{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,17]],"date-time":"2026-06-17T07:52:39Z","timestamp":1781682759110,"version":"3.54.5"},"reference-count":86,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,5,11]],"date-time":"2026-05-11T00:00:00Z","timestamp":1778457600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,5,11]],"date-time":"2026-05-11T00:00:00Z","timestamp":1778457600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100000780","name":"European Union","doi-asserted-by":"crossref","award":["CERTAINTY"],"award-info":[{"award-number":["CERTAINTY"]}],"id":[{"id":"10.13039\/501100000780","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100000780","name":"European Union","doi-asserted-by":"crossref","award":["CERTAINTY"],"award-info":[{"award-number":["CERTAINTY"]}],"id":[{"id":"10.13039\/501100000780","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100000780","name":"European Union","doi-asserted-by":"crossref","award":["CERTAINTY"],"award-info":[{"award-number":["CERTAINTY"]}],"id":[{"id":"10.13039\/501100000780","id-type":"DOI","asserted-by":"crossref"}]},{"name":"S\u00e4chsisches Staatsministerium f\u00fcr Wissenschaft, Kultur und Tourismus","award":["ScaDS.AI"],"award-info":[{"award-number":["ScaDS.AI"]}]},{"name":"S\u00e4chsisches Staatsministerium f\u00fcr Wissenschaft, Kultur und Tourismus","award":["ScaDS.AI"],"award-info":[{"award-number":["ScaDS.AI"]}]},{"DOI":"10.13039\/100018857","name":"International Myeloma Society","doi-asserted-by":"publisher","award":["IMS Research Grant 2023"],"award-info":[{"award-number":["IMS Research Grant 2023"]}],"id":[{"id":"10.13039\/100018857","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100018857","name":"International Myeloma Society","doi-asserted-by":"publisher","award":["IMS Research Grant 2023"],"award-info":[{"award-number":["IMS Research Grant 2023"]}],"id":[{"id":"10.13039\/100018857","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001659","name":"German Research Foundation","doi-asserted-by":"crossref","award":["SPP \u00b5bone"],"award-info":[{"award-number":["SPP \u00b5bone"]}],"id":[{"id":"10.13039\/501100001659","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["npj Digit. Med."],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Risk stratification is an important tool in clinical decision-making, yet current approaches often fail to translate sophisticated survival analysis into actionable clinical criteria. We present a novel method for training any neural network architecture on any data modality to identify prognostically distinct patient groups by directly optimizing for survival heterogeneity across patient clusters. We evaluate the method in simulation experiments and demonstrate its utility in practice by applying it to two distinct cancer types: analyzing laboratory parameters from multiple myeloma (MM) patients using the CoMMpass dataset and computed tomography images from non-small cell lung cancer (NSCLC) patients using the Lung1 dataset. Post-hoc explainability analyses uncover clinically meaningful features determining group assignments, which align well with established risk factors in both cases. Our findings in MM were externally validated using the GMMG-MM5 study dataset, while the NSCLC findings were validated with data from our own institution, thus lending strong weight to the method\u2019s utility. This pan-cancer, model-agnostic approach enables the discovery of novel prognostic signatures across diverse data types while providing interpretable results that promise to complement treatment personalization and clinical decision-making in oncology and beyond.<\/jats:p>","DOI":"10.1038\/s41746-026-02663-w","type":"journal-article","created":{"date-parts":[[2026,5,11]],"date-time":"2026-05-11T08:17:42Z","timestamp":1778487462000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Unsupervised risk factor identification across cancer types and data modalities via explainable artificial intelligence"],"prefix":"10.1038","volume":"9","author":[{"given":"Maximilian","family":"Ferle","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jonas","family":"Ader","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Thomas","family":"Wiemers","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nora","family":"Grieb","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Beatrice","family":"Berneck","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Adrian","family":"Lindenmeyer","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hartmut","family":"Goldschmidt","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Elias