{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,3]],"date-time":"2026-11-03T00:12:38Z","timestamp":1793664758157,"version":"4.5.1"},"reference-count":45,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,6,22]],"date-time":"2026-06-22T00:00:00Z","timestamp":1782086400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,10,9]],"date-time":"2026-10-09T00:00:00Z","timestamp":1791504000000},"content-version":"vor","delay-in-days":109,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["npj Digit. Med."],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Accurate survival prediction in non-small cell lung cancer (NSCLC) requires integrating clinical, radiological, and histopathological data. Multimodal deep learning (MDL) can improve precision prognosis, but small cohorts and missing modalities limit its clinical applicability, as conventional approaches enforce complete-case filtering or imputation. We present a missing-aware multimodal survival framework that combines computed tomography (CT), whole-slide histopathology images (WSI), and structured clinical variables for overall survival modeling in unresectable stage II\u2013III NSCLC. The framework uses foundation models (FMs) for modality-specific feature extraction and a missing-aware encoding strategy that enables intermediate multimodal fusion under naturally incomplete modality profiles. By design, the architecture processes all available data without dropping patients during training or inference. Intermediate fusion outperforms unimodal baselines and both early and late fusion strategies, with the trimodal configuration reaching a C-index of 74.42. Modality-importance analyses show that the fusion model adapts its reliance on each data stream according to representation informativeness, shaped by the alignment between FM pretraining objectives and the survival task. The learned risk scores produce clinically meaningful stratification of disease progression and metastatic risk, with statistically significant log-rank tests across all modality combinations, supporting the translational relevance of the proposed framework.<\/jats:p>","DOI":"10.1038\/s41746-026-02783-3","type":"journal-article","created":{"date-parts":[[2026,6,22]],"date-time":"2026-06-22T20:14:39Z","timestamp":1782159279000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Handling missing modalities in multimodal survival prediction for non-small cell lung cancer"],"prefix":"10.1038","volume":"9","author":[{"given":"Filippo","family":"Ruffini","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Camillo Maria","family":"Caruso","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Claudia","family":"Tacconi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lorenzo","family":"Nibid","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Francesca","family":"Miccolis","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Marta","family":"Lovino","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Carlo","family":"Greco","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Edy","family":"Ippolito","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Michele","family":"Fiore","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alessio","family":"Cortellini","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bruno","family":"Beomonte Zobel","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Giuseppe","family":"Perrone","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bruno","family":"Vincenzi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Claudio","family":"Marrocco","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alessandro","family":"Bria","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Elisa","family":"Ficarra","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sara","family":"Ramella","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Valerio","family":"Guarrasi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Paolo","family":"Soda","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,6,22]]},"reference":[{"key":"2783_CR1","doi-asserted-by":"publisher","first-page":"186","DOI":"10.1038\/s41392-025-02243-6","volume":"10","author":"Q Huang","year":"2025","unstructured":"Huang, Q. et al. Advances in molecular pathology and therapy of non-small cell lung cancer. Signal Transduct. Target. Ther. 10, 186 (2025).","journal-title":"Signal Transduct. Target. Ther."