{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,7]],"date-time":"2026-01-07T21:25:58Z","timestamp":1767821158130,"version":"3.49.0"},"reference-count":22,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2025,12,3]],"date-time":"2025-12-03T00:00:00Z","timestamp":1764720000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,1,7]],"date-time":"2026-01-07T00:00:00Z","timestamp":1767744000000},"content-version":"vor","delay-in-days":35,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100001691","name":"Japan Society for the Promotion of Science","doi-asserted-by":"publisher","award":["23K17235"],"award-info":[{"award-number":["23K17235"]}],"id":[{"id":"10.13039\/501100001691","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001691","name":"Japan Society for the Promotion of Science","doi-asserted-by":"publisher","award":["24K10131"],"award-info":[{"award-number":["24K10131"]}],"id":[{"id":"10.13039\/501100001691","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100013422","name":"NEC Corporation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100013422","id-type":"DOI","asserted-by":"publisher"}]},{"name":"the Japan Science and Technology Agency Moonshot R&D Program","award":["JPMJMS2022-9"],"award-info":[{"award-number":["JPMJMS2022-9"]}]},{"name":"RIKEN TRIP initiative"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["npj Digit. Med."],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Machine learning has shown promise in medical image classification. However, its generalizability remains challenging. Here, we show that data-efficient pre-surgical prognostication of prostate cancer from biopsy specimens is enabled by versatile feature extraction from whole-mount histopathology and a clinically informed intermediate reasoning step. With data from multiple institutions, our pipeline resolved dual-domain shifts across specimen types and institutions and achieved consistent external validation, reinforced by comprehensive analyses of generalizability. This highlights the robustness of our prognostic approach when compared to the Gleason grading system. We establish an equitable, interpretable, and clinically applicable framework, supporting actionable decisions for prognosis and treatment planning, even in limited real-world clinical environments.<\/jats:p>","DOI":"10.1038\/s41746-025-02193-x","type":"journal-article","created":{"date-parts":[[2025,12,3]],"date-time":"2025-12-03T09:52:12Z","timestamp":1764755532000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Clinically informed intermediate reasoning enables generalizable prostate cancer prognostication through machine learning in limited settings"],"prefix":"10.1038","volume":"9","author":[{"given":"Jun","family":"Akatsuka","sequence":"first","affiliation":[]},{"given":"Kotaro","family":"Tsutsumi","sequence":"additional","affiliation":[]},{"given":"Mami","family":"Takadate","sequence":"additional","affiliation":[]},{"given":"Yasushi","family":"Numata","sequence":"additional","affiliation":[]},{"given":"Hiromu","family":"Morikawa","sequence":"additional","affiliation":[]},{"given":"Atsushi","family":"Marugame","sequence":"additional","affiliation":[]},{"given":"Hayato","family":"Takeda","sequence":"additional","affiliation":[]},{"given":"Yuki","family":"Endo","sequence":"additional","affiliation":[]},{"given":"Yuka","family":"Toyama","sequence":"additional","affiliation":[]},{"given":"Takayuki","family":"Takahashi","sequence":"additional","affiliation":[]},{"given":"Kaori","family":"Ono","sequence":"additional","affiliation":[]},{"given":"Junya","family":"Iwazaki","sequence":"additional","affiliation":[]},{"given":"Ryuji","family":"Ohashi","sequence":"additional","affiliation":[]},{"given":"Akira","family":"Shimizu","sequence":"additional","affiliation":[]},{"given":"Tomoharu","family":"Kiyuna","sequence":"additional","affiliation":[]},{"given":"Maki","family":"Ogura","sequence":"additional","affiliation":[]},{"given":"Masao","family":"Ueki","sequence":"additional","affiliation":[]},{"given":"Takuma","family":"Kato","sequence":"additional","affiliation":[]},{"given":"Toshiyuki","family":"China","sequence":"additional","affiliation":[]},{"given":"Mikio","family":"Sugimoto","sequence":"additional","affiliation":[]},{"given":"Hisamitsu","family":"Ide","sequence":"additional","affiliation":[]},{"given":"Naoto","family":"Sassa","sequence":"additional","affiliation":[]},{"given":"Naonori","family":"Ueda","sequence":"additional","affiliation":[]},{"given":"Shigeo","family":"Horie","sequence":"additional","affiliation":[]},{"given":"Toyonori","family":"Tsuzuki","sequence":"additional","affiliation":[]},{"given":"Go","family":"Kimura","sequence":"additional","affiliation":[]},{"given":"Yukihiro","family":"Kondo","sequence":"additional","affiliation":[]},{"given":"Yoichiro","family":"Yamamoto","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,12,3]]},"reference":[{"key":"2193_CR1","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-022-04951-3","volume":"12","author":"J