Artificial Intelligence-Based Multimodal Prediction of Postoperative Adjuvant Immunotherapy Benefit in Urothelial Carcinoma: Results From the Phase III, Multicenter, Randomized, IMvigor010 Trial

Abstract

While circulating tumor DNA (ctDNA) testing has demonstrated utility in identifying muscle-invasive urothelial carcinoma (MIUC) patients likely to benefit from adjuvant immunotherapy, the prognostic value of transcriptome data from surgical specimens remains underexplored. Using transcriptomic and ctDNA data from the IMvigor010 trial, we developed an artificial intelligence (AI)-driven biomarker to predict immunotherapy response in urothelial carcinoma, termed UAIscore. Patients with high UAIscore had significantly better outcomes in the atezolizumab arm versus the observation arm. Notably, the predictive performance of the UAIscore consistently outperformed that of ctDNA, tTMB, and PD-L1, highlighting its value as an independent biomarker. Moreover, combining ctDNA, tTMB, and PD-L1 with the UAIscore further improved predictive accuracy, underscoring the importance of integrating multi-modality biomarkers. Further analysis of molecular subtypes revealed that the luminal subtype tends to be sensitive to adjuvant immunotherapy, as it may exhibit the highest level of immune infiltration and the lowest degree of hypoxia. Remarkably, we elucidated the role of the NF-κB and TNF-α pathways in mediating immunotherapy resistance within the immune-enriched tumor microenvironment. These findings stratify patients likely to respond to adjuvant immunotherapy, concurrently providing a mechanistic rationale for combination therapies to augment immunotherapy efficacy in urothelial carcinoma.

Keywords

adjuvant immunotherapy / biomarker / decision tree model / predictive score / urothelial carcinoma

References

[1] J. A. Witjes, H. M. Bruins, R. Cathomas, et al., “European Association of Urology Guidelines on Muscle-Invasive and Metastatic Bladder Cancer: Summary of the 2020 Guidelines,” European Urology 79, no. 1 (2021): 82-104.

[2] M. Rouprêt, T. Seisen, A. J. Birtle, et al., “European Association of Urology Guidelines on Upper Urinary Tract Urothelial Carcinoma: 2023 Update,” European Urology 84, no. 1 (2023): 49-64.

[3] D. F. Bajorin, J. A. Witjes, J. E. Gschwend, et al., “Adjuvant Nivolumab Versus Placebo in Muscle-Invasive Urothelial Carcinoma,” New England Journal of Medicine 384, no. 22 (2021): 2102-2114.

[4] T. Powles, S. H. Park, E. Voog, et al., “Avelumab Maintenance Therapy for Advanced or Metastatic Urothelial Carcinoma,” New England Journal of Medicine 383, no. 13 (2020): 1218-1230.

[5] A. V. Balar, D. Castellano, and P. H. O'Donnell, “First-Line Pembrolizumab in Cisplatin-Ineligible Patients With Locally Advanced and Unresectable or Metastatic Urothelial Cancer (KEYNOTE-052): A Multicentre, Single-Arm, Phase 2 Study,” Lancet Oncology 18, no. 11 (2017): 1483-1492.

[6] J. Bellmunt, M. Hussain, J. E. Gschwend, et al., “Adjuvant Atezolizumab Versus Observation in Muscle-Invasive Urothelial Carcinoma (IMvigor010): A Multicentre, Open-Label, Randomised, Phase 3 Trial,” Lancet Oncology 22, no. 4 (2021): 525-537.

[7] T. Powles, Z. J. Assaf, N. Davarpanah, et al., “ctDNA Guiding Adjuvant Immunotherapy in Urothelial Carcinoma,” Nature 595, no. 7867 (2021): 432-437.

[8] D. B. Doroshow, S. Bhalla, M. B. Beasley, et al., “PD-L1 as a Biomarker of Response to Immune-Checkpoint Inhibitors,” Nature Reviews Clinical Oncology 18, no. 6 (2021): 345-362.

[9] B. Halbert, and D. J. Einstein, “Hot or Not: Tumor Mutational Burden (TMB) as a Biomarker of Immunotherapy Response in Genitourinary Cancers,” Urology 147 (2021): 119-126.

[10] P. Zhao, L. Li, X. Jiang, and Q. Li, “Mismatch Repair Deficiency/Microsatellite Instability-High as a Predictor for Anti-PD-1/PD-L1 Immunotherapy Efficacy,” Journal of Hematology & Oncology 12, no. 1 (2019): 54.

[11] K. Swanson, E. Wu, A. Zhang, A. A. Alizadeh, and J. Zou, “From Patterns to Patients: Advances in Clinical Machine Learning for Cancer Diagnosis, Prognosis, and Treatment,” Cell 186, no. 8 (2023): 1772-1791.

