Multimodal classifier of medical risk based on a multielectrode bioimpedance converter

The purpose of the research. The aim of the study is Russian and foreign studies have shown that malignant breast tumors have significantly different impedance from normal tissues. However, bioimpedance analysis has limitations in resolution, as well as in the imperfection of bioimpedance models required to generate input vectors for machine learning systems.

Methods. The presented study proposes a multimodal classifier, the raw data for which are obtained through an electrode matrix. It also has three channels for processing the results of bioimpedance analysis, with subsequent aggregation of their solutions. An impedance model of biomaterial is proposed, which allows forming descriptors for medical risk classifiers.

Results. Hardware and software for bioimpedance studies have been developed, which include a data collection device for bioimpedance spectroscopy based on an electrode matrix, a device for communication with the object of study, and a device for bioimpedance spectroscopy using an electrode matrix. The software includes interface windows for setting up the bioimpedance research program and training and testing fully connected neural networks. An experimental study of the multimodal classifier on a physical model was conducted using inclusions of higher conductivity (tumor imitation) of various types and sizes in the conductivity range from 1.1 to 1.9 of the background. Based on the obtained images in the two-level neural network of the first channel, the integral risk of breast cancer was determined for all pixels of the image. Statistical studies (ROC analysis) showed sufficient sensitivity and specificity for the screening method - > 0.75. 

Conclusion. Thus, a new model of intelligent support for medical decision-making has been created, integrating the capabilities of bioimpedance spectroscopy, convolutional neural networks and expert assessment of images generated by bioimpedance mapping. However, current data confirming the possibility of separating benign and malignant breast tumors using bioimpedancemetry methods are very limited, which requires further research in this direction.

1. Alieva G.S., Korzhenkova G.P., Kolyadina I.V. Analysis of key radiological characteristics of early invasive breast cancer stages T1a-bN0M0 and DCIS. Onkologicheskii zhurnal: luchevaya diagnostika, luchevaya terapiya = Oncological Journal: Radiodiagnosis, Radiotherapy. 2021;4(1):9–19. (In Russ.) https://doi.org/10.37174/2587-7593-2021-4-1-9-19

2. Khamitov A.R., Ismagilov A.Kh., Savel’eva N.A., Kiyasov I.A. Objectification of topographic-anatomical indicators of malignant breast tumors in ultrasound examination. Povolzhskii onkologicheskii vestnik = Volga Oncology Bulletin. 2017;1(28):59–64. (In Russ.)

3. Zou Y., Guo Z. A review of electrical impedance techniques for breast cancer detection. Medical Engineering & Physics. 2003;25(2):79–90. https://doi.org/10.1016/s1350-4533(02)00194-7

4. Shatalova O.V. Intelligent systems for monitoring medical risks considering bioimpedance studies. Kursk: Yugo-Zapadnyi gosudarstvennyi universitet; 2020. 356 p. (In Russ.)

5. Shatalova O.V., Stadnichenko N.S., Efremov M.A., Bashmakova I.A., Lyakh A.V., Serebrovsky A.V. Technologies of bioimpedance spectroscopy in decision support systems for the diagnosis of socially significant diseases. Izvestiya Yugo-Zapadnogo gosudarstvennogo universiteta. Seriya: Upravlenie, vychislitel’naya tekhnika, informatika. Meditsinskoe priborostroenie = Proceedings of the Southwest State University. Series: Control, Computer Engineering, Information Science. Medical Instruments Engineering. 2023;13(4):148–174. (In Russ.) https://doi.org/10.21869/2223-1536-2023-13-4-148-174

6. Shatalova O.V., Serebrovsky A.V., Stadnichenko N.S., Novoselov A.Yu., Lyakh A.V. Biomedical spectroscopy in classifiers of the functional state of human organs and systems based on hybrid artificial intelligence technologies. Sistemnyi analiz i upravlenie v biomeditsinskikh sistemakh = System Analysis and Control in Biomedical Systems. 2023;22(2):100–113. (In Russ.) https://doi.org/10.36622/VSTU.2023.22.2.015

7. Miroshnikov A.V., Stadnichenko N.S., Shatalova O.V., Filist S.A. Impedance models of biomaterials for forming descriptors in intelligent systems for diagnosing infectious diseases. Modelirovanie, optimiza-tsiya i informatsionnye tekhnologii = Modeling, Optimization and Information Technologies. 2020;8(4):1–14. (In Russ.) https://doi.org/10.26102/2310-6018/2020.31.4.018

8. Naseem U., Rashid J., Ali L., Kim J., Ul Haq Q.E., Awan M.J., Imran M. An Automatic Detection of Breast Cancer Diagnosis and Prognosis Based on Machine Learning Using Ensemble of Classifiers. IEEE Access. 2022;10: 78242–78252.

9. Filist S.A., Emelyanov S.G., Rybochkin A.F. Neural network decision module for studying living systems. Izvestiya Kurskogo gosudarstvennogo tekhnicheskogo universiteta = Proceedings of the Kursk State Technical University. 2008;2(23):77–82 (In Russ.)

10. Zhilin V.V., Filist S.A., Rakhim Kh.A., Shatalova O.V. A method for creating fuzzy neural-network models using the MATLAB package for biomedical applications. Biomedical Engineering. 2008;42(2):64-66. (In Russ.) https://doi.org/10.1007/s10527-008-9019-y

11. Filist S.A., Kassim K.D.A., Rutskiy R.V. Hybrid decision systems for predicting postoperative complications in patients with benign prostatic hyperplasia. Izvestiya Yugo-Zapadnogo gosudar-stvennogo universiteta = Proceedings of the Southwest State University. 2013;5(50):40–49. (In Russ.)