},{"key":"2783_CR2","doi-asserted-by":"publisher","first-page":"152204","DOI":"10.1016\/j.bbrc.2025.152204","volume":"776","author":"T Vincent","year":"2025","unstructured":"Vincent, T. et al. Mechanistic insights into molecular targeted therapy and immunotherapy for lung cancer. Biochem. Biophys. Res. Commun. 776, 152204 (2025).","journal-title":"Biochem. Biophys. Res. Commun."},{"key":"2783_CR3","doi-asserted-by":"publisher","DOI":"10.1038\/s41698-025-01095-1","volume":"9","author":"X Yuan","year":"2025","unstructured":"Yuan, X. et al. Systematic review and meta-analysis of artificial intelligence for image-based lung cancer classification and prognostic evaluation. NPJ Precis. Oncol. 9, 300 (2025).","journal-title":"NPJ Precis. Oncol."},{"key":"2783_CR4","doi-asserted-by":"crossref","unstructured":"Guarrasi, V. et al. Beyond unimodal analysis: multimodal ensemble learning for enhanced assessment of atherosclerotic disease progression. Comput. Med. Imaging Graph. 124, 102617 (2025).","DOI":"10.1016\/j.compmedimag.2025.102617"},{"key":"2783_CR5","doi-asserted-by":"publisher","first-page":"110825","DOI":"10.1016\/j.patcog.2024.110825","volume":"156","author":"V Guarrasi","year":"2024","unstructured":"Guarrasi, V. et al. Multimodal explainability via latent shift applied to COVID-19 stratification. Pattern Recognit. 156, 110825 (2024).","journal-title":"Pattern Recognit."},{"key":"2783_CR6","doi-asserted-by":"crossref","unstructured":"Captier, N. et al. Integration of clinical, pathological, radiological, and transcriptomic data improves prediction for first-line immunotherapy outcome in metastatic non-small cell lung cancer. Nat. Commun. 16, 10 (2025)","DOI":"10.1038\/s41467-025-55847-5"},{"key":"2783_CR7","doi-asserted-by":"crossref","unstructured":"Guedes, J. et al. A perspective on integrating digital pathology, proteomics, clinical data and AI analytics in cancer research. J. Proteomics 320, 105493 (2025).","DOI":"10.1016\/j.jprot.2025.105493"},{"key":"2783_CR8","doi-asserted-by":"publisher","DOI":"10.1038\/s41698-024-00656-0","volume":"8","author":"H Paverd","year":"2024","unstructured":"Paverd, H., Zormpas-Petridis, K., Clayton, H., Burge, S. & Crispin-Ortuzar, M. Radiology and multi-scale data integration for precision oncology. NPJ Precis. Oncol. 8, 158 (2024).","journal-title":"NPJ Precis. Oncol."},{"key":"2783_CR9","doi-asserted-by":"publisher","first-page":"3215","DOI":"10.3390\/cancers14133215","volume":"14","author":"B Lobato-Delgado","year":"2022","unstructured":"Lobato-Delgado, B., Priego-Torres, B. & Sanchez-Morillo, D. Combining molecular, imaging, and clinical data analysis for predicting cancer prognosis. Cancers 14, 3215 (2022).","journal-title":"Cancers"},{"key":"2783_CR10","doi-asserted-by":"crossref","unstructured":"Peng, J., Pond, G. R., Donovan, E. K., Ellis, P. M. & Swaminath, A. A comparison of radiation techniques in patients treated with concurrent chemoradiation for stage III non-small cell lung cancer. Int. J. Radiat. Oncol. Biol. Phys. 106, 985\u2013992 (2020)","DOI":"10.1016\/j.ijrobp.2019.12.027"},{"key":"2783_CR11","doi-asserted-by":"publisher","first-page":"30","DOI":"10.1038\/s44172-026-00602-x","volume":"5","author":"LMT Doan","year":"2026","unstructured":"Doan, L. M. T. et al. Bridging modalities with AI: a review of ai advances in multimodal biomedical imaging. Commun. Eng. 5, 30 (2026).","journal-title":"Commun. Eng."