K.","family":"Mai","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Uta","family":"Bertsch","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hans-Jonas","family":"Meyer","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Thomas","family":"Neumuth","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Markus","family":"Kreuz","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kristin","family":"Reiche","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Maximilian","family":"Merz","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,5,11]]},"reference":[{"key":"2663_CR1","doi-asserted-by":"publisher","first-page":"232","DOI":"10.1038\/sj.bjc.6601118","volume":"89","author":"TG Clark","year":"2003","unstructured":"Clark, T. G., Bradburn, M. J., Love, S. B. & Altman, D. G. Survival analysis part i: basic concepts and first analyses. Br. J. Cancer 89, 232\u2013238 (2003).","journal-title":"Br. J. Cancer"},{"key":"2663_CR2","doi-asserted-by":"crossref","unstructured":"Harrell, F. E.Cox Proportional Hazards Regression Model, 465-507 (Springer New York, 2001). http:\/\/link.springer.com\/10.1007\/978-1-4757-3462-1_19.Series Title: Springer Series in Statistics.","DOI":"10.1007\/978-1-4757-3462-1_19"},{"key":"2663_CR3","doi-asserted-by":"crossref","unstructured":"Ishwaran, H., Kogalur, U. B., Blackstone, E. H. & Lauer, M. S. Random survival forests. Ann. Appl. Stat.2 (2008). https:\/\/projecteuclid.org\/journals\/annals-of-applied-statistics\/volume-2\/issue-3\/Random-survival-forests\/10.1214\/08-AOAS169.full.","DOI":"10.1214\/08-AOAS169"},{"key":"2663_CR4","doi-asserted-by":"publisher","first-page":"36308","DOI":"10.18632\/oncotarget.6121","volume":"6","author":"KH Eng","year":"2015","unstructured":"Eng, K. H., Schiller, E. & Morrell, K. On representing the prognostic value of continuous gene expression biomarkers with the restricted mean survival curve. Oncotarget 6, 36308\u201336318 (2015).","journal-title":"Oncotarget"},{"key":"2663_CR5","doi-asserted-by":"publisher","DOI":"10.1186\/s12911-023-02293-2","volume":"23","author":"Y Wang","year":"2023","unstructured":"Wang, Y. et al. A comparison of random survival forest and cox regression for prediction of mortality in patients with hemorrhagic stroke. BMC Med Inf. Decis. Mak. 23, 215 (2023).","journal-title":"BMC Med Inf. Decis. Mak."},{"key":"2663_CR6","doi-asserted-by":"publisher","first-page":"31","DOI":"10.1186\/s40708-023-00211-w","volume":"10","author":"A Sarica","year":"2023","unstructured":"Sarica, A. et al. Explainability of random survival forests in predicting conversion risk from mild cognitive impairment to alzheimer\u2019s disease. Brain Inf. 10, 31 (2023).","journal-title":"Brain Inf."},{"key":"2663_CR7","doi-asserted-by":"publisher","first-page":"129","DOI":"10.1016\/j.gastha.2021.11.008","volume":"1","author":"H Innes","year":"2022","unstructured":"Innes, H. et al. Competing risk bias in prognostic models predicting hepatocellular carcinoma occurrence: Impact on clinical decision-making. Gastro Hep Adv. 1, 129\u2013136 (2022).","journal-title":"Gastro Hep Adv."},{"key":"2663_CR8","doi-asserted-by":"publisher","first-page":"333","DOI":"10.1080\/10543406.2017.1377730","volume":"28","author":"C Hu","year":"2018","unstructured":"Hu, C. & Steingrimsson, J. A. Personalized risk prediction in clinical oncology research: Applications and practical issues using survival trees and random forests. J. Biopharm. Stat. 28, 333\u2013349 (2018).","journal-title":"J. Biopharm. Stat."},{"key":"2663_CR9","doi-asserted-by":"crossref","unstructured":"Ahmed, M. I. et al. A systematic review of the barriers to the implementation of artificial intelligence in healthcare. Cureus (2023). https:\/\/www.cureus.com\/articles\/170025-a-systematic-review-of-the-barriers-to-the-implementation-of-artificial-intelligence-in-healthcare.","DOI":"10.7759\/cureus.46454"},{"key":"2663_CR10","doi-asserted-by":"publisher","first-page":"2863","DOI":"10.1200\/JCO.2015.61.2267","volume":"33","author":"A Palumbo","year":"2015","unstructured":"Palumbo, A. et al. Revised international staging system for multiple myeloma: A report from international myeloma working group. JCO 33, 2863\u20132869 (2015).","journal-title":"JCO"},{"key":"2663_CR11","doi-asserted-by":"publisher","first-page":"511","DOI":"10.1016\/j.clml.2016.06.001","volume":"16","author":"VH Jimenez-Zepeda","year":"2016","unstructured":"Jimenez-Zepeda, V. H. et al. Revised international staging system applied to real world multiple myeloma patients. Clin. Lymphoma Myeloma Leuk. 16, 511\u2013518 (2016).","journal-title":"Clin. Lymphoma Myeloma Leuk."