12. Filist S.A., Tomakova R.A., Degtyarev S.V., Rybochkin A.F. Hybrid intelligent models for segmenting chest X-ray images. Meditsinskaya tekhnika = Medical Technology. 2017;5(305):41–45. (In Russ.)

13. Filist S.A., Tomakova R.A., Naser A.A. Fuzzy neural network technologies for segmenting pathological formations and morphological structures in medical images. Biomeditsinskaya radioelektronika = Biomedical Radioelectronics. 2012;(4):43–50. (In Russ.)

14. Serebrovsky A.V., Shatalova O.V., Lyakh A.V., Khalin I.A., Bashmakova I.A., Protasova Z.U. Multimodal classifier for breast cancer risk based on the analysis of biomaterial impedance. Izvestiya Yugo-Zapadnogo gosudarstvennogo universiteta. Seriya: Upravlenie, vychislitel’naya tekhnika, informatika. Meditsinskoe priborostroenie = Proceedings of the Southwest State University. Series: Control, Computer Engineering, Information Science. Medical Instruments Engineering. 2024;14(2):142–159. (In Russ.) https://doi.org/10.21869/2223-1536-2024-14-2-142-159

15. Miroshnikov A.V., Shatalova O.V., Stadnichenko N.S., Shulga L.V. Classifications of biological objects based on multidimensional bioimpedance analysis. Izvestiya Yugo-Zapadnogo gosudarstvennogo universiteta. Seriya: Upravlenie, vychislitel’naya tekhnika, informatika. Meditsinskoe priborostroenie = Proceedings of the Southwest State University. Series: Control, Computer Engineering, Information Science. Medical Instruments Engineering. 2020;10(3/4):29–49. (In Russ.)

16. Filist S.A., Shatalova O.V., Bogdanov A.S. Bioimpedance models in nonlinear voltammetric characteristics and reversible breakdown of the dielectric component of biomaterial. Byulleten’ sibirskoi meditsiny = Bulletin of Siberian Medicine. 2014;13(4):129–135. (In Russ.)

17. Miroshnikov A.V., Shatalova O.V., Efremov M.A., Stadnichenko N.S., Novoselov A.Yu., Pavlenko A.V. Algorithm for optimizing the Voit model in classifiers of the functional state of living systems. Izvestiya Yugo-Zapadnogo gosudarstvennogo universiteta. Seriya: Upravlenie, vychislitel’naya tekhnika, informatika. Meditsinskoe priborostroenie = Proceedings of the Southwest State University. Series: Control, Computer Engineering, Information Science. Medical Instruments Engineering. 2022;12(2):59–75. (In Russ.) https://doi.org/10.21869/2223-1536-2022-12-2-59-75

18. Kurachkin A.G., Zhilin V.V., Surzhikova S.A., Filist S.A. Using hybrid neural network models for multi-agent classification systems in heterogeneous spaces of informative features. Prikaspiiskii zhurnal: upravlenie i vysokie tekhnologii = Caspian Journal: Management and High Technologies. 2015;3(31):85–95. (In Russ.)

19. Kurachkin A.G., Protasova V.V., Filist S.A., Shutkin A.N. Neural network models for meta-analysis of medical and environmental data. Neirokomp’yutery. Razrabotka, primenenie = Neurocomputers. Development and Application. 2015;(6):42–48. (In Russ.)

20. Filist S.A., Shatalova O.V., Efremov M.A. Hybrid neural network with macro layers for medical applications. Neirokomp’yutery. Razrabotka i primenenie = Neurocomputers. Development and Application. 2014;(6):35–39. (In Russ.)

21. Surzhikova S.E., Shatalova O.V., Fedyanin V.V. Software and hardware complex for diagnosing socially significant diseases. Izvestiya Yugo-Zapadnogo gosudarstvennogo universiteta. Seriya: Upravlenie, vychislitel’naya tekhnika, informatika. Meditsinskoe priborostroenie = Proceedings of the Southwest State University. Series: Control, Computer Engineering, Information Science. Medical Instruments Engineering. 2015;2(15):79–87. (In Russ.)

22. Surzhikova S.E., Shatalova O.V., Fedyanin V.V. Software and hardware complex for analyzing voltammetric characteristics of bioactive points based on the L-CARD E20-10 module. Prikaspiiskii zhurnal: upravlenie i vysokie tekhnologii = Caspian Journal: Management and High Technologies. 2015;2(30):150–161. (In Russ.)

23. Petrunina E.V., Shatalova O.V., Alavsi Haider A.H., Pesok V.V., Kuzmin A.A., Shulga L.V. Multimodal classifier of cardiorespiratory risk taking into account comorbidities and synergy effect. Izvestiya Yugo-Zapadnogo gosudarstvennogo universiteta. Seriya: Upravlenie, vychislitel’naya tekhnika, informatika. Meditsinskoe priborostroenie = Proceedings of the Southwest State University. Series: Control, Computer Engineering, Information Science. Medical Instruments Engineering. 2024;14(2):81–105. (In Russ.) https://doi.org/10.21869/2223-1536-2024-14-2-81-105

24. Petrova T.V., Kuzmin A.A., Savinov D.Yu., Serebrovsky V.V. Distributed autonomous intelligent agents for monitoring and meta-analysis of the effectiveness of managing living systems. Prikaspiiskii zhurnal: upravlenie i vysokie tekhnologii = Caspian Journal: Management and High Technologies. 2017;40(4):61–73. (In Russ.)

25. Kudryavtsev P.S., Shutkin A.N., Protasova V.V., Filist S.A. Structural-functional model for monitoring the influence of control actions on the functional state of self-organizing systems. Prikaspiiskii zhurnal: upravlenie i vysokie tekhnologii = Caspian Journal: Management and High Technologies. 2015;(2):105–118. (In Russ.)