},{"key":"2783_CR12","doi-asserted-by":"crossref","unstructured":"Niu, Y. et al. Multimodal deep learning integrating tumor radiomics and mediastinal adiposity improves survival prediction in non-small cell lung cancer: A prognostic modeling study. Cancer Med. 14, e70125 (2025).","DOI":"10.1002\/cam4.71077"},{"key":"2783_CR13","doi-asserted-by":"crossref","unstructured":"Machin, D., Cheung, Y. B. & Parmar, M. Survival Analysis: A Practical Approach 2nd edn (Wiley, 2006).","DOI":"10.1002\/0470034572"},{"key":"2783_CR14","doi-asserted-by":"crossref","unstructured":"Soenksen, L. et al. Integrated multimodal artificial intelligence framework for healthcare applications. Nat. Comput. Sci. 5, 149 (2022)","DOI":"10.1038\/s41746-022-00689-4"},{"key":"2783_CR15","doi-asserted-by":"publisher","first-page":"108308","DOI":"10.1016\/j.cmpb.2024.108308","volume":"254","author":"CM Caruso","year":"2024","unstructured":"Caruso, C. M., Guarrasi, V., Ramella, S. & Soda, P. A deep learning approach for overall survival prediction in lung cancer with missing values. Comput. Methods Prog. Biomed. 254, 108308 (2024).","journal-title":"Comput. Methods Prog. Biomed."},{"key":"2783_CR16","doi-asserted-by":"publisher","DOI":"10.1038\/s41746-025-02018-x","volume":"8","author":"J Lee","year":"2025","unstructured":"Lee, J. et al. Gliosurv: interpretable transformer for multimodal, individualized survival prediction in diffuse glioma. npj Digit. Med. 8, 660 (2025).","journal-title":"npj Digit. Med."},{"key":"2783_CR17","doi-asserted-by":"crossref","unstructured":"Graf, R., Todd, S. & Baksh, M. Comparison of the Cox proportional hazards model and Random Survival Forest algorithm for predicting patient-specific survival probabilities in clinical trial data. Preprint at https:\/\/arxiv.org\/abs\/2502.03119 (2025).","DOI":"10.1002\/bimj.70171"},{"key":"2783_CR18","doi-asserted-by":"crossref","unstructured":"Yang, H. et al. Mmsurv: a multimodal multi-instance multi-cancer survival prediction model integrating pathological images, clinical information, and sequencing data. Brief. Bioinform. 26, bbaf209 (2025).","DOI":"10.1093\/bib\/bbaf209"},{"key":"2783_CR19","doi-asserted-by":"publisher","first-page":"107663","DOI":"10.1016\/j.bspc.2025.107663","volume":"106","author":"Y Wu","year":"2025","unstructured":"Wu, Y. et al. Multimodal learning for non-small cell lung cancer prognosis. Biomed. Signal Process. Control 106, 107663 (2025).","journal-title":"Biomed. Signal Process. Control"},{"key":"2783_CR20","doi-asserted-by":"publisher","DOI":"10.1186\/s12859-023-05160-z","volume":"24","author":"S Oh","year":"2023","unstructured":"Oh, S., Kang, S.-R., Oh, I.-J. & Kim, M.-S. Deep learning model integrating positron emission tomography and clinical data for prognosis prediction in non-small cell lung cancer patients. BMC Bioinformatics 24, 39 (2023).","journal-title":"BMC Bioinformatics"},{"key":"2783_CR21","doi-asserted-by":"crossref","unstructured":"Yang, H. et al. Multimodal deep learning approaches for precision oncology: a comprehensive review. Brief. Bioinform. 26, bbae699 (2024).","DOI":"10.1093\/bib\/bbae699"},{"key":"2783_CR22","unstructured":"Bommasani, R. On the opportunities and risks of foundation models. Preprint at https:\/\/arxiv.org\/abs\/2108.07258 (2021)."},{"key":"2783_CR23","doi-asserted-by":"publisher","first-page":"102996","DOI":"10.1016\/j.media.2023.102996","volume":"91","author":"S Zhang","year":"2023","unstructured":"Zhang, S. & Metaxas, D. N. On the challenges and perspectives of foundation models for medical image analysis. Med. Image Anal. 91, 102996 (2023).","journal-title":"Med. Image Anal."