{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T12:26:08Z","timestamp":1784204768344,"version":"3.55.0"},"reference-count":32,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,4,25]],"date-time":"2026-04-25T00:00:00Z","timestamp":1777075200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,7,2]],"date-time":"2026-07-02T00:00:00Z","timestamp":1782950400000},"content-version":"vor","delay-in-days":68,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["62225112"],"award-info":[{"award-number":["62225112"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["62225112"],"award-info":[{"award-number":["62225112"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["62225112"],"award-info":[{"award-number":["62225112"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"name":"The Sino-German Center Call for the Mobility Programme 2020","award":["M-0171"],"award-info":[{"award-number":["M-0171"]}]},{"name":"The Sino-German Center Call for the Mobility Programme 2020","award":["M-0171"],"award-info":[{"award-number":["M-0171"]}]},{"name":"National Key R&D Program","award":["2024YFC3506202"],"award-info":[{"award-number":["2024YFC3506202"]}]},{"name":"The Science Foundation for Distinguished Young Scholars of Guangxi Medical University"},{"name":"The Yongjiang Program of Nanning","award":["2021015"],"award-info":[{"award-number":["2021015"]}]},{"name":"Shanghai Oriental Talents-Excellent Young Academic Leader"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["npj Digit. Med."],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>\n                    Accurate prostate cancer (PCa) diagnosis remains difficult because of tumor heterogeneity and the challenge of integrating multimodal clinical information. We developed Prost-LM, a multimodal large language model that jointly embeds MRI-derived features, numerical PSA values, and free-text clinical reports into a unified semantic space to enable deep cross-modal reasoning. Trained and validated on a large multi-center cohort of 3940 patients, Prost-LM achieved strong diagnostic performance, with an internal validation AUC of 0.954 for distinguishing PCa from benign conditions, outperforming MRI-only models (AUC = 0.868,\n                    <jats:italic>P<\/jats:italic>\n                    &lt; 0.001). For detecting clinically significant PCa (Gleason score \u2265 7), Prost-LM reached an AUC of 0.955. Additionally, the model provides interpretable diagnostic decisions to support clinical verification. These results suggest Prost-LM can improve automated PCa diagnosis and support precision oncology through multimodal AI.\n                  <\/jats:p>","DOI":"10.1038\/s41746-026-02670-x","type":"journal-article","created":{"date-parts":[[2026,4,25]],"date-time":"2026-04-25T14:54:30Z","timestamp":1777128870000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Integrating multimodal clinical data with a large model for prostate cancer diagnosis"],"prefix":"10.1038","volume":"9","author":[{"given":"Chengbang","family":"Wang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuan","family":"Tian","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shaojie","family":"Yin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xuhong","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xuedong","family":"Wei","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lingfeng","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhengdong","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guijian","family":"Pang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yan","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wangjian","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shukai","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ziwei","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiangnan","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hao","family":"He","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Minglun","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhankui","family":"Jia","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xu","family":"Gao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fubo","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guangtao","family":"Zhai","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bin","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,4,25]]},"reference":[{"key":"2670_CR1","doi-asserted-by":"publisher","first-page":"229","DOI":"10.3322\/caac.21834","volume":"74","author":"F Bray","year":"2024","unstructured":"Bray, F. et al. Global cancer statistics 2022: Globocan estimates of incidence and mortality worldwide for 36 cancers in 185 countries. Cancer J. Clin. 74, 229\u2013263 (2024).","journal-title":"Cancer J. Clin."