treatment and the accumulated radiation dose by blood analysis]. Patent RF, no. 2135997, 1999.

5. Kurochkin A. G., Kuzmin A. A., Filist S. A. [Database structure for metaanalysis of the effectiveness of medicinal prescriptions according to indications of intercellular ratios in peripheral blood smears]. Sovremennye metody prikladnoi matematiki, teorii upravleniya i komp'yuternykh tekhnologii (PMTUKT – 2015). Sbornik trudov VIII Mezhdunarodnoi konferentsii, Voronezh, 21–26 sentyabrya 2015 goda [Modern methods of applied mathematics, control theory and computer technologies (PMTCT – 2015). Proceedings of the VIII International Conference, Voronezh, 21–26 September 2015]. Voronezh, Scientific Book Publ., 2015, pp. 196–199. (In Russ.)

6. Filist S. A., Shutkin A. N., Uvarova V. V. Strukturno-funktsional'naya model' metaanaliza mediko-ekologicheskikh dannykh [Structural-functional model of meta-analysis of medical and environmental data]. Aktual'nyye napravleniya nauchnykh issledovaniy XXI veka: teoriya i praktika = Actual Directions of Scientific Research of the XXI Century: Theory and Practice, 2015, vol. 3, no. 8-1 (19-1), pp. 364–367.

7. Shutkin A. N., Efremov M. A., Shatalova O. V., eds. Gibridnyye mnogoagentnyye klassifikatory v biotekhnicheskikh sistemakh diagnostiki zabolevaniy i monitoringe lekarstvennykh naznacheniy [Hybrid multi-agent classifiers in biotechnical systems for diagnosing diseases and monitoring drug prescriptions]. Neyrokomp'yutery: razrabotka, primeneniye = Neurocomputers: Development, Application, 2015, no. 6, pp. 42–48.

8. Shutkin A. N., Kurochkin A. G., Protasova V. V., eds. Neyrosetevyye modeli dlya metaanaliza mediko-ekologicheskikh dannykh [Neural network models for metaanalysis of medical and environmental data]. Neyrokomp'yutery: razrabotka, primeneniye = Neurocomputers: Development, Application, 2015, no. 6, pp. 48–54.

9. Filist S. A., Uvarova V. V., Shutkin A. N. Strukturno-funktsional'naya model' metaanaliza mediko-ekologicheskikh dannykh [Structural-functional model of metaanalysis of medical and environmental data]. Voprosy radioelektroniki. Seriya "Obshchetekhnicheskaya" = Questions of Radio Electronics. Series "General technical", 2015, no. 7, pp. 102– 110.

10. Filist S. A., Shatalova O. V., Efremov M. A. Gibridnaya neyronnaya set' s makrosloyami dlya meditsinskikh prilozheniy [Hybrid neural network with macrolayers for medical applications]. Neyrokomp'yutery. Razrabotka i primeneniye = Neurocomputers. Development and Application, 2014, no. 6, pp. 35–39.

11. Filist S. A., Emelyanov S. G., Rybochkin A. F. Neyrosetevoy reshayushchiy modul' dlya issledovaniya zhivykh sistem [Neural network decision module for the study of living systems]. Izvestiya Kurskogo gosudarstvennogo tekhnicheskogo universiteta = Proceedings of the Kursk State Technical University, 2008, no. 2 (23), pp. 77–82.

12. Khatatneh K., Filist S., Al-Kasasbeh R. T., Aikeyeva A. A., Namazov M., Shatalova O., Shaqadan A., Miroshnikov A. Hybrid neural networks with virtual flows in medical risk classifiers. Journal of Intelligent & Fuzzy Systems, 2022, vol. 43, no. 1, pp. 1621–1632. https://doi.org/10.3233/JIFS-212617

13. Shatalova O. V., Filist S. A., Protasova Z. U., Korenevskiy N. A., Al-Kasasbeh R. T., eds. Application of Fuzzy Neural Model and Current-Voltage Analysis of Biologically Active Points for Prediction Post-Surgery Risks. Computer Method in Bio-medical Engineering, 2021, vol. 24, pp. 1504–1516. https://doi.org/10.1080/10255842.2021.1895128

14. Kurochkin A. G., Zhilin V. V., Surzhikova S. E., Filist S. A. Ispol'zovaniye gibridnykh neyrosetevykh modeley dlya mnogoagentnykh sistem klassifikatsii v geterogennom prostranstve informativnykh priznakov [Using hybrid neural network models for multi-agent classification systems in a heterogeneous space of informative features]. Prikaspiyskiy zhurnal: upravleniye i vysokiye tekhnologii = Caspian Journal: Management and High Technologies, 2015, no. 3 (31), pp. 85–95.

15. Kudryavtsev P. S., Shutkin A. N., Protasova V. V., Filist S. A. Funktsional'naya model' dlya monitoringa vliyaniya upravlyayushchikh vozdeystviy na funktsional'noye sostoyaniye samoorganizuyushchikhsya sistem [Functional model for monitoring the influence of control actions on the functional state of self-organizing systems]. Prikaspiyskiy zhurnal: upravleniye i vysokiye tekhnologii = Caspian Journal: Management and High Technologies, 2015, no. 2 (30), pp. 105–118.

16. Filist S. A., Petrova T. V., Journeymen K. V., Shatalova O. V. [Intelligent information systems for monitoring the effectiveness of medicinal prescriptions and therapeutic procedures]. Neirokomp'yutery i ikh primenenie. Tezisy dokladov [Neurocomputers and their application: abstracts of reports]. Moscow, Moscow State Psychological and Pedagogical University Publ., 2018, pp. 74–77. (In Russ.)

17. Filist S. A., Al-Kasasbeh R. T., Shatalova O. V., eds. Classifier for the functional state of the respiratory system via descriptors de-terminated by using multimodal technology. Computer Methods in Biomechanics and Biomedical Engineering, 2022, pp. 1–19.

18. Petrunina E. V., Tomakova R. A., Filist S. A. Gibridnyye metody i modeli dlya biotekhnicheskikh sistem s adaptivnym upravleniyem diagnosticheskimi i reabilitatsionnymi protsessami [Hybrid methods and models for biotechnical systems with adaptive control of diagnostic and rehabilitation processes]. Kursk, Southwest State University Publ., 2022. 249 p.

19. Kurochkin A. G., Kuzmin A. A., Startsev E. A., Filist S. A. Algoritmy metaanaliza effektivnosti diagnosticheskikh i terapevticheskikh resheniy na osnove monitoringa surrogatnykh markerov, poluchayemykh po rezul'tatam analiza slozhnostrukturiruyemykh izobrazheniy [Metaanalysis algorithms for the effectiveness of diagnostic and therapeutic solutions based on the monitoring of surrogate markers obtained from the analysis of complexly structured images]. Izvestiya Yugo-Zapadnogo gosudarstvennogo universiteta. Seriya: Upravleniye, vychislitel'naya tekhnika, informatika. Meditsinskoye priborostroyeniye = Proceedings of the Southwest State University. Series: Control, Computer Engineering, Information Science. Medical Instruments Engineering, 2016, no. 4 (21), pp. 41–55.

20. Arsenyev A. A., Makarov V. K. Issledovaniye sostoyaniya immunoreaktivnosti bol'nykh khronicheskim prostatitom i rakom predstatel'noy zhelezy [Study of the state of immunoreactivity in patients with chronic prostatitis and prostate cancer]. Vestnik Volgogradskogo gosudarstvennogo meditsinskogo universiteta = Bulletin of the Volgograd State Medical University, 2010, is. 2, pp. 34–36.