Benchmarking Hybrid Learning Models for Personalized Risk Classification and Prediction in Oncology
Article Sidebar
Main Article Content
Abstract
In the field of oncology, and specifically regarding prostate cancer, recent breakthroughs in Artificial Intelligence (AI) have opened fascinating possibilities for risk classification and prediction. However, moving from theoretical success to actual clinical practice remains a significant challenge. In this study, we chose to evaluate several architectures (generative, discriminant, and hybrid models) to test their real-world relevance when faced with longitudinal medical data, which is often noisy or incomplete. Our analysis does not merely measure raw performance; it seeks to understand the critical balance between statistical precision and the interpretability that clinicians require for daily decision-making. By examining the inherent strengths and limitations of each method, we developed an advanced hybrid approach designed as a genuine support tool for the patient care pathway. Our findings are particularly encouraging: these deep hybrid models significantly outperform traditional methods, showing a notable improvement of 6% to 9% in both AUC-ROC and C-index scores. Beyond these metrics, we observed a superior ability in the model to adapt to the temporal variations of patient data over time. Ultimately, our goal is to demonstrate that more refined predictions, when properly integrated into the clinical context, can simplify the decision-making process. By making these models more transparent and robust, we hope to facilitate their adoption by the medical community, leading to more personalized and effective management for patients battling prostate cancer.
Article Details
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
All articles published in JIWE are licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International (CC BY-NC-ND 4.0) License. Readers are allowed to
- Share — copy and redistribute the material in any medium or format under the following conditions:
- Attribution — You must give appropriate credit, provide a link to the license, and indicate if changes were made. You may do so in any reasonable manner, but not in any way that suggests the licensor endorses you or your use;
- NonCommercial — You may not use the material for commercial purposes;
- NoDerivatives — If you remix, transform, or build upon the material, you may not distribute the modified material.
References
[1] A. Esteva et al., "A guide to deep learning in healthcare," Nature Medicine, vol. 25, no. 1, pp. 24-29, Jan. 2019, doi: 10.1038/s41591-018-0316-z.
[2] C.-Y. Hsu et al., "AI-driven multi-omics integration in precision oncology: Bridging the data deluge to clinical decisions," Clinical and Experimental Medicine, vol. 26, no. 1, p. 29, Nov. 2025, doi: 10.1007/s10238-025-01965-9.
[3] S. Kourou et al., "Machine learning applications in cancer prognosis and prediction," Computational and Structural Biotechnology Journal, vol. 13, pp. 8-17, Nov. 2014, doi: 10.1016/j.csbj.2014.11.005.
[4] T. Tu et al., "Towards a generalist biomedical AI," NEJM AI, vol. 1, no. 3, pp. 120-135, Feb. 2024, doi: 10.1056/AIoa2300138.
[5] E. Topol, Deep Medicine: How Artificial Intelligence Can Make Healthcare Human Again. New York, NY, USA: Basic Books, 2019.
[6] R. Miotto, F. Wang, S. Wang, X. Jiang, and J. Dudley, "Deep learning for healthcare: Review, opportunities and challenges," Briefings in Bioinformatics, vol. 19, no. 6, pp. 1236-1246, Nov. 2018, doi: 10.1093/bib/bbx044.
[7] Y. Bengio, A. Courville, and P. Vincent, "Representation learning: A review and new perspectives," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 35, no. 8, pp. 1798-1828, Aug. 2013, doi: 10.1109/TPAMI.2013.50.
[8] D. Rizopoulos, Joint Models for Longitudinal and Time-to-Event Data: With Applications in R. Boca Raton, FL, USA: CRC Press, 2012, eISBN: 9780429063381, doi: 10.1201/b12208.
[9] B. C. Agema, B. C. P. Koch, R. H. J. Mathijssen, and S. L. W. Koolen, "From prospective evaluation to practice: Model-informed dose optimization in oncology," Drugs, vol. 85, no. 4, pp. 487-503, Feb. 2025, doi: 10.1007/s40265-025-02152-6.
[10] C. S. Santos and M. Amorim-Lopes, "Externally validated and clinically useful machine learning algorithms to support patient-related decision-making in oncology: A scoping review," BMC Medical Research Methodology, vol. 25, no. 1, p. 45, Feb. 2025, doi: 10.1186/s12874-025-02463-y.
[11] L. Breiman, "Statistical modeling: The two cultures," Statistical Science, vol. 16, no. 3, pp. 199-231, Aug. 2001, doi: 10.1214/ss/1009213726.