},{"key":"2670_CR2","doi-asserted-by":"publisher","first-page":"7","DOI":"10.3322\/caac.21708","volume":"72","author":"RL Siegel","year":"2022","unstructured":"Siegel, R. L., Miller, K. D., Fuchs, H. E. & Jemal, A. Cancer statistics, 2022. Cancer J. Clin. 72, 7\u201333 (2022).","journal-title":"Cancer J. Clin."},{"key":"2670_CR3","doi-asserted-by":"publisher","first-page":"112","DOI":"10.1016\/j.eururo.2011.09.027","volume":"61","author":"L Bud\u00e4us","year":"2012","unstructured":"Bud\u00e4us, L. et al. Functional outcomes and complications following radiation therapy for prostate cancer: a critical analysis of the literature. Eur. Urol. 61, 112\u2013127 (2012).","journal-title":"Eur. Urol."},{"key":"2670_CR4","doi-asserted-by":"publisher","first-page":"16","DOI":"10.1016\/j.eururo.2015.08.052","volume":"69","author":"JC Weinreb","year":"2016","unstructured":"Weinreb, J. C. et al. Pi-rads prostate imaging\u2013reporting and data system: 2015, version 2. Eur. Urol. 69, 16\u201340 (2016).","journal-title":"Eur. Urol."},{"key":"2670_CR5","doi-asserted-by":"publisher","first-page":"177","DOI":"10.1016\/j.eururo.2017.01.042","volume":"72","author":"S Woo","year":"2017","unstructured":"Woo, S., Suh, C. H., Kim, S. Y., Cho, J. Y. & Kim, S. H. Diagnostic performance of prostate imaging reporting and data system version 2 for detection of prostate cancer: a systematic review and diagnostic meta-analysis. Eur. Urol. 72, 177\u2013188 (2017).","journal-title":"Eur. Urol."},{"key":"2670_CR6","doi-asserted-by":"publisher","first-page":"76","DOI":"10.1148\/radiol.2020190646","volume":"296","author":"AC Westphalen","year":"2020","unstructured":"Westphalen, A. C. et al. Variability of the positive predictive value of pi-rads for prostate MRI across 26 centers: experience of the Society of Abdominal Radiology prostate cancer disease-focused panel. Radiology 296, 76\u201384 (2020).","journal-title":"Radiology"},{"key":"2670_CR7","doi-asserted-by":"publisher","first-page":"682","DOI":"10.1016\/j.eururo.2021.08.002","volume":"80","author":"L Emmett","year":"2021","unstructured":"Emmett, L. et al. The additive diagnostic value of prostate-specific membrane antigen positron emission tomography computed tomography to multiparametric magnetic resonance imaging triage in the diagnosis of prostate cancer (primary): a prospective multicentre study. Eur. Urol. 80, 682\u2013689 (2021).","journal-title":"Eur. Urol."},{"key":"2670_CR8","doi-asserted-by":"crossref","unstructured":"Wang, N. N. et al. Applying the precision approach in biopsy naive and previously negative prostate biopsy patients. In Urologic Oncology: Seminars and Original Investigations, vol. 37, 530\u2013e19 (Elsevier, 2019).","DOI":"10.1016\/j.urolonc.2019.05.002"},{"key":"2670_CR9","doi-asserted-by":"publisher","first-page":"41","DOI":"10.1038\/s41585-019-0212-4","volume":"17","author":"A Stabile","year":"2020","unstructured":"Stabile, A. et al. Multiparametric MRI for prostate cancer diagnosis: current status and future directions. Nat. Rev. Urol. 17, 41\u201361 (2020).","journal-title":"Nat. Rev. Urol."},{"key":"2670_CR10","doi-asserted-by":"publisher","first-page":"431","DOI":"10.1200\/JCO.2006.06.9351","volume":"25","author":"H Lilja","year":"2007","unstructured":"Lilja, H. et al. Long-term prediction of prostate cancer up to 25 years before diagnosis of prostate cancer using prostate kallikreins measured at age 44 to 50 years. J. Clin. Oncol. 25, 431\u2013436 (2007).","journal-title":"J. Clin. Oncol."},{"key":"2670_CR11","doi-asserted-by":"publisher","first-page":"941349","DOI":"10.3389\/fonc.2022.941349","volume":"12","author":"S Chen","year":"2022","unstructured":"Chen, S. et al. Machine learning-based models enhance the prediction of prostate cancer. Front. Oncol. 12, 941349 (2022).","journal-title":"Front. Oncol."},{"key":"2670_CR12","doi-asserted-by":"publisher","first-page":"78140","DOI":"10.18632\/oncotarget.11293","volume":"7","author":"Y-D Zhang","year":"2016","unstructured":"Zhang, Y.