graduate student from 01.01.2020 until now
Russian Federation
Russian Federation
519.688
A study presents a comparative analysis of the extended Cox model with modern survival analysis methods. The main purpose of the research is to evaluate the predictive capabilities of the extended Cox model in comparison with current survival analysis models and techniques. To achieve this goal, machine learning methods (survival random forest, gradient boosting, support vector machines) and classical statistical approaches (Weibull, log-logistic, and log-normal models) were used. Research method includes the analysis of three datasets: prostate cancer patients, criminal recidivism data, and breast cancer patients. The results of the stydy demonstrate that the extended Cox model outperforms or is comparable in accuracy to modern machine learning methods while maintaining high interpretability. Practical significance of the work lies in the applicability of the extended Cox model in medicine, social sciences, and other fields where both prediction accuracy and understanding of the influence of factors on the risk of an event are crucial. The scientific novelty of the study lies in conducting the first comparative analysis of the extended Cox model with other survival analysis methods, opening new opportunities for improving and adapting the model in future research. The study is of great importance for the development of survival analysis methods and their application in practical tasks, contributing to increased prediction accuracy and improved interpretability of results.
survival analysis, Cox model, metaheuristic algorithms, ant colony optimization, optimization.
1. Letchikov A. V., Matveev R. Yu., Shirobokova M. A. Reshenie problemy cenzurirovannyh dannyh pri modelirovanii ocenki individual'nogo kreditnogo riska // Vestnik Udmurtskogo universiteta. Seriya «Ekonomika i pravo». 2019. T. 29, Vyp. 1. S. 34–41.
2. Heterogeneous Datasets for Federated Survival Analysis Simulation / A. Archetti, E. Lomurno, F. Lattari [et al.] // ICPE ‘23 Companion: Companion of the ACM/SPEC International Conference on Performance Engineering (Coimbra, Portugal, 15–19 April 2023). New York (NY): Association for Computing Machinery, 2023. Pp. 173–180. DOI:https://doi.org/10.1145/3578245.3584935.
3. Mikulik I. I., Zharinov G. M., Kneev A. Yu. Algoritm postroeniya funkcii riska rasshirennoy modeli Koksa i ego primenenie na baze dannyh bol'nyh rakom predstatel'noy zhelezy // Advanced Engineering Research (Rostov-on- Don). 2024. T. 24, № 4. S. 413–423. DOI:https://doi.org/10.23947/2687-1653-2024-24-4-413-423.
4. Wang P., Li Y., Reddy C. K. Machine Learning for Survival Analysis: A Survey // ACM Computing Surveys. 2019. Vol. 51, Iss. 6. Art. No. 110. 36 p. DOI:https://doi.org/10.1145/3214306.
5. Overview of Parametric Survival Analysis for Health-Economic Applications / K. J. Ishak, N. Kreif, A. Benedict, N. Muszbek // PharmacoEconomics. 2013. Vol. 31, Iss. 8. Pp. 663–675. DOI:https://doi.org/10.1007/s40273-013-0064-3.
6. Zhu S., Campanella O., Chen G. Estimation of Parameters in the Weibull Model from Microbial Survival Data Obtained Under Constant Conditions with Come-up Times // Journal of Food Engineering. 2021. Vol. 292. Art. No. 110364. 10 p. DOI:https://doi.org/10.1016/j.jfoodeng.2020.110364.
7. Borges P. Estimating the Turning Point of the Log-Logistic Hazard Function in the Presence of Long-Term Survivors with an Application for Uterine Cervical Cancer Data // Journal of Applied Statistics. 2021. Vol. 48, Iss. 2. Pp. 203–213. DOI:https://doi.org/10.1080/02664763.2020.1720627.
8. Extrapolation of Survival Curves Using Standard Parametric Models and Flexible Parametric Spline Models: Comparisons in Large Registry Cohorts with Advanced Cancer / J. Gray, T. Sullivan, N. R. Latimer [et al.] // Medical Decision Making. 2021. Vol. 41, Iss. 2. Pp. 179–193. DOI:https://doi.org/10.1177/0272989X20978958.
