Hybrid genetic algorithm for identifying parameters of nonlinear models with constraints in biomaterial impedance problems

Purpose of research. The research objective is to evaluate the effectiveness of a hybrid algorithm combining a genetic algorithm (GA) and a least squares method (LSM) designed to identify bioimpedance parameters in the tasks of pulmonary pathology diagnostics. The main attention is paid to improving the measurement accuracy (the norm of the residual ≤ 0.09) and developing recommendations for integrating the method into software and.

Methods. The study was performed on the basis of the E20-10 module ("L-Card"), which generates sinusoidal signals using ECG electrodes. to minimize parasitic containers. The bioimpedance parameters were identified using a hybrid algorithm in which genetic search was combined with the least squares method, including regularization (λ=0.1). Data analysis was carried out using the Cole method, and measurement control was carried out through software implemented in Delphi, which provided real—time signal processing.

Results. Based on the E20-10 module and a complex developed for measurement and biological analysis. The average distance between the model data and Xperiment is 4% (standard deviation of 0.09). The REXTRA identification error does not exceed 2.1%, which confirms the reliability of the method in clinical settings.

Conclusion. The study has confirmed that the hybrid algorithm provides high accuracy (residual norm of 0.09) and the ability to regenerate when determining biological parameters. Analysis of the characteristics of the amplitude and frequency phase, which allowed the development of classifications that can automate the diagnosis of lung diseases. The results showed that the potential of the method is to create a medical diagnostic package that can work in real time (1 sec per analysis). However, additional research on living subjects is required for clinical implementation, as well as the adaptation of algorithms for various diseases.

1. Grimnes S., Martinsen О.G. Bioimpedance and Bioelectricity Basics. Academic Press; 2015. 490 p.

2. Korsunsky N.A. Bioimpedance Analysis in Pulmonology. Meditsinskie tekhnologii = Medical Technologies. 2020; 15(3): 45–52. (In Russ.).

3. Fuks L.F., et al. Low-frequency impedance spectroscopy for extracellular matrix analysis. Annals of Biomedical Engineering. 2021; 49: 267–275.

4. Serebrovsky A.V., Korsunsky N.A., Lyakh A.V., Mishustin V.N., Shatalova O.V., Shulga L.V. Multimodal classifier of medical risk based on a multielectrode bioimpedance converter. Izvestiya Yugo-Zapadnogo gosudarstvennogo universiteta. Seriya: Upravlenie, vychislitel'naya tekhnika, informatika. Meditsinskoe priborostroenie = Proceedings of the Southwest State University. Series: IT Management, Computer Science, Computer Engineering. Medical Equipment Engineering. 2024;14(3):121-143. (In Russ.). https://doi.org/10.21869/2223-1536-2024-14-3-121-143.

5. Korsunsky N.A., et al. Baseline in Bioimpedance Diagnostics. Vestnik novykh meditsinskikh tekhnologi = Journal of New Medical Technologies. 2023; 10(2): 112–118. (In Russ.).

6. Korsunsky N.A. Neural network methods in biomedical diagnostics. Iskusstvennyi intellekt v meditsine = Artificial intelligence in medicine. 2022; 8(4): 22–30. (In Russ.).

7. Miroshnikov A.V., Shatalova O.V., Efremov M.A., Stadnichenko N.S., Novoselov A.Y., Pavlenko A.V. Method for Classification of the Functional State of Living Systems Based on Recurrent Voigt Models. Izvestiya Yugo-Zapadnogo gosudarstvennogo universiteta. Seriya: Upravlenie, vychislitel'naya tekhnika, informatika. Meditsinskoe priborostroenie = Proceedings of the Southwest State University. Series: IT Management, Computer Science, Computer Engineering. Medical Equipment Engineering. 2022;12(2):59-75. (In Russ.). https://doi.org/10.21869/2223-1536-2022-12-2-59-75.

8. Oludare I.A., Jantan A., Kemi V.D., Asrshad H. State-of-the-Art in Artificial Neural Network Applications: A Survey. Heliyon. 2018; 4(11): 160–204. DOI 10.1016/j.heliyon.2018.e00938.

9. Pecherskaya E. A., Antipenko V. V., Karpanin O. V., et al. Metrological aspects of the automated method of bioimpedance measurement. Pribory, sistemy i izdeliya meditsinskogo naznacheniya = Medical Devices, Systems, and Products. 2020; (3): 78–84. (In Russ.).

10. Agrebi S., Larbi A. Use of artificial intelligence in infectious diseases. Medical Decision Making. 2020; 6(3): 415–438. DOI 10.1016/B978-0-12-817133-2.00018-5.

11. Agrebi S., Larbi A. The need for uncertainty quantification in machine-assisted medical decision making. Nature Machine Intelligence. 2019; 1(1): 20–23. DOI 10.1038/s42256-018-0004-1.

12. Goldberg D.E. Genetic Algorithms in Optimization. Addison-Wesley, 1989. 412 p.7. National Instruments. PXIe-5122 User Manual. 2021. 87 p.

13. Martinsen O.G., et al. Instrumentation for bioimpedance spectroscopy. Journal of Electrical Bioimpedance. 2019; 10: 1–8. DOI: 10.2478/joeb-2019-0001

14. Nocedal J., Wright S. Numerical Optimization. Springer, 2006. 664 p.

15. Zhang Y., et al. Hybrid optimization in medicine. Journal of Computational Physics. 2021; 445:110567. DOI: 10.1016/j.jcp.2021.110567

16. Sarvamangala D.R. Evolutionary algorithms in biomedical engineering. Evolutionary Intelligence. 2022; 15: 151–173. DOI: 10.1007/s12065-020-00540-3

17. Baiburin R.Kh. Biomedical Sensors. Biomeditsinskie tekhnologii = Biomedical Technologies. 2020; 15: 34–40. (In Russ.).

18. Rinaldi S., et al. Clinical validation of bioimpedance models. Medical Engineering & Physics. 2020; 85: 63–71.

19. Wu K., et al. Portable bioimpedance systems: Design and applications. Scientific Reports. 2022; 12: 6789. DOI: 10.1038/s41598-022-10888-4

20. Oludare I.A., et al. Adaptive filtering in bioimpedance signals. Heliyon. 2018; 4: e00938. DOI: 10.1016/j.heliyon.2018.e00938