-D. et al. An imaging-based approach predicts clinical outcomes in prostate cancer through a novel support vector machine classification. Oncotarget 7, 78140 (2016).","journal-title":"Oncotarget"},{"key":"2670_CR13","doi-asserted-by":"publisher","first-page":"586","DOI":"10.4103\/1008-682X.186884","volume":"19","author":"L-H Xiao","year":"2017","unstructured":"Xiao, L.-H. et al. Prostate cancer prediction using the random forest algorithm that takes into account transrectal ultrasound findings, age, and serum levels of prostate-specific antigen. Asian J. Androl. 19, 586\u2013590 (2017).","journal-title":"Asian J. Androl."},{"key":"2670_CR14","doi-asserted-by":"crossref","unstructured":"Stenman, U.-H., Leinonen, J., Zhang, W.-M. & Finne, P. Prostate-specific antigen. In Seminars in Cancer Biology, vol. 9, 83\u201393 (Elsevier, 1999).","DOI":"10.1006\/scbi.1998.0086"},{"key":"2670_CR15","doi-asserted-by":"publisher","first-page":"1083","DOI":"10.1109\/TMI.2014.2303821","volume":"33","author":"G Litjens","year":"2014","unstructured":"Litjens, G., Debats, O., Barentsz, J., Karssemeijer, N. & Huisman, H. Computer-aided detection of prostate cancer in MRI. IEEE Trans. Med. imaging 33, 1083\u20131092 (2014).","journal-title":"IEEE Trans. Med. imaging"},{"key":"2670_CR16","doi-asserted-by":"publisher","first-page":"197","DOI":"10.1016\/j.eururo.2018.05.003","volume":"74","author":"DP Ankerst","year":"2018","unstructured":"Ankerst, D. P. et al. A contemporary prostate biopsy risk calculator based on multiple heterogeneous cohorts. Eur. Urol. 74, 197\u2013203 (2018).","journal-title":"Eur. Urol."},{"key":"2670_CR17","doi-asserted-by":"publisher","first-page":"879","DOI":"10.1016\/S1470-2045(24)00220-1","volume":"25","author":"A Saha","year":"2024","unstructured":"Saha, A. et al. Artificial intelligence and radiologists in prostate cancer detection on MRI (pi-cai): an international, paired, non-inferiority, confirmatory study. Lancet Oncol. 25, 879\u2013887 (2024).","journal-title":"Lancet Oncol."},{"key":"2670_CR18","doi-asserted-by":"publisher","first-page":"896","DOI":"10.1016\/j.crad.2019.07.011","volume":"74","author":"B Liu","year":"2019","unstructured":"Liu, B. et al. Prediction of prostate cancer aggressiveness with a combination of radiomics and machine learning-based analysis of dynamic contrast-enhanced MRI. Clin. Radiol. 74, 896\u2013e1 (2019).","journal-title":"Clin. Radiol."},{"key":"2670_CR19","doi-asserted-by":"publisher","first-page":"523","DOI":"10.1007\/s11571-020-09587-5","volume":"14","author":"AA Abbasi","year":"2020","unstructured":"Abbasi, A. A. et al. Detecting prostate cancer using deep learning convolution neural network with transfer learning approach. Cogn. Neurodyn. 14, 523\u2013533 (2020).","journal-title":"Cogn. Neurodyn."},{"key":"2670_CR20","doi-asserted-by":"publisher","first-page":"e222276","DOI":"10.1148\/radiol.222276","volume":"307","author":"CA Hamm","year":"2023","unstructured":"Hamm, C. A. et al. Interactive explainable deep learning model informs prostate cancer diagnosis at MRI. Radiology 307, e222276 (2023).","journal-title":"Radiology"},{"key":"2670_CR21","doi-asserted-by":"publisher","first-page":"e445","DOI":"10.1016\/S2589-7500(21)00082-0","volume":"3","author":"A Hiremath","year":"2021","unstructured":"Hiremath, A. et al. An integrated nomogram combining deep learning, prostate imaging\u2013reporting and data system (PI-RADS) scoring, and clinical variables for identification of clinically significant prostate cancer on biparametric MRI: a retrospective multicentre study. Lancet Digit. Health 3, e445\u2013e454 (2021).","journal-title":"Lancet Digit. Health"},{"key":"2670_CR22","doi-asserted-by":"publisher","first-page":"2257","DOI":"10.3390\/cancers17132257","volume":"17","author":"E Bacchetti","year":"2025","unstructured":"Bacchetti, E. et al. A deep learning model integrating clinical and MRI features improves risk stratification and reduces unnecessary biopsies in men with suspected prostate cancer. Cancers 17, 2257 (2025).","journal-title":"Cancers"},{"key":"2670_CR23","doi-asserted-by":"publisher","first-page":"45","DOI":"10.1016\/j.euros.2022.04.017","volume":"41","author":"S Parekh","year":"2022","unstructured":"Parekh, S. et al. The Mount Sinai prebiopsy risk calculator for predicting any prostate cancer and clinically significant prostate cancer: development of a risk predictive tool and validation with advanced neural networking, prostate magnetic resonance imaging outcome database, and European randomized study of screening for prostate cancer risk calculator. Eur. Urol. open Sci. 41, 45\u201354 (2022).","journal-title":"Eur. Urol. open Sci."