[12] T. Hastie, R. Tibshirani, and J. Friedman, The Elements of Statistical Learning: Data Mining, Inference, and Prediction, 2nd ed. New York, NY, USA: Springer, 2009, eISBN: 978-0-387-84858-7, doi: 10.1007/978-0-387-84858-7.
[13] J. Friedman, "Greedy function approximation: A gradient boosting machine," Annals of Statistics, vol. 29, no. 5, pp. 1189-1232, Oct. 2001, doi: 10.1214/aos/1013203451.
[14] W. L. Bi et al., "Artificial intelligence in cancer imaging: Clinical challenges and applications," CA: A Cancer Journal for Clinicians, vol. 69, no. 2, pp. 127-157, Mar. 2019, doi: 10.3322/caac.21552.
[15] Z. Wang et al., "Bayesian logistic shape model inference: Application to cochlear image segmentation," Medical Image Analysis, vol. 75, p. 102268, Jan. 2022, doi: 10.1016/j.media.2021.102268.
[16] A. J. London, "Artificial intelligence and black-box medical decisions: Accuracy versus explainability," The Hastings Center Report, vol. 49, no. 1, pp. 15-21, Jan./Feb. 2019, doi: 10.1002/hast.973.
[17] F. E. Harrell, Regression Modeling Strategies: With Applications to Linear Models, Logistic and Ordinal Regression, and Survival Analysis, 2nd ed. New York, NY, USA: Springer, 2015, doi: 10.1007/978-3-319-19425-7.
[18] W. Wang et al., "Joint modeling of longitudinal and survival data in public health and biomedical research: A systematic review," International Journal of Environmental Research and Public Health, vol. 23, no. 4, p. 492, Apr. 2026, doi: 10.3390/ijerph23040492.
[19] T. Kour et al., "Transformative impact of deep learning and machine learning in oncology: A comprehensive review of AI-based approaches for early detection, diagnosis and therapeutics across different cancer types," Archives of Computational Methods in Engineering, vol. 33, no. 3, pp. 3449-3474, Sep. 2025, doi: 10.1007/s11831-025-10401-w.
[20] A. Tsiatis, Dynamic Treatment Regimes: Statistical Methods for Precision Medicine. Boca Raton, FL, USA: CRC Press, 2019, eISBN: 9780429192692, doi: 10.1201/9780429192692.
[21] J. Fan et al., Statistical Foundations of Data Science. Boca Raton, FL, USA: Chapman and Hall/CRC, 2020, eISBN: 9780429096280, doi: 10.1201/9780429096280.
[22] R. C. Deo, "Machine learning in medicine," Circulation, vol. 132, no. 20, pp. 1920-1930, Nov. 2015, doi: 10.1161/CIRCULATIONAHA.115.001593.
[23] H. Putter, M. Fiocco, and R. B. Geskus, "Tutorial in biostatistics: Competing risks and multi-state models," Statistics in Medicine, vol. 26, no. 11, pp. 2389-2430, Oct. 2006, doi: 10.1002/sim.2712.
[24] Z. Che et al., "Recurrent neural networks for multivariate time series with missing values," Scientific Reports, vol. 8, p. 6085, Apr. 2018, doi: 10.1038/s41598-018-24271-9.
[25] A. Kendall and Y. Gal, "What uncertainties do we need in deep learning for computer vision?," in Advances in Neural Information Processing Systems (NeurIPS), 2017, pp. 5574-5584, doi: 10.48550/arXiv.1703.04977.
[26] L. T. Penberthy, D. R. Rivera, J. L. Lund, M. A. Bruno, and A. Meyer, "An overview of real-world data sources for oncology and considerations for research," CA: A Cancer Journal for Clinicians, vol. 72, no. 3, pp. 287-300, Dec. 2021, doi: 10.3322/caac.21714.
[27] C. Proust-Lima, V. Philipps, and B. Liquet, "Estimation of extended mixed models using latent classes and latent processes: The R package lcmm," Journal of Statistical Software, vol. 78, no. 2, pp. 1-33, Jun. 2017, doi: 10.18637/jss.v078.i02.
[28] C. Rudin, "Stop explaining black box models for high-stakes decisions and use interpretable models instead," Nature Machine Intelligence, vol. 1, no. 5, pp. 206-215, May 2019, doi: 10.1038/s42256-019-0048-x.
[29] G. Verbeke and G. Molenberghs, Linear Mixed Models for Longitudinal Data. New York, NY, USA: Springer, 2000, doi: 10.1007/978-1-4419-0300-6.