9. Decision Tree for Competing Risks Survival Probability in Breast Cancer Study / N. A. Ibrahim, A. Kudus, I. Daud, M. R. Abu Bakar // International Journal of Biological and Medical Sciences. 2008. Vol. 3, Iss. 1. Pp. 25–29.
10. Support Vector Machines for Survival Analysis / V. Van Belle, K. Pelckmans, J. A. K. Suykens, S. Van Huffel // Proceedings of the Third International Conference on Computational Intelligence in Medicine and Healthcare (CIMED2007), (Plymouth, United Kingdom, 25–27 July 2007). 8 p.
11. Shivaswamy P. K., Chu W., Jansche M. A Support Vector Approach to Censored Targets // Proceedings of the 7th IEEE International Conference on Data Mining (ICDM 2007) (Omaha, NE, USA, 28–31 October 2007). Institute of Electrical and Electronics Engineers, 2007. Pp. 655–660. DOI:https://doi.org/10.1109/ICDM.2007.93.
12. Integrating Bioinformatics and Machine Learning Methods to Analyze Diagnostic Biomarkers for HBV-induced Hepatocellular Carcinoma / A. Yang, J. Liu, M. Li [et al.] // Diagnostic Pathology. 2024. Vol. 19, Iss. 1. Art. No. 105. 10 p. DOI:https://doi.org/10.1186/s13000-024-01528-8.
13. Deep Learning for Survival Analysis: A Review / S. Wiegrebe, P. Kopper, R. Sonabend [et al.] // Artificial Intelligence Review. 2024. Vol. 57, Iss. 3. Art. No. 65. 34 p. DOI:https://doi.org/10.1007/s10462-023-10681-3.
14. Kovalev M. S., Utkin L. V. A Robust Algorithm for Explaining Unreliable Machine Learning Survival Models Using the Kolmogorov — Smirnov Bounds // Neural Networks. 2020. Vol. 132. Pp. 1–18. DOI:https://doi.org/10.1016/j.neunet.2020.08.007.
15. Archetti A., Ieva F., Matteucci M. Scaling Survival Analysis in Healthcare with Federated Survival Forests: A Comparative Study on Heart Failure and Breast Cancer Genomics // Future Generation Computer Systems. 2023. Vol. 149. Pp. 343–358. DOI:https://doi.org/10.1016/j.future.2023.07.036.
16. Powell J. L. Estimation of Semiparametric Models // Handbook of Econometrics. Volume IV / R. F. Engle, D. L. McFadden (eds.). Amsterdam: North-Holland Publishing, 1994. Pp. 2443–2521. DOI:https://doi.org/10.1016/S1573-4412(05)80010-8.
17. Assessing Performance and Clinical Usefulness in Prediction Models with Survival Outcomes: Practical Guidance for Cox Proportional Hazards Models / D. J. McLernon, D. Giardiello, B. Van Calster // Annals of Internal Medicine. 2023. Vol. 176, No. 1. Pp. 105–114. DOI:https://doi.org/10.7326/M22-0844.
18. Tao X., Wang M., Ji Y. The Application of Graph-Structured Cox Model in Financial Risk Early Warning of Companies // Sustainability. 2023. Vol. 15, Iss. 14. Art. No. 10802. 16 p. DOI:https://doi.org/10.3390/su151410802.
19. Gomez-Gonzalez J. E., Uribe J. M., Valencia O. M. Does Economic Complexity Reduce the Probability of a Fiscal Crisis? // World Development. 2023. Vol. 168. Art. No. 106250. 17 p. DOI:https://doi.org/10.1016/j.worlddev.2023.106250.
20. Viral Kinetics in Sylvatic Yellow Fever Cases / V. I. Avelino-Silva, M. V. Thomazella, M. P. Marmorato [et al.] // The Journal of Infectious Diseases. 2023. Vol. 227, Iss. 9. Pp. 1097–1103. DOI:https://doi.org/10.1093/infdis/jiac435.
