<link rel="stylesheet" href="styles.f3b1fba60ec7970c.css">

Багатофакторний регресійний аналіз для прогнозування кардіологічного діагнозу на основі функції амплітудної варіабельності

Ескіз

Файли

191678.pdf (610,63 KB)

Дата

2025

Автори


Назва журналу

Номер ISSN

Назва тому

Видавець

Вінницький національний технічний університет

DOI

https://doi.org/10.31649/1997-9266-2025-181-4-136-145

Анотація

Multifactor regression model for automatic cardiac diagnosis prediction based on statistical characteristics of the amplitude variability function of electrocardiographic signals is proposed. The model employs seven statistically significant predictors (mean, median, mode, standard deviation, sample variance, kurtosis, and skewness) ed by means of stepwise regression with forward variable ion the initial set of 13 parameters. The predictor inclusion criterion established a significance level of p &lt; 0.05. The model for prediction of cardiac diagnosis, based on the function of the amplitude variability takes into consideration weight coefficients for each predictor, determined by the least squares method. Central tendency measurements make the greatest contribution into diagnostic outcome formation (β = 201.78 for mean and β = 68.69 for median). The model provides effective differentiation among three clinical states: conditional norm, cardiac rhythm disorders in the form of extrasystole, and morphological conduction abnormalities represented by incomplete left bundle branch block, achieving a Nagelkerke coefficient of determination R² = 0.991. Normal conditions are characterized by minimal amplitude variability values (mathematical expectation 0.00003…0.00064 mV), while extrasystole demonstrates an increase of 3—4 orders of magnitude. Model validation on a representative sample of 204 electrocardiographic signals (102 normal, 51 extrasystole, 51 block) confirmed its high statistical significance (Fisher's F-criterion 953.93, p &lt; 0.001) and compliance with fundamental regression analysis assumptions. Residual analysis demonstrated normal distribution and homoscedasticity, confirming model adequacy. The proposed approach combines the advantages of high interpretability of classical statistical methods with innovative application of the amplitude variability function for comprehensive analysis of morphological and rhythmic characteristics of cardiac signals. The practical significance lies in creating mathematical tools for automated cardiovascular disease diagnostic systems and clinical decision support systems.

Опис

Ключові слова

amplitude variability function , multifactor regression model , electrocardiographic signal , cardiac diagnosis , stepwise regression , extrasystole , eft bundle branch block , CDPCAVF prediction coefficient , statistical predictors , automatic classification of cardiac pathologies

УДК

616.12-073.97:004.9

Тип документа

Article, professional native edition
Article

Мова

uk_UA

Є частиною

Вісник Вінницького політехнічного інституту. № 4 : 136-145.

ISSN

1997-9274

Бібліографічний опис

Сверстюк А. С., Мосій Л. Є. Багатофакторний регресійний аналіз для прогнозування кардіологічного діагнозу на основі функції амплітудної варіабельності // Вісник Вінницького політехнічного інституту. 2025. № 4. С. 136-145. URI: https://visnyk.vntu.edu.ua/index.php/visnyk/article/view/3312.

URI

https://ir.lib.vntu.edu.ua/handle/123456789/51153

Зібрання

Вісник Вінницького політехнічного інституту. 2025. № 4

Схвалення

Рецензія

Доповнено

Цитується в

Список використаної літератури (35)

  1. B. Li, and Y. Lian, “A Forecasting Approach for Wholesale Market Agricultural Product Prices Based on Combined Re-sidual Correction,”Applied Sciences, no. 15(10), 5575, 2025. https://doi.org/10.3390/app15105575.
  2. S. Ali, M. Ali, D. Bhatti, M. S., and B. J. Choi, “Explainable Clustered Federated Learning for Solar Energy Forecast-ing,”Energies, no. 18(9), 2380, 2025. https://doi.org/10.3390/en18092380.
  3. H. Zhang, Y. Liu, C. Zhang, and N. Li, “Machine Learning Methods for Weather Forecasting: a Survey,”Atmosphere, no. 16(1), pp. 82, 2025. https://doi.org/10.3390/atmos16010082.
  4. H. Hewamalage, K. Ackermann, and C. Bergmeir,. Forecast evaluation for data scientists: common pitfalls and best prac-tices. Data Mining and Knowledge Discovery, no. 37(2), pp. 788-832, 2022. https://doi.org/10.1007/s10618-022-00894-5.
  5. G. Skenderi, C. Joppi, M., and M. Cristani, “On the Use of Learning-Based Forecasting Methods for Ameliorating Fash-ion Business Processes: A Position Paper,” In Lecture Notes in Computer Science, pp. 647-659, 2023. Springer Nature Switzer-land. https://doi.org/10.1007/978-3-031-37742-6_50.
  6. J. Kaur, K. S. Parmar, and S. Singh, “Autoregressive models in environmental forecasting time series: a theoretical andapplicationreview”Environmental Science and Pollution Research,no. 30(8),pp. 19617-19641, 2023. https://doi.org/10.1007/s11356-023-25148-9.
  7. M. F. Rizvi, “ARIMA Model Time Series Forecasting,” International Journal for Research in Applied Science and Engi-neering Technology, no. 12(5), pp. 3782-3785, 2024. https://doi.org/10.22214/ijraset.2024.62416.
  8. “Vector Autoregressive Models for Multivariate Time Series. (n.d.),” in Modeling Financial Time Series with S-PLUS®, pp. 385-429. Springer New York. https://doi.org/10.1007/978-0-387-32348-0_11.
  9. M. Di Mauro, G. Galatro, F. Postiglione, W. Song, and A. Liotta, “Multivariate Time Series Characterization and Fore-casting of VoIP Traffic in Real Mobile Networks,”IEEE Transactions on Network and Service Management, no. 21(1),pp. 851-865, 2024. https://doi.org/10.1109/tnsm.2023.3295748.
  10. S. Verstyuk, “Modeling Multivariate Time Series in Economics: From Auto-Regressions to Recurrent Neural Net-works,” SSRN Electronic Journal, 2019. https://doi.org/10.2139/ssrn.3357211.