{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,30]],"date-time":"2026-10-30T13:23:29Z","timestamp":1793366609149,"version":"4.5.0"},"reference-count":27,"publisher":"SAGE Publications","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/journals.sagepub.com\/page\/policies\/text-and-data-mining-license"}],"content-domain":{"domain":["journals.sagepub.com"],"crossmark-restriction":true},"short-container-title":["Cancer Inform"],"published-print":{"date-parts":[[2025,1]]},"abstract":"<jats:sec>\n                    <jats:title>Objectives:<\/jats:title>\n                    <jats:p>Multimodal deep learning models have the potential to significantly improve survival predictions and treatment planning for cancer patients. These models integrate diverse data modalities using early, intermediate, or late fusion techniques. However, many existing multimodal models either underperform or show only marginal improvements over unimodal models. To establish the true efficacy of multimodal survival prediction models, it is critical to demonstrate consistent and substantial advantages over unimodal counterparts.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods:<\/jats:title>\n                    <jats:p>In this paper, we introduce the Robust Multimodal Survival Model (RMSurv), a novel discrete late fusion model that leverages synthetic data generation to compute time-dependent weights for various modalities. RMSurv utilizes up to 6 distinct data modalities from The Cancer Genome Atlas Program (TCGA) non-small cell lung cancer and the TCGA pan-cancer datasets to predict overall survival over a period of 10\u2009years. The key innovations of RMSurv are the calculation of time-dependent late fusion weights using a synthetically generated dataset and a new statistical feature normalization technique to enhance the interpretability and accuracy of discrete survival predictions. We evaluate the performance of the proposed method and several alternatives with cross validation using the concordance index, and vary the number of modalities included. We also create a late fusion simulation to highlight the complex relationships of multimodal fusion.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results:<\/jats:title>\n                    <jats:p>In our experiments, RMSurv outperforms the best unimodal model\u2019s Concordance index (C-Index) by 0.0273 on the 6-modal TCGA Lung Adenocarcinoma (LUAD) dataset. Existing late and early fusion methods improved the C-index by only 0.0143 and 0.0072, respectively. RMSurv also performs best on the combined TCGA non-small-cell lung cancer dataset and the TCGA pan-cancer dataset.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions:<\/jats:title>\n                    <jats:p>These advancements underscore RMSurv\u2019s potential as a powerful approach for survival prediction, establishing robust multimodal benefits, and setting a new benchmark for survival prediction models in pan-cancer settings.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1177\/11769351251376192","type":"journal-article","created":{"date-parts":[[2025,9,27]],"date-time":"2025-09-27T09:55:12Z","timestamp":1758966912000},"update-policy":"https:\/\/doi.org\/10.1177\/sage-journals-update-policy","source":"Crossref","is-referenced-by-count":6,"title":["Robust Multimodal Fusion for Survival Prediction in Cancer Patients"],"prefix":"10.1177","volume":"24","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-4083-5709","authenticated-orcid":false,"given":"Dominic","family":"Flack","sequence":"first","affiliation":[{"name":"Chester F. Carlson Center for Imaging Science, Rochester Institute of Technology, NY, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Aakash","family":"Tripathi","sequence":"additional","affiliation":[{"name":"Department of Machine Learning, Moffitt Cancer Center, Tampa, FL, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Asim","family":"Waqas","sequence":"additional","affiliation":[{"name":"Department of Machine Learning, Moffitt Cancer Center, Tampa, FL, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ghulam","family":"Rasool","sequence":"additional","affiliation":[{"name":"Department of Machine Learning, Moffitt Cancer Center, Tampa, FL, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7168-5858","authenticated-orcid":false,"given":"Dimah","family":"Dera","sequence":"additional","affiliation":[{"name":"Chester F. Carlson Center for Imaging Science, Rochester Institute of Technology, NY, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"179","published-online":{"date-parts":[[2025,9,27]]},"reference":[{"key":"e_1_3_2_2_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.ccell.2022.09.012"},{"key":"e_1_3_2_3_2","article-title":"SeNMo: a self-normalizing deep learning model for enhanced multi-omics data analysis in oncology","author":"Waqas A","year":"2024","unstructured":"Waqas A, Tripathi A, Ahmed S. SeNMo: a self-normalizing deep learning model for enhanced multi-omics data analysis in oncology. arXiv: 2405.08226, 