},{"key":"2670_CR24","doi-asserted-by":"publisher","first-page":"183","DOI":"10.3390\/jcm14010183","volume":"14","author":"M Sungur","year":"2024","unstructured":"Sungur, M., Ayka\u00e7, A., Aydin, M. E., Celik, O. & Kaya, C. Machine learning-based prediction of prostate biopsy necessity using psa, MRI, and hematologic parameters. J. Clin. Med. 14, 183 (2024).","journal-title":"J. Clin. Med."},{"key":"2670_CR25","doi-asserted-by":"publisher","first-page":"e240507","DOI":"10.1148\/rycan.240507","volume":"7","author":"AC Rodrigues","year":"2025","unstructured":"Rodrigues, A. C. et al. Improving clinically significant prostate cancer detection with a multimodal machine learning approach: a large-scale multicenter study. Radiol. Imaging Cancer 7, e240507 (2025).","journal-title":"Radiol. Imaging Cancer"},{"key":"2670_CR26","doi-asserted-by":"publisher","first-page":"102274","DOI":"10.1016\/j.lindif.2023.102274","volume":"103","author":"E Kasneci","year":"2023","unstructured":"Kasneci, E. et al. ChatGPT for good? on opportunities and challenges of large language models for education. Learn. Individ. Differ. 103, 102274 (2023).","journal-title":"Learn. Individ. Differ."},{"key":"2670_CR27","doi-asserted-by":"crossref","unstructured":"Liang, Z. et al. A survey of multimodel large language models. In Proceedings of the 3rd International Conference on Computer, Artificial Intelligence and Control Engineering, 405\u2013409 (2024).","DOI":"10.1145\/3672758.3672824"},{"key":"2670_CR28","doi-asserted-by":"crossref","unstructured":"Nguyen, D.-K. & Okatani, T. Improved fusion of visual and language representations by dense symmetric co-attention for visual question answering. In Proceedings of the IEEE conference on computer vision and pattern recognition, 6087\u20136096 (2018).","DOI":"10.1109\/CVPR.2018.00637"},{"key":"2670_CR29","doi-asserted-by":"publisher","first-page":"32942","DOI":"10.52202\/068431-2387","volume":"35","author":"Z-Y Dou","year":"2022","unstructured":"Dou, Z.-Y. et al. Coarse-to-fine vision-language pre-training with fusion in the backbone. Adv. Neural Inf. Process. Syst. 35, 32942\u201332956 (2022).","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"2670_CR30","doi-asserted-by":"crossref","unstructured":"Huang, J. et al. Clover: Towards a unified video-language alignment and fusion model. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 14856\u201314866 (2023).","DOI":"10.1109\/CVPR52729.2023.01427"},{"key":"2670_CR31","doi-asserted-by":"publisher","first-page":"33536","DOI":"10.52202\/068431-2430","volume":"35","author":"F Wang","year":"2022","unstructured":"Wang, F., Zhou, Y., Wang, S., Vardhanabhuti, V. & Yu, L. Multi-granularity cross-modal alignment for generalized medical visual representation learning. Adv. Neural Inf. Process. Syst. 35, 33536\u201333549 (2022).","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"2670_CR32","unstructured":"Loshchilov, I. & Hutter, F. Decoupled weight decay regularization. International Conference on Learning Representations (2017)."}],"container-title":["npj Digital Medicine"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41746-026-02670-x","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41746-026-02670-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41746-026-02670-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T22:23:57Z","timestamp":1782944637000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41746-026-02670-x"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,25]]},"references-count":32,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,12]]}},"alternative-id":["2670"],"URL":"https:\/\/doi.org\/10.1038\/s41746-026-02670-x","relation":{},"ISSN":["2398-6352"],"issn-type":[{"value":"2398-6352","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4,25]]},"assertion":[{"value":"5 July 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"13 April 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"25 April 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","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"497"}}