},{"key":"2663_CR12","doi-asserted-by":"publisher","first-page":"65","DOI":"10.1007\/s10462-023-10681-3","volume":"57","author":"S Wiegrebe","year":"2024","unstructured":"Wiegrebe, S., Kopper, P., Sonabend, R., Bischl, B. & Bender, A. Deep learning for survival analysis: a review. Artif. Intell. Rev. 57, 65 (2024).","journal-title":"Artif. Intell. Rev."},{"key":"2663_CR13","doi-asserted-by":"publisher","unstructured":"Chapfuwa, P., Li, C., Mehta, N., Carin, L. & Henao, R. Survival cluster analysis. In Proceedings of the ACM Conference on Health, Inference, and Learning, 60\u201368 (ACM, 2020). https:\/\/doi.org\/10.1145\/3368555.3384465.","DOI":"10.1145\/3368555.3384465"},{"key":"2663_CR14","unstructured":"Manduchi, L. et al. A deep variational approach to clustering survival data35 p. (2022). http:\/\/hdl.handle.net\/20.500.11850\/536597.Artwork Size: 35 p. Medium: application\/pdf Publisher: ETH Zurich."},{"key":"2663_CR15","doi-asserted-by":"crossref","unstructured":"You, L., Ferrat, L., Parikh, H., Huo, Y. & Yang, Y. SurvivalClusteringTree: Clustering analysis using survival tree and forest algorithms (2023). https:\/\/CRAN.R-project.org\/package=SurvivalClusteringTree.Institution: Comprehensive R Archive Network Pages: 1.1.1.","DOI":"10.32614\/CRAN.package.SurvivalClusteringTree"},{"key":"2663_CR16","first-page":"92","volume":"174","author":"V Jeanselme","year":"2022","unstructured":"Jeanselme, V., Tom, B. & Barrett, J. Neural survival clustering: Non-parametric mixture of neural networks for survival clustering. Proc. Mach. Learn Res 174, 92\u2013102 (2022).","journal-title":"Proc. Mach. Learn Res"},{"key":"2663_CR17","unstructured":"Buginga, G. & Silva, E. d. S. e. Clustering survival data using a mixture of non-parametric experts (2024). http:\/\/arxiv.org\/abs\/2405.15934."},{"key":"2663_CR18","unstructured":"Mouli, S. C., Teixeira, L., Neville, J. & Ribeiro, B. Deep lifetime clustering (2019). http:\/\/arxiv.org\/abs\/1910.00547."},{"key":"2663_CR19","doi-asserted-by":"publisher","first-page":"3558","DOI":"10.1093\/bioinformatics\/btx464","volume":"33","author":"A Ahmad","year":"2017","unstructured":"Ahmad, A. & Fr\u00f6hlich, H. Towards clinically more relevant dissection of patient heterogeneity via survival-based bayesian clustering. Bioinformatics 33, 3558\u20133566 (2017).","journal-title":"Bioinformatics"},{"key":"2663_CR20","doi-asserted-by":"publisher","DOI":"10.1093\/gigascience\/giz134","volume":"8","author":"J De Jong","year":"2019","unstructured":"De Jong, J. et al. Deep learning for clustering of multivariate clinical patient trajectories with missing values. GigaScience 8, giz134 (2019).","journal-title":"GigaScience"},{"key":"2663_CR21","doi-asserted-by":"publisher","first-page":"102302","DOI":"10.1016\/j.compmedimag.2023.102302","volume":"110","author":"Z Tang","year":"2023","unstructured":"Tang, Z. et al. Explainable survival analysis with uncertainty using convolution-involved vision transformer. Computerized Med. Imaging Graph. 110, 102302 (2023).","journal-title":"Computerized Med. Imaging Graph."},{"key":"2663_CR22","doi-asserted-by":"publisher","first-page":"2233","DOI":"10.1007\/s00345-023-04489-7","volume":"41","author":"F Wessels","year":"2023","unstructured":"Wessels, F. et al. A self-supervised vision transformer to predict survival from histopathology in renal cell carcinoma. World J. Urol. 41, 2233\u20132241 (2023).","journal-title":"World J. Urol."},{"key":"2663_CR23","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-025-56625-z","volume":"16","author":"J Qiu","year":"2025","unstructured":"Qiu, J. et al. Deep representation learning for clustering longitudinal survival data from electronic health records. Nat. Commun. 16, 2534 (2025).","journal-title":"Nat. Commun."},{"key":"2663_CR24","unstructured":"Paszke, A. et al. PyTorch: An imperative style, high-performance deep learning library (2019). http:\/\/arxiv.org\/abs\/1912.01703."},{"key":"2663_CR25","doi-asserted-by":"publisher","first-page":"e33","DOI":"10.1002\/hem3.33","volume":"8","author":"H Cho","year":"2024","unstructured":"Cho, H. et al. Evaluation of the r2-ISS in real-world patients with newly diagnosed multiple myeloma: A nationwide cohort study by the korean multiple myeloma working party (KMM 2202). HemaSphere 8, e33 (2024).","journal-title":"HemaSphere"},{"key":"2663_CR26","doi-asserted-by":"publisher","DOI":"10.1038\/s41408-025-01268-y","volume":"15","author":"C Brieghel","year":"2025","unstructured":"Brieghel, C. et al. A real-world international staging system (RW-ISS) for patients with newly diagnosed multiple myeloma. Blood Cancer J. 15, 59 (2025).","journal-title":"Blood Cancer J."