[12] Y. Yang, Y. Zhao, X. Liu, and J. Huang, “Artificial Intelligence for Prediction of Response to Cancer Immunotherapy,” Seminars in Cancer Biology 87 (2022): 137-147.

[13] D. Q. Wang, L. Y. Feng, J. G. Ye, J. G. Zou, and Y. F. Zheng, “Accelerating the Integration of ChatGPT and Other Large-Scale AI Models Into Biomedical Research and Healthcare,” MedComm - Future Medicine 2, no. 2 (2023): e43.

[14] G. Sjödahl, J. Abrahamsson, K. Holmsten, et al., “Different Responses to Neoadjuvant Chemotherapy in Urothelial Carcinoma Molecular Subtypes,” European Urology 81, no. 5 (2022): 523-532.

[15] J. Kim, D. Kwiatkowski, D. J. McConkey, et al., “The Cancer Genome Atlas Expression Subtypes Stratify Response to Checkpoint Inhibition in Advanced Urothelial Cancer and Identify a Subset of Patients With High Survival Probability,” European Urology 75, no. 6 (2019): 961-964.

[16] F. Erlmeier, N. Klümper, L. Landgraf, et al., “Spatial Immunephenotypes of Distant Metastases but Not Matched Primary Urothelial Carcinomas Predict Response to Immune Checkpoint Inhibition,” European Urology 83, no. 2 (2023): 133-142.

[17] R. C. Deo, “Machine Learning in Medicine,” Circulation 132, no. 20 (2015): 1920-1930.

[18] C. Chen, C. Liao, and Y.-Y. Liu, “Teasing Out Missing Reactions in Genome-Scale Metabolic Networks Through Hypergraph Learning,” Nature Communications 14, no. 1 (2023): 2375.

[19] S. Steyaert, M. Pizurica, D. Nagaraj, et al., “Multimodal Data Fusion for Cancer Biomarker Discovery With Deep Learning,” Nature Machine Intelligence 5, no. 4 (2023): 351-362.

[20] M. Sorin, M. Rezanejad, E. Karimi, et al., “Single-Cell Spatial Landscapes of the Lung Tumour Immune Microenvironment,” Nature 614, no. 7948 (2023): 548-554.

[21] B. Wang, Q. Zhao, Y. Zhang, et al., “Targeting Hypoxia in the Tumor Microenvironment: A Potential Strategy to Improve Cancer Immunotherapy,” Journal of Experimental & Clinical Cancer Research 40, no. 1 (2021): 24.

[22] R. S. Apte, D. S. Chen, and N. Ferrara, “VEGF in Signaling and Disease: Beyond Discovery and Development,” Cell 176, no. 6 (2019): 1248-1264.

[23] Y. Zhang, C. Gao, F. Cao, et al., “Pan-Cancer Analysis of IGF-1 and IGF-1R as Potential Prognostic Biomarkers and Immunotherapy Targets,” Frontiers in Oncology 11 (2021): 755341.

[24] N. Turner, and R. Grose, “Fibroblast Growth Factor Signalling: From Development to Cancer,” Nature Reviews Cancer 10, no. 2 (2010): 116-129.

[25] Q. Guo, Y. Jin, X. Chen, et al., “NF-κB in Biology and Targeted Therapy: New Insights and Translational Implications,” Signal Transduction and Targeted Therapy 9, no. 1 (2024): 53.

[26] B. Bonavida, and H. Garban, “Nitric Oxide-Mediated Sensitization of Resistant Tumor Cells to Apoptosis by Chemo-Immunotherapeutics,” Redox Biology 6 (2015): 486-494.

[27] J. Jassem, F. de Marinis, G. Giaccone, et al., “Updated Overall Survival Analysis From IMpower110: Atezolizumab Versus Platinum-Based Chemotherapy in Treatment-Naive Programmed Death-Ligand 1-Selected NSCLC,” Journal of Thoracic Oncology 16, no. 11 (2021): 1872-1882.

[28] Y. Li, L. Liang, W. Dai, et al., “Prognostic Impact of Programed Cell Death-1 (PD-1) and PD-Ligand 1 (PD-L1) Expression in Cancer Cells and Tumor Infiltrating Lymphocytes in Colorectal Cancer,” Molecular Cancer 15, no. 1 (2016): 55.

[29] T. Powles, I. Durán, M. S. van der Heijden, et al., “Atezolizumab Versus Chemotherapy in Patients With Platinum-Treated Locally Advanced or Metastatic Urothelial Carcinoma (IMvigor211): A Multicentre, Open-Label, Phase 3 Randomised Controlled Trial,” Lancet (London, England) 391, no. 10122 (2018): 748-757.

