Development of a system for evaluating the personalized effect of treatment based on Mixture-of-Experts model using the Mahalanobis distance

S. Mhammad, S. А. Molodyakov, L.V. Utkin

Abstract


The concept of personalized treatment aim to improve effectiveness of treatment by studying the characteristics for patients. Practical work on personalized treatment using modern technologies and artificial intelligence have emerged in recent years.  Most of these studies focused on using existing algorithms, and evaluating their effectiveness, while a few tried to develop new methods. In this study, a new structure for evaluating the personalized effect of treatment is proposed using Mixture of Experts model and a Siamese network. To calculate the correlation between features and find the similarity index, the Mahalanobis distance is used. The system contains two branch: control and treatment. The effectiveness of personalized treatment is measured using Conditional Average Treatment Effect CATE. Finally, the system can be used in future research to improve the treatment of many diseases.


Full Text:

PDF (Russian)

References


Maltsev D., Tyravska Y., Shpryakha Y., Kaminskyy V., & Merzliak S. Individualised Medicine: Application of a Personalised Approach in Clinical Practice. Journal of Pioneering Medical Sciences, 2025, vol. 14, no. 6, pp. 7–19. DOI: 10.47310/jpms2025140602

Akomolafe O. O., Okoli A. O., & Merotiwon D. O. A Systematic Review of Personalized Medicine’s Role in Improving Cancer Therapy and Outcomes. International Journal of Pharma Growth Research Review, 2025, vol. 2, no. 3, pp. 24–29. DOI: 10.54660/IJPGRR.2025.2.3.24-29

Li Z., & Wang L. Multi-task reinforcement learning and explainable AI-Driven platform for personalized planning and clinical decision support in orthodontic-orthognathic treatment. Scientific Reports, 2025, vol. 15, no. 1. DOI : 10.1038/s41598-025-09236-z

Fan Y., Lv J., & Wang J. DNN: A Two-Scale Distributional Tale of Heterogeneous Treatment Effect Inference. SSRN Electronic Journal, 2018. DOI: https://doi.org/10.2139/ssrn.3238897

Alagoz O., Hsu H., Schaefer A. J., & Roberts M. S. Markov decision processes: A tool for sequential decision making under uncertainty. Medical Decision Making, 2010, vol. 30, no. 4, pp. 474–483. DOI : 10.1177/0272989X09353194

Lu M., Sadiq S., Feaster D. J., & Ishwaran H. Estimating Individual Treatment Effect in Observational Data Using Random Forest Methods. Journal of Computational and Graphical Statistics, 2018, vol. 27, no. 1, pp. 209–219. DOI : 10.1080/10618600.2017.1356325

Caron A., Baio G., & Manolopoulou I. Estimating individual treatment effects using non-parametric regression models: A review. Journal of the Royal Statistical Society. Series A: Statistics in Society, 2022, vol. 185, no. 3, pp. 1115–1149. DOI :10.1111/rssa.12824

Acharki N. et al. Heterogeneous Treatment Effects Estimation: When Machine Learning meets multiple treatments regime //53èmes Journées de Statistique, 2022

Konstantinov A., Kirpichenko S., & Utkin L. Heterogeneous Treatment Effect with Trained Kernels of the Nadaraya–Watson Regression. Algorithms, 2023, vol. 16, no. 5. DOI: 10.3390/a16050226

Fernández-Loría C., Provost F. Causal classification: Treatment effect estimation vs. outcome prediction //Journal of Machine Learning Research. – 2022. – Т. 23. – №. 59. – С. 1-35.

Wang Q., Chen Z., Zhang H., Zhou Y., Du C., Hu W., Lv X., Xie T., & Zheng H. Large language models could be applied in personalized out-of-hospital management for breast cancer: a prospective randomized single blind study. Scientific Reports, 2025, vol. 15, no. 1, DOI:10.1038/s41598-025-18759-4

Vegetabile B. G. On the distinction between" conditional average treatment effects"(cate) and" individual treatment effects"(ite) under ignorability assumptions. arXiv preprint, 2021. arXiv:2108.04939

Wolf J. M. tehtuner: An R package to fit and tune models for the conditional average treatment effect. Journal of Open Source Software, 2023, vol. 8, no. 86, p. 5453. DOI: 10.21105/joss.05453

Kobayashi G. et al. Incorporating residual and normalization layers into analysis of masked language models //Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing. – 2021. – С. 4547-4568.

Lu Y. et al. Beyond finite layer neural networks: Bridging deep architectures and numerical differential equations //International conference on machine learning. – PMLR, 2018. – С. 3276-3285.

Xu L. Configuration Strategy and Application of Siemens PLC Control

Network. Learning & Education, 2021, vol. 10, no. 3, pp. 40-43.

Bellet A., Habrard A., Sebban M. A survey on metric learning for feature vectors and structured data //arXiv preprint arXiv:1306.6709. – 2013.


Refbacks

  • There are currently no refbacks.


Abava  Кибербезопасность Monetec 2026 СНЭ

ISSN: 2307-8162