},{"key":"2663_CR27","doi-asserted-by":"publisher","first-page":"1721","DOI":"10.1038\/leu.2015.80","volume":"29","author":"EK Mai","year":"2015","unstructured":"Mai, E. K. et al. Phase III trial of bortezomib, cyclophosphamide and dexamethasone (VCD) versus bortezomib, doxorubicin and dexamethasone (PAd) in newly diagnosed myeloma. Leukemia 29, 1721\u20131729 (2015).","journal-title":"Leukemia"},{"key":"2663_CR28","doi-asserted-by":"crossref","unstructured":"Simon, N., Friedman, J., Hastie, T. & Tibshirani, R. Regularization paths for cox\u2019s proportional hazards model via coordinate descent. J. Stat. Soft. 39 (2011). http:\/\/www.jstatsoft.org\/v39\/i05\/.","DOI":"10.18637\/jss.v039.i05"},{"key":"2663_CR29","doi-asserted-by":"crossref","unstructured":"Akiba, T., Sano, S., Yanase, T., Ohta, T. & Koyama, M. Optuna: A next-generation hyperparameter optimization framework. In Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (2019).","DOI":"10.1145\/3292500.3330701"},{"key":"2663_CR30","doi-asserted-by":"publisher","first-page":"132","DOI":"10.6004\/jnccn.2025.0023","volume":"23","author":"SK Kumar","year":"2025","unstructured":"Kumar, S. K. et al. NCCN guidelines\u00ae insights: Multiple myeloma, version 1.2025: Featured updates to the NCCN guidelines\u24c7. J. Natl. Compr. Cancer Netw. 23, 132\u2013140 (2025).","journal-title":"J. Natl. Compr. Cancer Netw."},{"key":"2663_CR31","unstructured":"Aerts, H. J. W. L. et al. Data from NSCLC-radiomics (2019). https:\/\/www.cancerimagingarchive.net\/collection\/nsclc-radiomics\/."},{"key":"2663_CR32","doi-asserted-by":"publisher","DOI":"10.1038\/ncomms5006","volume":"5","author":"HJWL Aerts","year":"2014","unstructured":"Aerts, H. J. W. L. et al. Decoding tumour phenotype by noninvasive imaging using a quantitative radiomics approach. Nat. Commun. 5, 4006 (2014).","journal-title":"Nat. Commun."},{"key":"2663_CR33","doi-asserted-by":"publisher","first-page":"48","DOI":"10.1016\/j.acra.2009.07.016","volume":"17","author":"GR Washko","year":"2010","unstructured":"Washko, G. R. et al. Identification of early interstitial lung disease in smokers from the COPDGene study. Academic Radiol. 17, 48\u201353 (2010).","journal-title":"Academic Radiol."},{"key":"2663_CR34","doi-asserted-by":"publisher","first-page":"2249","DOI":"10.2147\/OTT.S114960","volume":"ume 10","author":"J Ma","year":"2017","unstructured":"Ma, J. et al. Relationship between computed tomography morphology and prognosis of patients with stage i non-small cell lung cancer. OTT ume 10, 2249\u20132256 (2017).","journal-title":"OTT"},{"key":"2663_CR35","doi-asserted-by":"publisher","first-page":"489","DOI":"10.1148\/radiol.2019182466","volume":"292","author":"T Iwasawa","year":"2019","unstructured":"Iwasawa, T. et al. Computer-aided quantification of pulmonary fibrosis in patients with lung cancer: Relationship to disease-free survival. Radiology 292, 489\u2013498 (2019).","journal-title":"Radiology"},{"key":"2663_CR36","doi-asserted-by":"publisher","first-page":"1902154","DOI":"10.1183\/13993003.02154-2019","volume":"56","author":"GT Axelsson","year":"2020","unstructured":"Axelsson, G. T. et al. The associations of interstitial lung abnormalities with cancer diagnoses and mortality. Eur. Respir. J. 56, 1902154 (2020).","journal-title":"Eur. Respir. J."},{"key":"2663_CR37","doi-asserted-by":"publisher","first-page":"484","DOI":"10.1007\/s11897-023-00635-9","volume":"20","author":"MM Hell","year":"2023","unstructured":"Hell, M. M., Emrich, T., Lurz, P., Von Bardeleben, R. S. & Schmermund, A. Cardiac CT beyond coronaries: Focus on structural heart disease. Curr. Heart Fail Rep. 20, 484\u2013492 (2023).","journal-title":"Curr. Heart Fail Rep."},{"key":"2663_CR38","doi-asserted-by":"publisher","first-page":"380","DOI":"10.1007\/s11547-024-01771-5","volume":"129","author":"G Cundari","year":"2024","unstructured":"Cundari, G. et al. Imaging biomarkers in cardiac CT: moving beyond simple coronary anatomical assessment. Radio. med 129, 380\u2013400 (2024).","journal-title":"Radio. med"},{"key":"2663_CR39","doi-asserted-by":"publisher","first-page":"1258991","DOI":"10.3389\/fonc.2024.1258991","volume":"14","author":"M De Jesus","year":"2024","unstructured":"De Jesus, M., Chanda, A., Grabauskas, T., Kumar, M. & Kim, A. S. Cardiovascular disease and lung cancer. Front. Oncol. 