[30] G. Fontanini, S. Vignati, F. Basolo, et al., “Angiogenesis as a Prognostic Indicator of Survival in Non-Small-Cell Lung Carcinoma: A Prospective Study,” JNCI: Journal of the National Cancer Institute 89, no. 12 (1997): 881-886.

[31] A. G. Robertson, J. Kim, H. Al-Ahmadie, et al., “Comprehensive Molecular Characterization of Muscle-Invasive Bladder Cancer,” Cell 171, no. 3 (2017): 540-556. e525.

[32] K. A. Khan, and R. S. Kerbel, “Improving Immunotherapy Outcomes With Anti-Angiogenic Treatments and Vice Versa,” Nature Reviews Clinical Oncology 15, no. 5 (2018): 310-324.

[33] Q. Wu, A.-L. Tian, B. Li, et al., “IGF1 Receptor Inhibition Amplifies the Effects of Cancer Drugs by Autophagy and Immune-Dependent Mechanisms,” Journal for ImmunoTherapy of Cancer 9, no. 6 (2021): e002722.

[34] R. Ruan, L. Li, X. Li, et al., “Unleashing the Potential of Combining FGFR Inhibitor and Immune Checkpoint Blockade for FGF/FGFR Signaling in Tumor Microenvironment,” Molecular Cancer 22, no. 1 (2023): 60.

[35] C. Sautès-Fridman, F. Petitprez, J. Calderaro, and W. H. Fridman, “Tertiary Lymphoid Structures in the Era of Cancer Immunotherapy,” Nature Reviews Cancer 19, no. 6 (2019): 307-325.

[36] T. N. Schumacher, and D. S. Thommen, “Tertiary Lymphoid Structures in Cancer,” Science 375, no. 6576 (2022): eabf9419.

[37] K. H. Gouin, N. Ing, J. T. Plummer, et al., “An N-Cadherin 2 Expressing Epithelial Cell Subpopulation Predicts Response to Surgery, Chemotherapy and Immunotherapy in Bladder Cancer,” Nature Communications 12, no. 1 (2021): 4906.

[38] H. Su, and M. Karin, “Collagen Architecture and Signaling Orchestrate Cancer Development,” Trends in Cancer 9, no. 9 (2023): 764-773.

[39] T. K. Kim, E. N. Vandsemb, R. S. Herbst, and L. Chen, “Adaptive Immune Resistance at the Tumour Site: Mechanisms and Therapeutic Opportunities,” Nature Reviews Drug Discovery 21, no. 7 (2022): 529-540.

[40] B. B. Aggarwal, S. C. Gupta, and J. H. Kim, “Historical Perspectives on Tumor Necrosis Factor and Its Superfamily: 25 Years Later, a Golden Journey,” Blood 119, no. 3 (2012): 651-665.

[41] L. Wu, Y. Jin, X. Zhao, et al., “Tumor Aerobic Glycolysis Confers Immune Evasion Through Modulating Sensitivity to T Cell-Mediated Bystander Killing via TNF-α,” Cell Metabolism 35, no. 9 (2023): 1580-1596. e1589.

[42] Y. Jing, K. Sun, W. Liu, et al., “Tumor Necrosis Factor-α Promotes Hepatocellular Carcinogenesis Through the Activation of Hepatic Progenitor Cells,” Cancer Letters 434 (2018): 22-32.

[43] W. Tan, X. Luo, W. Li, et al., “TNF-α Is a Potential Therapeutic Target to Overcome Sorafenib Resistance in Hepatocellular Carcinoma,” EBioMedicine 40 (2019): 446-456.

[44] A. Shinde, N. Chandak, J. Singh, et al., “TNF-α Induced NF-κB Mediated LYRM7 Expression Modulates the Tumor Growth and Metastatic Ability in Breast Cancer,” Free Radical Biology and Medicine 211 (2024): 158-170.

[45] W. Liu, X. Lu, P. Shi, et al., “TNF-α Increases Breast Cancer Stem-Like Cells Through Up-Regulating TAZ Expression via the Non-Canonical NF-κB Pathway,” Scientific Reports 10, no. 1 (2020): 1804.

[46] A. Shinde, X. Tang, R. Singh, and D. N. Brindley, “Infliximab, a Monoclonal Antibody Against TNF-α, Inhibits NF-κB Activation, Autotaxin Expression and Breast Cancer Metastasis to Lungs,” Cancers 16, no. 1 (2023): 52.

[47] B.-X. Liu, Y. Xie, J. Zhang, et al., “SERPINB5 Promotes Colorectal Cancer Invasion and Migration by Promoting EMT and Angiogenesis via the TNF-α/NF-κB Pathway,” International Immunopharmacology 131 (2024): 111759.