},{"key":"2783_CR24","doi-asserted-by":"crossref","unstructured":"Li, X. et al. Artificial general intelligence for medical imaging analysis. IEEE Rev. Biomed. Eng. 18, 113\u2013129 (2025).","DOI":"10.1109\/RBME.2024.3493775"},{"key":"2783_CR25","doi-asserted-by":"crossref","unstructured":"Lu, M. Y. et al. Visual language pretrained multiple instance zero-shot transfer for histopathology images. In Proc. 2023 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 19764\u201319775 (IEEE, 2023).","DOI":"10.1109\/CVPR52729.2023.01893"},{"key":"2783_CR26","doi-asserted-by":"crossref","unstructured":"Ding, T. et al. A multimodal whole-slide foundation model for pathology. Nat. Med. 31, 3749\u20133761 (2025).","DOI":"10.1038\/s41591-025-03982-3"},{"key":"2783_CR27","doi-asserted-by":"crossref","unstructured":"Blankemeier, L. et al. Merlin: a computed tomography vision\u2013language foundation model and dataset. Nature 652, 1318\u20131328 (2026).","DOI":"10.1038\/s41586-026-10181-8"},{"key":"2783_CR28","doi-asserted-by":"publisher","first-page":"181 \u2013 188","DOI":"10.1038\/s41586-024-07441-w","volume":"630","author":"H Xu","year":"2024","unstructured":"Xu, H. et al. A whole-slide foundation model for digital pathology from real-world data. Nature 630, 181 \u2013 188 (2024).","journal-title":"Nature"},{"key":"2783_CR29","doi-asserted-by":"crossref","unstructured":"Hamamci, I. E. et al. Generalist foundation models from a multimodal dataset for 3d computed tomography. Nat. Biomed. Eng. 1\u201319 (2026).","DOI":"10.1038\/s41551-025-01599-y"},{"key":"2783_CR30","unstructured":"Pai, S. et al. Vision foundation models for computed tomography. Preprint at https:\/\/arxiv.org\/abs\/2501.09001 (2025)"},{"key":"2783_CR31","doi-asserted-by":"publisher","first-page":"109196","DOI":"10.1016\/j.cmpb.2025.109196","volume":"275","author":"F Ruffini","year":"2025","unstructured":"Ruffini, F., Ayllon, E. M., Shen, L., Soda, P. & Guarrasi, V. Benchmarking foundation models and parameter-efficient fine-tuning for prognosis prediction in medical imaging. Comput. Methods Programs Biomed. 275, 109196 (2025).","journal-title":"Comput. Methods Programs Biomed."},{"key":"2783_CR32","doi-asserted-by":"publisher","first-page":"96","DOI":"10.1016\/j.aiopen.2026.02.005","volume":"7","author":"CM Caruso","year":"2026","unstructured":"Caruso, C. M., Soda, P. & Guarrasi, V. Not another imputation method: a transformer-based model for missing values in tabular datasets. AI Open 7, 96\u2013122 (2026).","journal-title":"AI Open"},{"key":"2783_CR33","doi-asserted-by":"publisher","first-page":"1095","DOI":"10.1016\/j.ccell.2022.09.012","volume":"40","author":"J Lipkova","year":"2022","unstructured":"Lipkova, J. et al. Artificial intelligence for multimodal data integration in oncology. Cancer Cell 40, 1095\u20131110 (2022).","journal-title":"Cancer Cell"},{"key":"2783_CR34","doi-asserted-by":"publisher","first-page":"595","DOI":"10.1093\/jnci\/djt072","volume":"105 9","author":"C Lee","year":"2013","unstructured":"Lee, C. et al. Impact of egfr inhibitor in non-small cell lung cancer on progression-free and overall survival: a meta-analysis. J. Natl. Cancer Inst. 105 9, 595\u2013605 (2013).","journal-title":"J. Natl. Cancer Inst."},{"key":"2783_CR35","doi-asserted-by":"publisher","first-page":"1301 \u2013 1311","DOI":"10.1200\/JCO.21.01308","volume":"40","author":"D Spigel","year":"2022","unstructured":"Spigel, D. et al. Five-year survival outcomes from the pacific trial: durvalumab after chemoradiotherapy in stage iii non-small-cell lung cancer. J. Clin. Oncol. 40, 1301 \u2013 1311 (2022).","journal-title":"J. Clin. Oncol."},{"key":"2783_CR36","doi-asserted-by":"publisher","first-page":"555","DOI":"10.1038\/s41551-020-00682-w","volume":"5","author":"MY Lu","year":"2021","unstructured":"Lu, M. Y. et al. Data-efficient and weakly supervised computational pathology on whole-slide images. Nat. Biomed. Eng. 5, 555\u2013570 (2021).","journal-title":"Nat. Biomed. Eng."