2024.","journal-title":"arXiv: 2405.08226"},{"key":"e_1_3_2_4_2","doi-asserted-by":"publisher","DOI":"10.1111\/j.2517-6161.1972.tb00899.x"},{"key":"e_1_3_2_5_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-021-92799-4"},{"key":"e_1_3_2_6_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-025-93770-3"},{"key":"e_1_3_2_7_2","article-title":"Comprehensive multimodal deep learning survival prediction enabled by a transformer architecture: a multicenter study in glioblastoma","volume":"6","author":"Gomaa A","year":"2024","unstructured":"Gomaa A, Huang Y, Hagag A, et al. Comprehensive multimodal deep learning survival prediction enabled by a transformer architecture: a multicenter study in glioblastoma. Neurooncol Adv. 2024;6:vdae122.","journal-title":"Neurooncol Adv"},{"key":"e_1_3_2_8_2","doi-asserted-by":"publisher","DOI":"10.1093\/bib\/bbaf209"},{"key":"e_1_3_2_9_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.ccell.2022.07.004"},{"key":"e_1_3_2_10_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41698-025-00917-6"},{"key":"e_1_3_2_11_2","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pcbi.1006076"},{"key":"e_1_3_2_12_2","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2020.3021387"},{"key":"e_1_3_2_13_2","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btac113"},{"key":"e_1_3_2_14_2","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-023-00633-5"},{"key":"e_1_3_2_15_2","doi-asserted-by":"publisher","DOI":"10.1093\/bib\/bbab569"},{"key":"e_1_3_2_16_2","doi-asserted-by":"publisher","DOI":"10.1093\/imanum\/22.3.329"},{"key":"e_1_3_2_17_2","doi-asserted-by":"publisher","DOI":"10.1038\/ng.2764"},{"key":"e_1_3_2_18_2","article-title":"An integrated TCGA pan-cancer clinical data resource to drive high-quality survival outcome analytics","volume":"173","author":"Liu J","year":"2018","unstructured":"Liu J, Lichtenberg T, Hoadley KA, et al. An integrated TCGA pan-cancer clinical data resource to drive high-quality survival outcome analytics. Cells. 2018;173:400-416.e11.","journal-title":"Cells"},{"key":"e_1_3_2_19_2","doi-asserted-by":"publisher","DOI":"10.1038\/npp.2012.112"},{"key":"e_1_3_2_20_2","doi-asserted-by":"publisher","DOI":"10.1038\/ncomms4887"},{"key":"e_1_3_2_21_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41587-020-0546-8"},{"key":"e_1_3_2_22_2","doi-asserted-by":"publisher","DOI":"10.3390\/s24051634"},{"key":"e_1_3_2_23_2","article-title":"TRIPOD+AI statement: updated guidance for reporting clinical prediction models that use regression or machine learning methods","volume":"385","author":"Moons K","year":"2024","unstructured":"Moons K, Collins G, Reitsma J. TRIPOD+AI statement: updated guidance for reporting clinical prediction models that use regression or machine learning methods. BMJ. 2024;385:e078378.","journal-title":"BMJ"},{"key":"e_1_3_2_24_2","article-title":"HoneyBee: a scalable modular framework for creating multimodal oncology datasets with foundational embedding models","author":"Tripathi A","year":"2024","unstructured":"Tripathi A, Waqas A, Yilmaz Y, Rasool G. HoneyBee: a scalable modular framework for creating multimodal oncology datasets with foundational embedding models. arXiv: 2405.07460, 2024.","journal-title":"arXiv: 2405.07460"},{"key":"e_1_3_2_25_2","article-title":"GatorTron: a large clinical language model to unlock patient information from unstructured electronic health records","author":"Yang X","year":"2022","unstructured":"Yang X, Chen A, PourNejatian N. GatorTron: a large clinical language model to unlock patient information from unstructured electronic health records. arXiv: 2203.03540, 2022.","journal-title":"arXiv: 2203.03540"},{"key":"e_1_3_2_26_2","article-title":"A general-purpose self-supervised model for computational pathology","author":"Chen R","year":"2023","unstructured":"Chen R, Ding T, Lu M. A general-purpose self-supervised model for computational pathology. arXiv: 2308.15474. 2023.","journal-title":"arXiv: 2308.15474"},{"key":"e_1_3_2_27_2","doi-asserted-by":"publisher","DOI":"10.1023\/A:1008202821328"},{"key":"e_1_3_2_28_2","doi-asserted-by":"publisher","DOI":"10.3348\/kjr.2020.0325"}],"container-title":["Cancer Informatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.1177\/11769351251376192","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/full-xml\/10.1177\/11769351251376192","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.1177\/11769351251376192","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,28]],"date-time":"2026-04-28T15:20:51Z","timestamp":1777389651000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.sagepub.com\/doi\/10.1177\/11769351251376192"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,1]]},"references-count":27,"alternative-id":["10.1177\/11769351251376192"],"URL":"https:\/\/doi.org\/10.1177\/11769351251376192","relation":{},"ISSN":["1176-9351","1176-9351"],"issn-type":[{"value":"1176-9351","type":"print"},{"value":"1176-9351","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,1]]},"article-number":"11769351251376192"}}