21. Survival Analysis of Productive Life in Florida Dairy Goats Using a Cox Proportional Hazards Model / C. Ziadi, J. P. Sánchez, M. Sánchez [et al.] // Journal of Animal Breeding and Genetics. 2023. Vol. 140, Iss. 4. Pp. 431–439. DOI:https://doi.org/10.1111/jbg.12769.
22. High Social Risk and Mortality. A Prospective Study in Community-Dwelling Older Adults Living in a Rural Ecuadorian Village / O. H. Del Brutto, R. M. Mera, D. A. Rumbea [et al.] // Preventive Medicine Reports. 2023. Vol. 32. Art. No. 102146. 4 p. DOI:https://doi.org/10.1016/j.pmedr.2023.102146.
23. Papathanasiou D., Demertzis K., Tziritas N. Machine Failure Prediction Using Survival Analysis // Future Internet. 2023. Vol. 15, Iss. 5. Art. No. 153. 26 p. DOI:https://doi.org/10.3390/fi15050153.
24. Evaluating the Yield of Medical Tests / F. E. Harrell Jr., R. M. Califf, D. B. Pryor [et al.] // JAMA: The Journal of the American Medical Association. 1982. Vol. 247, No. 18. Pp. 2543–2546. DOI:https://doi.org/10.1001/jama.1982.03320430047030.
25. The Concordance Index Decomposition: A Measure for a Deeper Understanding of Survival Prediction Models / A. Alabdallah, M. Ohlsson, S. Pashami, T. Rögnvaldsson // Artificial Intelligence in Medicine. 2024. Vol. 148. Art. No. 102781. 10 p. DOI:https://doi.org/10.1016/j.artmed.2024.102781.
26. Pitfalls of the Concordance Index for Survival Outcomes / N. Hartman, S. Kim, K. He, J. D. Kalbfleisch // Statistics in Medicine. 2023. Vol. 42, Iss. 13. Pp. 2179–2190. DOI:https://doi.org/10.1002/sim.9717.
27. Rumyanceva E. V., Furmanov K. K. Ispol'zovanie vnevyborochnyh ostatkov Koksa — Snell pri prognozirovanii nastupleniya sobytiy // Biznes-informatika. 2021. T. 15, № 1. S. 7–18. DOI:https://doi.org/10.17323/2587-814X.2021.1.7.18.
28. Longato E., Vettoretti M., Di Camillo B. A Practical Perspective on the Concordance Index for the Evaluation and Selection of Prognostic Time-to-Event Models // Journal of Biomedical Informatics. 2020. Vol. 108. Art. No. 103496. 9 p. DOI:https://doi.org/10.1016/j.jbi.2020.103496.
29. Pencina M. J., D’Agostino R. B. Overall C as a Measure of Discrimination in Survival Analysis: Model Specific Population Value and Confidence Interval Estimation // Statistics in Medicine. 2004. Vol. 23, Iss. 13. Pp. 2109–2123. DOI:https://doi.org/10.1002/sim.1802.
30. A Convolutional Neural Network Model for Survival Prediction Based on Prognosis-Related Cascaded Wx Feature Selection / Q. Yin, W. Chen, C. Zhang, Z. Wei // Laboratory Investigation. 2022. Vol. 102, Iss. 10. Pp. 1064–1074. DOI:https://doi.org/10.1038/s41374-022-00801-y.
31. Svidetel'stvo o gosudarstvennoy registracii bazy dannyh № 2016620331 Rossiyskaya Federaciya. Baza dannyh bol'nyh rakom predstatel'noy zhelezy: opubl. 20.04.2016 / G. M. Zharinov.
32. Rossi P. H., Berk R. A., Lenihan K. J. Money, Work, and Crime: Experimental Evidence. New York: Academic Press, 1980. 260 p.
33. Teng J. SEER Breast Cancer Data // IEEE Dataport. Last update 18.01.2019. DOI:https://doi.org/10.21227/a9qy-ph35.