14, 1258991 (2024).","journal-title":"Front. Oncol."},{"key":"2663_CR40","doi-asserted-by":"publisher","first-page":"80","DOI":"10.1016\/j.jtho.2023.09.004","volume":"19","author":"S Zhang","year":"2024","unstructured":"Zhang, S. et al. Bidirectional association between cardiovascular disease and lung cancer in a prospective cohort study. J. Thorac. Oncol. 19, 80\u201393 (2024).","journal-title":"J. Thorac. Oncol."},{"key":"2663_CR41","first-page":"325","volume":"7","author":"M El-Rayes","year":"2025","unstructured":"El-Rayes, M. et al. Lung cancer and cardiovascular disease. JACC: CardioOncology 7, 325\u2013344 (2025).","journal-title":"JACC: CardioOncology"},{"key":"2663_CR42","doi-asserted-by":"publisher","first-page":"1124","DOI":"10.3348\/kjr.2018.0070","volume":"20","author":"JE Park","year":"2019","unstructured":"Park, J. E., Park, S. Y., Kim, H. J. & Kim, H. S. Reproducibility and generalizability in radiomics modeling: Possible strategies in radiologic and statistical perspectives. Korean J. Radio. 20, 1124 (2019).","journal-title":"Korean J. Radio."},{"key":"2663_CR43","first-page":"e200068","volume":"2","author":"PO Alderson","year":"2020","unstructured":"Alderson, P. O. The quest for generalizability in radiomics. Radiology: Artif. Intell. 2, e200068 (2020).","journal-title":"Radiology: Artif. Intell."},{"key":"2663_CR44","doi-asserted-by":"crossref","unstructured":"Ofer, D., Linial, M. & Shahaf, D. InterFeat: An automated pipeline for finding interesting hypotheses in structured biomedical data (2025). http:\/\/arxiv.org\/abs\/2505.13534.","DOI":"10.2139\/ssrn.5342565"},{"key":"2663_CR45","doi-asserted-by":"publisher","first-page":"3412","DOI":"10.1200\/JCO.2005.04.242","volume":"23","author":"PR Greipp","year":"2005","unstructured":"Greipp, P. R. et al. International staging system for multiple myeloma. JCO 23, 3412\u20133420 (2005).","journal-title":"JCO"},{"key":"2663_CR46","doi-asserted-by":"publisher","first-page":"e40710","DOI":"10.1097\/MD.0000000000040710","volume":"103","author":"Z Li","year":"2024","unstructured":"Li, Z., Zhao, H., Li, Z. & He, Y. Correlation analysis of laboratory indicators, genetic abnormalities and staging in patients with newly diagnosed multiple myeloma. Medicine 103, e40710 (2024).","journal-title":"Medicine"},{"key":"2663_CR47","doi-asserted-by":"crossref","unstructured":"Benson, R., Nair, S. G. & Narayanan, G. Early normalization of free light chains predicts better outcomes in patients with multiple myeloma. IJHOSCR (2020). https:\/\/18.184.16.47\/index.php\/IJHOSCR\/article\/view\/4475.","DOI":"10.18502\/ijhoscr.v14i4.4475"},{"key":"2663_CR48","doi-asserted-by":"publisher","first-page":"1592","DOI":"10.1093\/jalm\/jfab090","volume":"6","author":"Y Jin","year":"2021","unstructured":"Jin, Y., Savage, N. M., Bollag, R. J., Xu, H. & Singh, G. Light chain multiple myeloma: High serum free light chain concentrations portend renal damage and poorer survival. J. Appl. Lab. Med. 6, 1592\u20131600 (2021).","journal-title":"J. Appl. Lab. Med."},{"key":"2663_CR49","doi-asserted-by":"publisher","first-page":"1229","DOI":"10.1200\/JCO.23.01277","volume":"42","author":"F Maura","year":"2024","unstructured":"Maura, F. et al. Genomic classification and individualized prognosis in multiple myeloma. JCO 42, 1229\u20131240 (2024).","journal-title":"JCO"},{"key":"2663_CR50","doi-asserted-by":"publisher","first-page":"672","DOI":"10.1159\/000520312","volume":"44","author":"M Heider","year":"2021","unstructured":"Heider, M., Nickel, K., H\u00f6gner, M. & Bassermann, F. Multiple myeloma: Molecular pathogenesis and disease evolution. Oncol. Res Treat. 44, 672\u2013681 (2021).","journal-title":"Oncol. Res Treat."},{"key":"2663_CR51","doi-asserted-by":"publisher","first-page":"88","DOI":"10.1186\/s13045-023-01465-x","volume":"16","author":"K Rejeski","year":"2023","unstructured":"Rejeski, K. et al. The CAR-HEMATOTOX score as a prognostic model of toxicity and response in patients receiving BCMA-directed CAR-t for relapsed\/refractory multiple myeloma. J. Hematol. Oncol. 16, 88 (2023).","journal-title":"J. Hematol. Oncol."