An Explainable Multimodal Deep Learning Framework for Robust Cancer Survival Prediction
DOI:
https://doi.org/10.63949/Keywords:
- Multimodal Deep Learning,
- Explainable Artificial Intelligence (XAI),
- Cox Proportional Hazards Model,
- Multi-Omics Data Integration,
- Precision Oncology
Abstract
The persistence prediction of cancer is still a crucial issue of precision oncology, which is explained by heterogeneous and high-dimensional clinical data, genomic and imaging data. The current analysis presents a comprehensible multimodal deep-learning model that provides viable and broad generalizable cancer prognostication. This model is based on the concept of feature-level fusion by incorporating clinical variables by using an attention-based deep-learning structure in addition to gene-expression profiles and medical-imaging features. To estimate the risk score and probability of survival a Cox proportional-hazards survival layer is added. The architecture also incorporates Explainable Artificial Intelligence (XAI) for the use of interpretability and clinical trust. The experimental assessment through cross-validation reveals that the mentioned multimodal model significantly performs better as compared to conventional machine- and unimodal deep-learning models. The superior predictive capability is experienced through greater ROC-AUC and Concordance Index (C-Index) thus validating better discriminatory ability in addition to survival stratification. Statistical evaluation is used to confirm that the performance improvement is significant (p < 0.05). Stage of the tumor, prominent genomic markers, and textual features of imaging detected by the feature-attribution analysis as significant contributors to prognosis, which is in accordance with existing clinical data. The findings suggest that multimodal data fusion improves predictive strength and generalization and maintains the interpretability. As such, the presented framework can provide a scalable, clinically interpretable and high-performing AI-based cancer prognosis and precision-oncology systems.
Downloads
References
[1]. Hu, Y., Li, X., Yi, Y., Huang, Y., Wang, G., Wang, D., et al. (2025). Deep learning-driven survival prediction in pan-cancer studies by integrating multimodal histology-genomic data. Briefings in Bioinformatics, 26(2), bbaf121. https://doi.org/10.1093/bib/bbaf121
[2]. Iqbal, M. J., Javed, Z., Sadia, H., Qureshi, I. A., Irshad, A., Ahmed, R., et al. (2021). Clinical applications of artificial intelligence and machine learning in cancer diagnosis: Looking into the future. Cancer Cell International, 21, 270. https://doi.org/10.1186/s12935-021-01981-1
[3]. Jahnavi, Y., Anusha, P., Mathur, M., & Tiwari, V. (2023a). Computer vision in deep learning for the detection of cancer and its treatment. International Journal of Advanced Networking and Applications, 15(03), 5983–5988.
[4]. Jahnavi, Y., Kumar, P. N., Anusha, P., & Prasad, M. S. (2023b). Prediction and evaluation of cancer using machine learning techniques. In M. Pandit, M. K. Gaur, & S. Kumar (Eds.), Artificial Intelligence and Sustainable Computing (Algorithms for Intelligent Systems). Springer. https://doi.org/10.1007/978-981-99-1431-9_31
[5]. Kumar, Y., Gupta, S., Singla, R., & Hu, Y. C. (2022). A systematic review of artificial intelligence techniques in cancer prediction and diagnosis. Archives of Computational Methods in Engineering, 29, 2043–2070. https://doi.org/10.1007/s11831-021-09648-w
[6]. Lobato-Delgado, B., Priego-Torres, B., & Sanchez-Morillo, D. (2022). Combining molecular, imaging, and clinical data analysis for predicting cancer prognosis. Cancers, 14(13), 3215. https://doi.org/10.3390/cancers14133215
[7]. Mahmoud, A., Alhussein, M., Aurangzeb, K., & Takaoka, E. (2024). Breast cancer survival prediction modeling based on genomic data: An improved prognosis-driven deep learning approach. IEEE Access, 12, 119502–119519. https://doi.org/10.1109/ACCESS.2024.3449814
[8]. Mihaylov, I., Kańduła, M., Krachunov, M., et al. (2019). A novel framework for horizontal and vertical data integration in cancer studies with application to survival time prediction models. Biology Direct, 14, 22. https://doi.org/10.1186/s13062-019-0249-6
[9]. Nikolaou, N., Salazar, D., RaviPrakash, H., et al. (2025). A machine learning approach for multimodal data fusion for survival prediction in cancer patients. npj Precision Oncology, 9, 128. https://doi.org/10.1038/s41698-025-00917-6
[10]. Sharma, D., Deepali, Garg, V. K., et al. (2022). A deep learning-based integrative model for survival time prediction of head and neck squamous cell carcinoma patients. Neural Computing and Applications, 34, 21353–21365. https://doi.org/10.1007/s00521-022-07615-5
[11]. Singh, A., Kumar, T. C. A., Mithun, T., Majji, S., Rajesh, M., &Anusha, P. (2021). Image processing approaches for oral cancer detection in color images. In 2021 5th International Conference on Electronics, Communication and Aerospace Technology (ICECA) (pp. 817–821). IEEE. https://doi.org/10.1109/ICECA52323.2021.9675897
[12]. Srivastav, A. K., Singh, A., Singh, S., Rivers, B., Lillard, J. W., Jr., & Singh, R. (2025). Revolutionizing oncology through AI: Addressing cancer disparities by improving screening, treatment, and survival outcomes via integration of social determinants of health. Cancers, 17(17), 2866. https://doi.org/10.3390/cancers17172866
[13]. Tiwari, A., Mishra, S., &Kuo, T. R. (2025). Current AI technologies in cancer diagnostics and treatment. Molecular Cancer, 24, 159. https://doi.org/10.1186/s12943-025-02369-9
[14]. Tran, K. A., Kondrashova, O., Bradley, A., et al. (2021). Deep learning in cancer diagnosis, prognosis and treatment selection. Genome Medicine, 13, 152. https://doi.org/10.1186/s13073-021-00968-x
[15]. Vargas-Santiago, M., León-Velasco, D. A., Maldonado-Sifuentes, C. E., &Chanona-Hernandez, L. (2025). A state-of-the-art review of artificial intelligence (AI) applications in healthcare: Advances in diabetes, cancer, epidemiology, and mortality prediction. Computers, 14(4), 143. https://doi.org/10.3390/computers14040143
[16]. Wang, Z., Lin, R., Li, Y., Zeng, J., Chen, Y., Ouyang, W., et al. (2024). Deep learning-based multi-modal data integration enhancing breast cancer disease-free survival prediction. Precision Clinical Medicine, 7(2), pbae012. https://doi.org/10.1093/pcmedi/pbae012
[17]. Wekesa, J. S., &Kimwele, M. (2023). A review of multi-omics data integration through deep learning approaches for disease diagnosis, prognosis, and treatment. Frontiers in Genetics, 14, 1199087. https://doi.org/10.3389/fgene.2023.1199087
[18]. H. Shrestha, C. Dhasarathan, M. Kumar, R. Nidhya, A. Shankar, and M. Kumar, “A Deep Learning Based Convolution Neural Network (DCNN) Approach to Detect Brain Tumor,” Proceedings of Academia-Industry Consortium for Data Science (AICDS 2020), 2022.
[19]. D. Pavithra, R. Nidhya, C. Vinothini, and M. Murugaiyan, “A Lightweight Attention Based MobileNetV2 Model for Brain Tumor Segmentation and Severity of Tumor Classification Using Support Vector Machine,” 2023.
