PROCESSING ALGORITHM INCORPORATING COMPLEX DEPENDENCIES IN INPUT DATA

Saidov A.D.

Authors

Saidov A.D. Research Institute for the Development of Digital Technologies and Artificial Intelligence

Keywords:

Artificial intelligence, MLP model, QKV algorithm, cardiovascular diseases

Abstract

In this article, an algorithm (QKV) was developed that takes into account many factors in predicting the level of cardiovascular diseases, in particular, taking into account the relationships between factors. With the help of machine learning, the accuracy of the model has been increased, taking into account the complex interconnection of the data included in the MLP model. In addition, in the process of training the dataset processed through the QKV algorithm to the MLP model, it was possible to quickly achieve the minimum value of the Loss function and find the optimal weight coefficient.

References

1. Baessler, B., Mannil, M., Maintz, D., et al. (2018). Texture analysis and machine learning for detecting myocardial infarction in noncontrast-enhanced low-dose CT. «European Radiology», 28(7), 2955вЂ“2964. https://doi.org/10.1007/s00330-017-5230-8

2. Myers, P. D., Scirica, B. M., Stultz, C. M. (2019). Machine learning improves risk stratification after acute coronary syndrome. «Scientific Reports», 9, 15529. https://doi.org/10.1038/s41598-019-51375-9

3. Acharya, U. R., Fujita, H., Oh, S. L., et al. (2017). Application of deep convolutional neural network for automated detection of myocardial infarction using ECG signals. «Information Sciences», 415вЂ“416, 190вЂ“198. https://doi.org/10.1016/j.ins.2017.06.027

4. Radovanovic, S., Tesanovic, A., Lang, P., et al. (2021). Wearable-based machine learning for cardiovascular event prediction. «Sensors», 21(19), 6563. https://doi.org/10.3390/s21196563

5. Dogan, M. V., Beach, S. R., Simons, R. L., et al. (2020). Blood-based biomarkers and machine learning for cardiovascular risk prediction. «Journal of Molecular and Cellular Cardiology», 141, 54вЂ“62. https://doi.org/10.1016/j.yjmcc.2020.03.001

6. Siontis, K. C., Noseworthy, P. A., Attia, Z. I., et al. (2021). Artificial intelligence-enhanced electrocardiography in cardiovascular disease management. «Nature Reviews Cardiology», 18, 465вЂ“478. https://doi.org/10.1038/s41569-020-00503-2

7. Mortazavi, B. J., Bucholz, E. M., Desai, N. R., et al. (2019). Comparison of machine learning methods with traditional models for predicting heart failure readmissions. «Circulation: Heart Failure», 12, e005639.

8. Kusunose, K., Abe, T., Haga, A., et al. (2020). A deep learning approach for assessment of regional wall motion abnormality from echocardiographic images. «JACC: Cardiovascular Imaging», 13(2), 374-381.

9. Ho, J. E., Lyass, A., Courchesne, P., et al. (2018). Protein biomarkers of cardiovascular disease and mortality in the community. «Journal of the American Heart Association», 7, e008108. https://doi.org/10.1161/JAHA.117.008108

10. van Rosendael, A. R., Maliakal, G., Kolli, K. K., et al. (2019). Machine learning integration of coronary CT angiography for risk prediction in stable chest pain. «JACC: Cardiovascular Imaging», 12, 2231 “2240.

11. Steele, A. J., Denaxas, S. C., Shah, A. D., et al. (2018). Machine learning models in electronic health records can outperform conventional survival models for predicting patient mortality in coronary artery disease. «PLoS One», 13, e0202344. https://doi.org/10.1371/journal.pone.0202344

12. Shrivastava, S., et al. (2022). AI-based wearable devices for cardiovascular risk assessment. «Frontiers in Physiology», 13, 854672. https://doi.org/10.3389/fphys.2022.854672

13. Bello, G. A., Dawes, T. J. W., Duan, J., et al. (2019). Deep learning cardiac motion analysis for human survival prediction. «Nature Machine Intelligence», 1, 95вЂ“104. https://doi.org/10.1038/s42256-019-0019-2

14. Ascenzo, F., De Filippo, O., Gallone, G., et al. (2020). Machine learning-based prediction of adverse events following an acute coronary syndrome (PRAISE): A modelling study of 20,000 patients. «European Heart Journal», 42, 1601вЂ“1610. https://doi.org/10.1093/eurheartj/ehaa1010

15. Wu, J., et al. (2021). Deep learning-based ECG analysis for myocardial infarction detection. «Computerized Medical Imaging and Graphics», 88, 101857. https://doi.org/10.1016/j.compmedimag.2021.101857

16. Angraal, S., Mortazavi, B. J., Gupta, A., et al. (2020). Machine learning prediction of mortality and hospitalization in heart failure. «Circulation: Heart Failure», 13, e006574.

17. Lin, A., KolossvГЎry, M., Yuvaraj, J., et al. (2022). Machine learning-based coronary artery disease prediction using CT imaging. «JACC: Cardiovascular Imaging», 15, 703вЂ“714. https://doi.org/10.1016/j.jcmg.2021.10.008.

18. Kennedy, H. L., et al. (2021). Machine learning for stroke risk prediction in post-MI patients. «Stroke», 52, 1234вЂ“1242. https://doi.org/10.1161/STROKEAHA.120.032567.

19. Ganz, P., Heidecker, B., Hveem, K., et al. (2016). Development and validation of a protein-based risk score for cardiovascular outcomes. «JAMA», 315, 1698вЂ“1708. https://doi.org/10.1001/jama.2016.3467.

20. Quer, G., Arnaout, R., Henne, M., et al. (2021). Machine learning and wearable devices for cardiovascular risk assessment. «NPJ Digital Medicine», 4, 65. https://doi.org/10.1038/s41746-021-00427-0.