},{"key":"2783_CR37","doi-asserted-by":"crossref","unstructured":"K, M. S. et al. Survival analysis with cox proportional hazards model in predicting patient outcomes. In 2024 5th International Conference on Electronics and Sustainable Communication Systems (ICESC) 1155\u20131161 (IEEE, 2024).","DOI":"10.1109\/ICESC60852.2024.10689732"},{"key":"2783_CR38","doi-asserted-by":"publisher","first-page":"841","DOI":"10.1214\/08-AOAS169","volume":"2","author":"H Ishwaran","year":"2008","unstructured":"Ishwaran, H., Kogalur, U. B., Blackstone, E. H. & Lauer, M. S. Random survival forests. Ann. Appl. Stat. 2, 841\u2013860 (2008).","journal-title":"Ann. Appl. Stat."},{"key":"2783_CR39","doi-asserted-by":"publisher","first-page":"355","DOI":"10.1093\/biostatistics\/kxj011","volume":"7","author":"T Hothorn","year":"2006","unstructured":"Hothorn, T., B\u00fchlmann, P., Dudoit, S., Molinaro, A. M. & van der Laan, M. J. Survival ensembles. Biostatistics 7, 355\u2013373 (2006).","journal-title":"Biostatistics"},{"key":"2783_CR40","unstructured":"Popov, S., Morozov, S. & Babenko, A. Neural oblivious decision ensembles for deep learning on tabular data. Preprint at https:\/\/arxiv.org\/abs\/1909.06312 (2019)."},{"key":"2783_CR41","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-024-72760-x","volume":"14","author":"Q Zhao","year":"2024","unstructured":"Zhao, Q. et al. Clinical multi-dimensional prognostic nomogram for predicting the efficacy of immunotherapy in nsclc. Sci. Rep. 14, 21380 (2024).","journal-title":"Sci. Rep."},{"key":"2783_CR42","doi-asserted-by":"publisher","first-page":"882","DOI":"10.1016\/j.chest.2024.05.026","volume":"166","author":"FC Detterbeck","year":"2024","unstructured":"Detterbeck, F. C. et al. The proposed ninth edition tnm classification of lung cancer. Chest 166, 882\u2013895 (2024).","journal-title":"Chest"},{"key":"2783_CR43","first-page":"1356 \u2013 1384","volume":"40","author":"M Daly","year":"2021","unstructured":"Daly, M. et al. Management of stage III non-small-cell lung cancer: ASCO guideline. J. Clin. Oncol. 40, 1356 \u2013 1384 (2021).","journal-title":"J. Clin. Oncol."},{"key":"2783_CR44","doi-asserted-by":"publisher","DOI":"10.1186\/s12911-020-01225-8","volume":"20","author":"L Tong","year":"2020","unstructured":"Tong, L., Mitchel, J., Chatlin, K. & Wang, M. D. Deep learning based feature-level integration of multi-omics data for breast cancer patients survival analysis. BMC Med. Inform. Decis. Mak. 20, 225 (2020).","journal-title":"BMC Med. Inform. Decis. Mak."},{"key":"2783_CR45","first-page":"1697 \u2013 1707","volume":"22","author":"S young Park","year":"2021","unstructured":"young Park, S., Park, J. E., Kim, H. & Park, S. H. Review of statistical methods for evaluating the performance of survival or other time-to-event prediction models (from conventional to deep learning approaches). Korean J. Radiol. 22, 1697 \u2013 1707 (2021).","journal-title":"Korean J. Radiol."}],"container-title":["npj Digital Medicine"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41746-026-02783-3","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41746-026-02783-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41746-026-02783-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,8]],"date-time":"2026-10-08T22:51:47Z","timestamp":1791499907000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41746-026-02783-3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,22]]},"references-count":45,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,12]]}},"alternative-id":["2783"],"URL":"https:\/\/doi.org\/10.1038\/s41746-026-02783-3","relation":{"has-preprint":[{"id-type":"doi","id":"10.21203\/rs.3.rs-8490631\/v1","asserted-by":"object"}]},"ISSN":["2398-6352"],"issn-type":[{"value":"2398-6352","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6,22]]},"assertion":[{"value":"31 December 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"13 May 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"22 June 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The authors declare no competing interests.","order":1,"name":"Ethics","label":"Competing interests","group":{"name":"EthicsHeading","label":"Ethics"}}],"article-number":"776"}}