Akatsuka","year":"2022","unstructured":"Akatsuka, J. et al. A data-driven ultrasound approach discriminates pathological high-grade prostate cancer. Sci. Rep. 12, 860 (2022).","journal-title":"Sci. Rep."},{"key":"2193_CR2","doi-asserted-by":"publisher","first-page":"115","DOI":"10.1038\/nature21056","volume":"542","author":"A Esteva","year":"2017","unstructured":"Esteva, A. et al. Dermatologist\u2013level classification of skin cancer with deep neural networks. Nature 542, 115\u2013118 (2017).","journal-title":"Nature"},{"key":"2193_CR3","doi-asserted-by":"publisher","first-page":"2199","DOI":"10.1001\/jama.2017.14585","volume":"318","author":"BE Bejnordi","year":"2017","unstructured":"Bejnordi, B. E. et al. Diagnostic assessment of deep learning algorithms for detection of lymph node metastases in women with breast cancer. JAMA. 318, 2199\u20132210 (2017).","journal-title":"JAMA"},{"key":"2193_CR4","doi-asserted-by":"publisher","first-page":"158","DOI":"10.1038\/s41551-018-0195-0","volume":"2","author":"R Poplin","year":"2018","unstructured":"Poplin, R. et al. Prediction of cardiovascular risk factors from retinal fundus photographs via deep learning. Nat. Biomed. Eng. 2, 158\u2013164 (2018).","journal-title":"Nat. Biomed. Eng."},{"key":"2193_CR5","doi-asserted-by":"publisher","first-page":"154","DOI":"10.1038\/s41591-021-01620-2","volume":"28","author":"W Bulten","year":"2022","unstructured":"Bulten, W. et al. Artificial intelligence for diagnosis and Gleason grading of prostate cancer: the PANDA challenge. Nat. Med. 28, 154\u2013163 (2022).","journal-title":"Nat. Med."},{"key":"2193_CR6","doi-asserted-by":"publisher","first-page":"609","DOI":"10.1038\/s41586-024-07894-z","volume":"634","author":"X Wang","year":"2024","unstructured":"Wang, X. et al. A pathology foundation model for cancer diagnosis and prognosis prediction. Nature 634, 609\u2013616 (2024).","journal-title":"Nature"},{"key":"2193_CR7","doi-asserted-by":"publisher","first-page":"537","DOI":"10.1038\/s41591-024-02856-4","volume":"30","author":"MY Lu","year":"2024","unstructured":"Lu, M. Y. et al. A visual-language foundation model for computational pathology. Nat. Med. 30, 537\u2013547 (2024).","journal-title":"Nat. Med."},{"key":"2193_CR8","doi-asserted-by":"publisher","unstructured":"Wei, J. et al. Emergent abilities of large language models. Preprint at https:\/\/doi.org\/10.48550\/arXiv.2206.07682 (2022).","DOI":"10.48550\/arXiv.2206.07682"},{"key":"2193_CR9","doi-asserted-by":"publisher","unstructured":"Kaplan, J. et al. Scaling laws for neural language models. Preprint at https:\/\/doi.org\/10.48550\/arXiv.2001.08361 (2020).","DOI":"10.48550\/arXiv.2001.08361"},{"key":"2193_CR10","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-019-13647-8","volume":"10","author":"Y Yamamoto","year":"2019","unstructured":"Yamamoto, Y. et al. Automated acquisition of explainable knowledge from unannotated histopathology images. Nat. Commun. 10, 5642 (2019).","journal-title":"Nat. Commun."},{"key":"2193_CR11","doi-asserted-by":"publisher","first-page":"5730","DOI":"10.3390\/molecules27175730","volume":"27","author":"M Sekhoacha","year":"2022","unstructured":"Sekhoacha, M. et al. Prostate Cancer Review: Genetics, Diagnosis, Treatment Options, and Alternative Approaches. Molecules 27, 5730 (2022).","journal-title":"Molecules"},{"key":"2193_CR12","doi-asserted-by":"crossref","first-page":"608","DOI":"10.1016\/j.euf.2017.02.014","volume":"4","author":"P Rajan","year":"2018","unstructured":"Rajan, P. et al. Oncologic outcomes after robot-assisted radical prostatectomy: A large European single-centre cohort with median 10-year follow-up. Eur. Urol. Focus 4, 608\u2013616 (2018).","journal-title":"Eur. Urol. Focus"},{"key":"2193_CR13","doi-asserted-by":"publisher","first-page":"141","DOI":"10.1016\/j.eururo.2014.06.025","volume":"67","author":"M Diaz","year":"2015","unstructured":"Diaz, M., Peabody, J. O., Kapoor, V., Sammon, J. & Rogers, C. Oncologic outcomes at 10 years following robotic radical prostatectomy. Eur. Urol. 67, 141\u2013147 (2015).","journal-title":"Eur. Urol."