[30] G. S. Collins et al., "Clinical prediction models using machine learning in oncology: Challenges and recommendations," BMJ Oncology, vol. 4, no. 1, p. e000914, Oct. 2025, doi: 10.1136/bmjonc-2025-000914.
[31] M. E. Mukendi et al., "Machine learning based on probabilistic models applied to medical data: The case of prostate cancer," Journal of Innovation Information Technology and Application (JINITA), vol. 5, no. 2, pp. 105-113, 2023, doi: 10.35970/jinita.v5i2.1879.
[32] R. Mabela Matendo, Analyse des donnees multidimensionnelles: Theories et applications en recherche biomedicale. Kinshasa, DRC: Presses Universitaires de Kinshasa, 2019.
[33] The Cancer Genome Atlas Research Network, "The molecular taxonomy of primary prostate cancer," Cell, vol. 163, no. 4, pp. 1011-1025, Nov. 2015, doi: 10.1016/j.cell.2015.10.025.
[34] R. Mabela Matendo, Modelisation des processus stochastiques et trajectoires temporelles des systemes complexes. Kinshasa, DRC: Editions de la Faculte des Sciences, Universite de Kinshasa, 2021.
[35] D. Singh and B. Singh, "Investigating the impact of data normalization on classification performance," Applied Soft Computing, vol. 97, p. 105524, Dec. 2020, doi: 10.1016/j.asoc.2019.105524.
[36] S. Shickel, P. J. Tighe, A. Bihorac, and P. Rashidi, "Deep EHR: A survey of recent advances in deep learning techniques for electronic health record analysis," IEEE Journal of Biomedical and Health Informatics, vol. 22, no. 5, pp. 1589-1604, Sep. 2018, doi: 10.1109/JBHI.2017.2767063.
[37] M. Kaddes, Y. M. Ayid, A. M. Elshewey, and Y. Fouad, "Breast cancer classification based on hybrid CNN with LSTM model," Scientific Reports, vol. 15, no. 1, p. 4409, Feb. 2025, doi: 10.1038/s41598-025-88459-6.
[38] Z. C. Lipton, D. C. Kale, C. Elkan, and R. Wetzel, "Learning to diagnose with LSTM recurrent neural networks," in Proc. Int. Conf. Learn. Representations (ICLR), 2016.
[39] D. A. Reynolds, "Gaussian mixture models," in Encyclopedia of Biometrics, vol. 1, pp. 741-747, 2009, doi: 10.1007/978-0-387-73003-5_196.
[40] I. Rish, "An empirical study of the naive Bayes classifier," in IJCAI 2001 Workshop on Empirical Methods in Artificial Intelligence, vol. 3, no. 22, pp. 41-46, 2001.
[41] A. Rajkomar, J. Dean, and I. Kohane, "Machine learning in medicine," New England Journal of Medicine, vol. 380, no. 14, pp. 1347-1358, Apr. 2019, doi: 10.1056/NEJMra1814259.
[42] M. Verma, N. Chauhan, and A. K. Agrawal, "Artificial intelligence in neuro-oncology: Evaluation of MRI-based brain tumor segmentation and classification techniques," in Proc. 2025 Int. Conf. Emerging Technologies and Innovation for Sustainability (EmergIN), Greater Noida, India, 2025, pp. 243-249, doi: 10.1109/EmergIN67762.2025.11450733.
[43] C. Lee, J. Yoon, and M. van der Schaar, "Dynamic-DeepHit: A deep learning approach for dynamic survival analysis with competing risks based on longitudinal data," IEEE Transactions on Biomedical Engineering, vol. 67, no. 1, pp. 122-133, Jan. 2020, doi: 10.1109/TBME.2019.2909027.
[44] M. Moor et al., "Foundation models for generalist medical artificial intelligence," Nature, vol. 616, pp. 259-265, Apr. 2023, doi: 10.1038/s41586-023-05881-4.
[45] R. Salakapuri, K. K. Singamaneni, P. Vital Terlapu, B. Peesala, S. N. Raju B, and R. Reddy Kandadi, "Enhancing breast cancer prediction with Xplainable AI: Application of LIME and SHAP techniques," in Proc. 2025 Int. Conf. Artificial Intelligence and Machine Vision (AIMV), Gandhinagar, India, 2025, pp. 1-6, doi: 10.1109/AIMV66517.2025.11203435.
[46] I. Khan and S. Bhoite, "XAI integration into cancer care for effective decision making," in Proc. 2025 7th Int. Conf. Innovative Data Communication Technologies and Application (ICIDCA), Coimbatore, India, 2025, pp. 1067-1074, doi: 10.1109/ICIDCA66325.2025.11280442.