},{"key":"2663_CR52","doi-asserted-by":"publisher","first-page":"e009220","DOI":"10.1136\/jitc-2024-009220","volume":"12","author":"JH Frenking","year":"2024","unstructured":"Frenking, J. H. et al. EASIX-guided risk stratification for complications and outcome after CAR t-cell therapy with ide-cel in relapsed\/refractory multiple myeloma. J. Immunother. Cancer 12, e009220 (2024).","journal-title":"J. Immunother. Cancer"},{"key":"2663_CR53","doi-asserted-by":"publisher","first-page":"296","DOI":"10.3390\/brainsci14030296","volume":"14","author":"M De Simone","year":"2024","unstructured":"De Simone, M. et al. Clustering functional magnetic resonance imaging time series in glioblastoma characterization: A review of the evolution, applications, and potentials. Brain Sci. 14, 296 (2024).","journal-title":"Brain Sci."},{"key":"2663_CR54","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-025-99000-0","volume":"15","author":"A Espis","year":"2025","unstructured":"Espis, A., Marzi, C. & Diciotti, S. Comparative analysis of supervised and self-supervised learning with small and imbalanced medical imaging datasets. Sci. Rep. 15, 32345 (2025).","journal-title":"Sci. Rep."},{"key":"2663_CR55","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-023-39591-8","volume":"13","author":"J Lee","year":"2023","unstructured":"Lee, J. et al. Clustering-based spatial analysis (CluSA) framework through graph neural network for chronic kidney disease prediction using histopathology images. Sci. Rep. 13, 12701 (2023).","journal-title":"Sci. Rep."},{"key":"2663_CR56","unstructured":"Mackenzie, C. C., Dawood, M., Graham, S., Eastwood, M. & Minhas, F. u. A. A. Neural graph modelling of whole slide images for survival ranking. In Proceedings of the First Learning on Graphs Conference, 48:1\u201348:10 (PMLR, 2022). https:\/\/proceedings.mlr.press\/v198\/mackenzie22a.html."},{"key":"2663_CR57","doi-asserted-by":"crossref","unstructured":"Ghesu, F. C. et al. Contrastive self-supervised learning from 100 million medical images with optional supervision9 (2022). https:\/\/www.spiedigitallibrary.org\/journals\/journal-of-medical-imaging\/volume-9\/issue-06\/064503\/Contrastive-self-supervised-learning-from-100million-medical-images-with-optional\/10.1117\/1.JMI.9.6.064503.full.","DOI":"10.1117\/1.JMI.9.6.064503"},{"key":"2663_CR58","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-025-25037-w","volume":"15","author":"MM Guy","year":"2025","unstructured":"Guy, M. M. et al. Development and validation of the risk stratification based on deep learning and radiomics to predict survival of advanced cervical cancer. Sci. Rep. 15, 41202 (2025).","journal-title":"Sci. Rep."},{"key":"2663_CR59","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-023-50451-3","volume":"14","author":"F Sch\u00f6n","year":"2024","unstructured":"Sch\u00f6n, F. et al. Comparative analysis of radiomics and deep-learning algorithms for survival prediction in hepatocellular carcinoma. Sci. Rep. 14, 590 (2024).","journal-title":"Sci. Rep."},{"key":"2663_CR60","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1515\/ijb-2022-0113","volume":"20","author":"S Morrison","year":"2024","unstructured":"Morrison, S., Gatsonis, C., Eloyan, A. & Steingrimsson, J. A. Survival analysis using deep learning with medical imaging. Int. J. Biostatistics 20, 1\u201312 (2024).","journal-title":"Int. J. Biostatistics"},{"key":"2663_CR61","doi-asserted-by":"publisher","first-page":"2837","DOI":"10.3390\/cancers16162837","volume":"16","author":"F Drakopanagiotakis","year":"2024","unstructured":"Drakopanagiotakis, F. et al. Lung cancer and interstitial lung diseases. Cancers 16, 2837 (2024).","journal-title":"Cancers"},{"key":"2663_CR62","doi-asserted-by":"publisher","DOI":"10.1186\/s40644-021-00383-w","volume":"21","author":"T Hida","year":"2021","unstructured":"Hida, T. et al. Interstitial lung abnormalities in patients with stage i non-small cell lung cancer are associated with shorter overall survival: the boston lung cancer study. Cancer Imaging 21, 14 (2021).","journal-title":"Cancer Imaging"},{"key":"2663_CR63","doi-asserted-by":"publisher","first-page":"1874","DOI":"10.1111\/1759-7714.14935","volume":"14","author":"M Zhu","year":"2023","unstructured":"Zhu, M. et al. Newly diagnosed non-small cell lung cancer with interstitial lung abnormality: Prevalence, characteristics, and prognosis. Thorac. Cancer 14, 1874\u20131882 (2023).","journal-title":"Thorac. Cancer"},{"key":"2663_CR64","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-020-69814-1","volume":"10","author":"SM Waldstein","year":"2020","unstructured":"Waldstein, S. M. et al. Unbiased identification of novel subclinical imaging biomarkers using unsupervised deep learning. Sci. Rep. 10, 12954 (2020).","journal-title":"Sci. Rep."