},{"key":"2193_CR14","doi-asserted-by":"publisher","first-page":"724","DOI":"10.1111\/iju.13982","volume":"26","author":"S Garc\u00eda-Barreras","year":"2019","unstructured":"Garc\u00eda-Barreras, S. et al. Biochemical recurrence-free conditional probability after radical prostatectomy: A dynamic prognosis. Int. J. Urol. 26, 724\u2013730 (2019).","journal-title":"Int. J. Urol."},{"key":"2193_CR15","doi-asserted-by":"publisher","first-page":"58","DOI":"10.1016\/S0022-5347(17)59889-4","volume":"111","author":"DF Gleason","year":"1974","unstructured":"Gleason, D. F. & Mellinger, G. T. Prediction of prognosis for prostatic adenocarcinoma by combined histological grading and clinical staging. J. Urol. 111, 58\u201364 (1974).","journal-title":"J. Urol."},{"key":"2193_CR16","doi-asserted-by":"publisher","unstructured":"Zhang, C. et al. A study on overfitting in deep reinforcement learning. Preprint at https:\/\/doi.org\/10.48550\/arXiv.1804.06893 (2018).","DOI":"10.48550\/arXiv.1804.06893"},{"key":"2193_CR17","doi-asserted-by":"publisher","unstructured":"Dosovitskiy, A. et al. An image is worth 16\u00d716 words: Transformers for image recognition at scale. Preprint at https:\/\/doi.org\/10.48550\/arXiv.2010.11929 (2020).","DOI":"10.48550\/arXiv.2010.11929"},{"key":"2193_CR18","first-page":"1228","volume":"44","author":"GJLH Van Leenders","year":"2020","unstructured":"Van Leenders, G. J. L. H. et al. The 2019 International Society of Urological Pathology (ISUP) consensus conference on grading of prostatic carcinoma. Am. J. Surg. Pathol. 44, 1228\u20131238 (2020).","journal-title":"Am. J. Surg. Pathol."},{"key":"2193_CR19","doi-asserted-by":"publisher","first-page":"231","DOI":"10.1016\/j.euf.2019.06.004","volume":"6","author":"T Van den Broeck","year":"2020","unstructured":"Van den Broeck, T. et al. Biochemical recurrence in prostate cancer: The European Association of Urology Prostate Cancer Guidelines Panel recommendations. Eur. Urol. Focus 6, 231\u2013234 (2020).","journal-title":"Eur. Urol. Focus"},{"key":"2193_CR20","doi-asserted-by":"publisher","first-page":"766","DOI":"10.1093\/jnci\/90.10.766","volume":"90","author":"MW Kattan","year":"1998","unstructured":"Kattan, M. W. et al. A preoperative nomogram for disease recurrence following radical prostatectomy for prostate cancer. J. Natl. Cancer Inst. 90, 766\u2013771 (1998).","journal-title":"J. Natl. Cancer Inst."},{"key":"2193_CR21","unstructured":"Memorial Sloan Kettering Cancer Center. Dynamic prostate cancer nomogram: coefficients. https:\/\/www.mskcc.org\/nomograms\/prostate\/pre_op\/coefficients (2025)."},{"key":"2193_CR22","doi-asserted-by":"publisher","first-page":"194","DOI":"10.1007\/s12630-009-9041-x","volume":"56","author":"KJM Janssen","year":"2009","unstructured":"Janssen, K. J. M. et al. A simple method to adjust clinical prediction models to local circumstances. Can. J. Anesth. 56, 194\u2013201 (2009).","journal-title":"Can. J. Anesth."}],"container-title":["npj Digital Medicine"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41746-025-02193-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41746-025-02193-x","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41746-025-02193-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,7]],"date-time":"2026-01-07T14:54:24Z","timestamp":1767797664000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41746-025-02193-x"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,3]]},"references-count":22,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,12]]}},"alternative-id":["2193"],"URL":"https:\/\/doi.org\/10.1038\/s41746-025-02193-x","relation":{},"ISSN":["2398-6352"],"issn-type":[{"value":"2398-6352","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,12,3]]},"assertion":[{"value":"26 June 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"18 November 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"3 December 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"Tomoharu Kiyuna and Maki Ogura are employees of the NEC Corporation. Yukihiro Kondo received research support from NEC Corporation for this study. All other authors declare no competing interests.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"19"}}