[48] Y. Liang, Y. Tan, B. Guan, et al., “Single-Cell Atlases Link Macrophages and CD8+ T-Cell Subpopulations to Disease Progression and Immunotherapy Response in Urothelial Carcinoma,” Theranostics 12, no. 18 (2022): 7745-7759.

[49] J. C. Marini, A. Forlino, H. P. Bächinger, et al., “Osteogenesis Imperfecta,” Nature Reviews Disease Primers 3, no. 1 (2017): 17052.

[50] D. Dangaj, M. Bruand, A. J. Grimm, et al., “Cooperation Between Constitutive and Inducible Chemokines Enables T Cell Engraftment and Immune Attack in Solid Tumors,” Cancer Cell 35, no. 6 (2019): 885-900. e810.

[51] H. Dong, S. E. Strome, D. R. Salomao, et al., “Tumor-Associated B7-H1 Promotes T-Cell Apoptosis: A Potential Mechanism of Immune Evasion,” Nature Medicine 8, no. 8 (2002): 793-800.

[52] L. Chen, “Co-inhibitory Molecules of the B7-CD28 Family in the Control of T-Cell Immunity,” Nature Reviews Immunology 4, no. 5 (2004): 336-347.

[53] W. Zou, and L. Chen, “Inhibitory B7-Family Molecules in the Tumour Microenvironment,” Nature Reviews Immunology 8, no. 6 (2008): 467-477.

[54] B. I. Rini, E. R. Plimack, V. Stus, et al., “Pembrolizumab Plus Axitinib Versus Sunitinib for Advanced Renal-Cell Carcinoma,” New England Journal of Medicine 380, no. 12 (2019): 1116-1127.

[55] Y. Liang, H. Tang, J. Guo, et al., “Targeting IFNα to Tumor by Anti-PD-L1 Creates Feedforward Antitumor Responses to Overcome Checkpoint Blockade Resistance,” Nature Communications 9, no. 1 (2018): 4586.

[56] C. R. Ager, M. J. Reilley, C. Nicholas, T. Bartkowiak, A. R. Jaiswal, and M. A. Curran, “Intratumoral STING Activation With T-Cell Checkpoint Modulation Generates Systemic Antitumor Immunity,” Cancer Immunology Research 5, no. 8 (2017): 676-684.

[57] B. M. Allen, K. J. Hiam, C. E. Burnett, et al., “Systemic Dysfunction and Plasticity of the Immune Macroenvironment in Cancer Models,” Nature Medicine 26, no. 7 (2020): 1125-1134.

[58] L. C. Dieterich, and A. Bikfalvi, “The Tumor Organismal Environment: Role in Tumor Development and Cancer Immunotherapy,” Seminars in Cancer Biology 65 (2020): 197-206.

[59] G. D. Sepich-Poore, L. Zitvogel, R. Straussman, J. Hasty, J. A. Wargo, and R. Knight, “The Microbiome and human Cancer,” Science 371, no. 6536 (2021): eabc4552.

[60] M. Y. Lu, T. Y. Chen, D. F. K. Williamson, et al., “AI-Based Pathology Predicts Origins for Cancers of Unknown Primary,” Nature 594, no. 7861 (2021): 106-110.

[61] X. Zhang, J. Wang, J. Lu, et al., “Robust Prognostic Subtyping of Muscle-Invasive Bladder Cancer Revealed by Deep Learning-Based Multi-Omics Data Integration,” Frontiers in Oncology 11 (2021): 689626.

[62] Q. Ou, Z. Lu, G. Cai, et al., “Unraveling the Influence of Metabolic Signatures on Immune Dynamics for Predicting Immunotherapy Response and Survival in Cancer,” MedComm - Future Medicine 3, no. 2 (2024): 89.

[63] J. Lipkova, R. J. Chen, B. Chen, et al., “Artificial Intelligence for Multimodal Data Integration in Oncology,” Cancer Cell 40, no. 10 (2022): 1095-1110.

[64] A. Prelaj, V. Miskovic, M. Zanitti, et al., “Artificial Intelligence for Predictive Biomarker Discovery in Immuno-Oncology: A Systematic Review,” Annals of Oncology 35, no. 1 (2024): 29-65.

[65] J. Liu, T. Lichtenberg, K. A. Hoadley, et al., “An Integrated TCGA Pan-Cancer Clinical Data Resource to Drive High-Quality Survival Outcome Analytics,” Cell 173, no. 2 (2018): 400-416. e411.

[66] D. Zeng, Y. Fang, P. Luo, et al., “IOBR2: Multidimensional Decoding Tumor Microenvironment for Immuno-Oncology Research,” BioRxiv (2024). https://doi.org/10.1101/2024.01.13.575484.

RIGHTS & PERMISSIONS

2025 The Author(s). MedComm published by Sichuan International Medical Exchange & Promotion Association (SCIMEA) and John Wiley & Sons Australia, Ltd.