},{"key":"2663_CR65","doi-asserted-by":"publisher","first-page":"354","DOI":"10.1038\/s42256-024-00807-9","volume":"6","author":"S Pai","year":"2024","unstructured":"Pai, S. et al. Foundation model for cancer imaging biomarkers. Nat. Mach. Intell. 6, 354\u2013367 (2024).","journal-title":"Nat. Mach. Intell."},{"key":"2663_CR66","doi-asserted-by":"publisher","first-page":"221","DOI":"10.1146\/annurev-bioeng-071516-044442","volume":"19","author":"D Shen","year":"2017","unstructured":"Shen, D., Wu, G. & Suk, H.-I. Deep learning in medical image analysis. Annu. Rev. Biomed. Eng. 19, 221\u2013248 (2017).","journal-title":"Annu. Rev. Biomed. Eng."},{"key":"2663_CR67","doi-asserted-by":"publisher","first-page":"267","DOI":"10.1007\/BF02289263","volume":"18","author":"RL Thorndike","year":"1953","unstructured":"Thorndike, R. L. Who belongs in the family? Psychometrika 18, 267\u2013276 (1953).","journal-title":"Psychometrika"},{"key":"2663_CR68","doi-asserted-by":"crossref","unstructured":"Teh, Y. W. Dirichlet process. In Sammut, C. & Webb, G. I. (eds.) Encyclopedia of Machine Learning, 280-287 (Springer US, 2011). https:\/\/link.springer.com\/10.1007\/978-0-387-30164-8_219.","DOI":"10.1007\/978-0-387-30164-8_219"},{"key":"2663_CR69","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-025-92500-z","volume":"15","author":"JH Kwon","year":"2025","unstructured":"Kwon, J. H., Jwa, E.-K., Lee, J. W., Tak, E. & Hwang, S. Development and validation of a dynamic prognostic nomogram for conditional survival in hepatocellular carcinoma: an analysis from the korea liver cancer registry. Sci. Rep. 15, 8654 (2025).","journal-title":"Sci. Rep."},{"key":"2663_CR70","doi-asserted-by":"publisher","first-page":"1738","DOI":"10.1093\/brain\/awab108","volume":"144","author":"J De Jong","year":"2021","unstructured":"De Jong, J. et al. Towards realizing the vision of precision medicine: AI based prediction of clinical drug response. Brain 144, 1738\u20131750 (2021).","journal-title":"Brain"},{"key":"2663_CR71","doi-asserted-by":"publisher","first-page":"231","DOI":"10.1038\/s41746-025-01636-9","volume":"8","author":"M Ferle","year":"2025","unstructured":"Ferle, M. et al. Predicting progression events in multiple myeloma from routine blood work. npj Digit. Med. 8, 231 (2025).","journal-title":"npj Digit. Med."},{"key":"2663_CR72","doi-asserted-by":"publisher","first-page":"1853","DOI":"10.1038\/s41375-020-0724-1","volume":"34","author":"H Goldschmidt","year":"2020","unstructured":"Goldschmidt, H. et al. Response-adapted lenalidomide maintenance in newly diagnosed myeloma: results from the phase III GMMG-MM5 trial. Leukemia 34, 1853\u20131865 (2020).","journal-title":"Leukemia"},{"key":"2663_CR73","doi-asserted-by":"publisher","first-page":"3007","DOI":"10.1038\/s41375-021-01298-y","volume":"35","author":"H Salwender","year":"2021","unstructured":"Salwender, H. et al. Long-term follow-up of subcutaneous versus intravenous bortezomib during induction therapy for newly diagnosed multiple myeloma treated within the GMMG-MM5 phase III trial. Leukemia 35, 3007\u20133011 (2021).","journal-title":"Leukemia"},{"key":"2663_CR74","doi-asserted-by":"publisher","first-page":"886","DOI":"10.1016\/j.tranon.2017.08.007","volume":"10","author":"C Shen","year":"2017","unstructured":"Shen, C. et al. 2d and 3d CT radiomics features prognostic performance comparison in non-small cell lung cancer. Transl. Oncol. 10, 886\u2013894 (2017).","journal-title":"Transl. Oncol."},{"key":"2663_CR75","doi-asserted-by":"publisher","first-page":"62","DOI":"10.1109\/TSMC.1979.4310076","volume":"9","author":"N Otsu","year":"1979","unstructured":"Otsu, N. A threshold selection method from gray-level histograms. IEEE Trans. Syst., Man, Cybern. 9, 62\u201366 (1979).","journal-title":"IEEE Trans. Syst., Man, Cybern."},{"key":"2663_CR76","first-page":"163","volume":"50","author":"N Mantel","year":"1966","unstructured":"Mantel, N. Evaluation of survival data and two new rank order statistics arising in its consideration. Cancer Chemother. Rep. 50, 163\u2013170 (1966).","journal-title":"Cancer Chemother. Rep."},{"key":"2663_CR77","doi-asserted-by":"publisher","first-page":"185","DOI":"10.2307\/2344317","volume":"135","author":"R Peto","year":"1972","unstructured":"Peto, R. & Peto, J. Asymptotically efficient rank invariant test procedures. J. R. Stat. Soc. Ser. A (Gen.) 135, 185 (1972).","journal-title":"J. R. Stat. Soc. Ser. A (Gen.)"},{"key":"2663_CR78","unstructured":"Falcon, W. & Team, T. P. L. PyTorch lightning (2023). https:\/\/zenodo.org\/record\/7822836."},{"key":"2663_CR79","unstructured":"Loshchilov, I. & Hutter, F. Decoupled weight decay regularization (2019). http:\/\/arxiv.org\/abs\/1711.05101."},{"key":"2663_CR80","unstructured":"Choi, D. et al. On empirical comparisons of optimizers for deep learning (2020). http:\/\/arxiv.org\/abs\/1910.05446."},{"key":"2663_CR81","doi-asserted-by":"crossref","unstructured":"Efron, B. & Tibshirani, R. J.An introduction to the bootstrap. No. in (Chapman & Hall, 1993).","DOI":"10.1007\/978-1-4899-4541-9"},{"key":"2663_CR82","unstructured":"Davison, A. C. & Hinkley, D. V.Bootstrap methods and their application. Cambridge series in statistical and probabilistic mathematics (Cambridge Univ. Press, 2010), 11. print., [nachdr.] edn."},{"key":"2663_CR83","doi-asserted-by":"crossref","unstructured":"Shapley, L. S. 17. a value for n-person games. In Kuhn, H. W. & Tucker, A. W. (eds.) Contributions to the Theory of Games (AM-28), Volume II, 307-318 (Princeton University Press, 1953). https:\/\/www.degruyter.com\/document\/doi\/10.1515\/9781400881970-018\/html.","DOI":"10.1515\/9781400881970-018"},{"key":"2663_CR84","unstructured":"Shrikumar, A., Greenside, P. & Kundaje, A. Learning important features through propagating activation differences (2019). http:\/\/arxiv.org\/abs\/1704.02685."},{"key":"2663_CR85","doi-asserted-by":"publisher","first-page":"647","DOI":"10.1007\/s10115-013-0679-x","volume":"41","author":"E \u0160trumbelj","year":"2014","unstructured":"\u0160trumbelj, E. & Kononenko, I. Explaining prediction models and individual predictions with feature contributions. Knowl. Inf. Syst. 41, 647\u2013665 (2014).","journal-title":"Knowl. Inf. Syst."},{"key":"2663_CR86","unstructured":"Lundberg, S. & Lee, S.-I. A unified approach to interpreting model predictions (2017). http:\/\/arxiv.org\/abs\/1705.07874."}],"updated-by":[{"DOI":"10.1038\/s41746-026-02833-w","type":"correction","label":"Correction","source":"publisher","updated":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T00:00:00Z","timestamp":1781568000000}}],"container-title":["npj Digital Medicine"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41746-026-02663-w","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41746-026-02663-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41746-026-02663-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,17]],"date-time":"2026-06-17T07:03:56Z","timestamp":1781679836000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41746-026-02663-w"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,11]]},"references-count":86,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,12]]}},"alternative-id":["2663"],"URL":"https:\/\/doi.org\/10.1038\/s41746-026-02663-w","relation":{},"ISSN":["2398-6352"],"issn-type":[{"value":"2398-6352","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5,11]]},"assertion":[{"value":"8 July 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"12 April 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"11 May 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"16 June 2026","order":6,"name":"change_date","label":"Change Date","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"Correction","order":7,"name":"change_type","label":"Change Type","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"A Correction to this paper has been published:","order":8,"name":"change_details","label":"Change Details","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"https:\/\/doi.org\/10.1038\/s41746-026-02833-w","URL":"https:\/\/doi.org\/10.1038\/s41746-026-02833-w","order":9,"name":"change_details","label":"Change Details","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"MM received financial support from and\/or held consulting or advisory roles for SpringWorks Therapeutics Inc., Janssen-Cilag GmbH and Roche Deutschland Holding GmbH. HG received financial support from and\/or held consulting or advisory roles for Janssen-Cilag GmbH, Celgene GmbH, Novartis Pharma GmbH, Onyx Pharmaceuticals Inc, Takeda Pharma Vertrieb GmbH and Roche Deutschland Holding GmbH. EKM received financial support from and\/or held consulting or advisory roles for Amgen GmbH, Bristol Myers Squibb GmbH, GlaxoSmithKline GmbH, Janssen-Cilag GmbH, Oncopeptides GmbH, Pfizer Deutschland GmbH, Sanofi-Aventis Deutschland GmbH, Stemline Therapeutics GmbH and Takeda Pharma Vertrieb GmbH. MF, JA, TW, NG, BB, AL, HJM, TN, MK and KR declare no conflict of interest.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"363"}}