{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,5]],"date-time":"2026-06-05T04:37:51Z","timestamp":1780634271108,"version":"3.54.1"},"reference-count":37,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2025,1,27]],"date-time":"2025-01-27T00:00:00Z","timestamp":1737936000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2025,1,27]],"date-time":"2025-01-27T00:00:00Z","timestamp":1737936000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100001779","name":"Monash University","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100001779","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Mach Learn"],"published-print":{"date-parts":[[2025,2]]},"abstract":"<jats:title>Abstract<\/jats:title>\n          <jats:p>Survival analysis holds a crucial role across diverse disciplines, such as economics, engineering and healthcare. It empowers researchers to analyze both time-invariant and time-varying data, encompassing phenomena like customer churn, material degradation and various medical outcomes. Given the complexity and heterogeneity of such data, recent endeavors have demonstrated successful integration of deep learning methodologies to address limitations in conventional statistical approaches. However, current methods typically involve cluttered probability distribution function (PDF), have lower sensitivity in censoring prediction, only model static datasets, or only rely on recurrent neural networks for dynamic modelling. In this paper, we propose a novel survival regression method capable of producing high-quality unimodal PDFs without any prior distribution assumption, by optimizing novel Margin-Mean-Variance loss and leveraging the flexibility of Transformer to handle both temporal and non-temporal data, coined <jats:bold>UniSurv<\/jats:bold>. Extensive experiments on several datasets demonstrate that UniSurv places a significantly higher emphasis on censoring compared to other methods.<\/jats:p>","DOI":"10.1007\/s10994-024-06686-w","type":"journal-article","created":{"date-parts":[[2025,1,27]],"date-time":"2025-01-27T21:07:10Z","timestamp":1738012030000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["Adaptive transformer modelling of density function for nonparametric survival analysis"],"prefix":"10.1007","volume":"114","author":[{"given":"Xin","family":"Zhang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Deval","family":"Mehta","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yanan","family":"Hu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chao","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"David","family":"Darby","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhen","family":"Yu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Daniel","family":"Merlo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Melissa","family":"Gresle","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Anneke","family":"van der Walt","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Helmut","family":"Butzkueven","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zongyuan","family":"Ge","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,1,27]]},"reference":[{"key":"6686_CR1","doi-asserted-by":"publisher","DOI":"10.1201\/9781003282525","volume-title":"Modelling survival data in medical research","author":"D Collett","year":"2023","unstructured":"Collett, D. (2023). Modelling survival data in medical research. Boca Raton: CRC Press."},{"issue":"2","key":"6686_CR2","doi-asserted-by":"publisher","first-page":"187","DOI":"10.1111\/j.2517-6161.1972.tb00899.x","volume":"34","author":"DR Cox","year":"1972","unstructured":"Cox, D. R. (1972). Regression models and life-tables. Journal of the Royal Statistical Society: Series B (Methodological), 34(2), 187\u2013202.","journal-title":"Journal of the Royal Statistical Society: Series B (Methodological)"},{"issue":"7403","key":"6686_CR3","doi-asserted-by":"publisher","first-page":"346","DOI":"10.1038\/nature10983","volume":"486","author":"C Curtis","year":"2012","unstructured":"Curtis, C., Shah, S. P., Chin, S. F., et al. (2012). The genomic and transcriptomic architecture of 2,000 breast tumours reveals novel subgroups. Nature, 486(7403), 346\u2013352.","journal-title":"Nature"},{"key":"6686_CR4","doi-asserted-by":"publisher","unstructured":"Davidson-Pilon, C. (2019). Lifelines: Survival analysis in python. Journal of Open Source Software 4(40):1317. https:\/\/doi.org\/10.21105\/joss.01317.","DOI":"10.21105\/joss.01317"},{"issue":"1","key":"6686_CR5","doi-asserted-by":"publisher","first-page":"73","DOI":"10.1002\/sim.4780140108","volume":"14","author":"D Faraggi","year":"1995","unstructured":"Faraggi, D., & Simon, R. (1995). A neural network model for survival data. Statistics in Medicine, 14(1), 73\u201382.","journal-title":"Statistics in Medicine"},{"key":"6686_CR6","doi-asserted-by":"crossref","unstructured":"Foong, Y. C., Bridge, F., & Merlo, D., et\u00a0al. (2023). Smartphone monitoring of cognition in people with multiple sclerosis: A systematic review. Multiple Sclerosis and Related Disorders 104674.","DOI":"10.1016\/j.msard.2023.104674"},{"key":"6686_CR7","doi-asserted-by":"publisher","first-page":"1","DOI":"10.18637\/jss.v031.i07","volume":"31","author":"T Giorgino","year":"2009","unstructured":"Giorgino, T. (2009). Computing and visualizing dynamic time warping alignments in r: The dtw package. Journal of Statistical Software, 31, 1\u201324.","journal-title":"Journal of Statistical Software"},{"issue":"1","key":"6686_CR8","first-page":"3289","volume":"21","author":"H Haider","year":"2020","unstructured":"Haider, H., Hoehn, B., Davis, S., et al. (2020). Effective ways to build and evaluate individual survival distributions. The Journal of Machine Learning Research, 21(1), 3289\u20133351.","journal-title":"The Journal of Machine Learning Research"},{"key":"6686_CR9","first-page":"132","volume-title":"Survival Prediction-Algorithms","author":"S Hu","year":"2021","unstructured":"Hu, S., Fridgeirsson, E., van Wingen, G., et al. (2021). Transformer-based deep survival analysis. Survival Prediction-Algorithms (pp. 132\u2013148). PMLR: Challenges and Applications."},{"issue":"2","key":"6686_CR10","doi-asserted-by":"publisher","first-page":"803","DOI":"10.1007\/s40120-021-00262-3","volume":"10","author":"SF Hunter","year":"2021","unstructured":"Hunter, S. F., Aburashed, R. A., Alroughani, R., et al. (2021). Confirmed 6-month disability improvement and worsening correlate with long-term disability outcomes in alemtuzumab-treated patients with multiple sclerosis: Post hoc analysis of the care-ms studies. Neurology and Therapy, 10(2), 803\u2013818.","journal-title":"Neurology and Therapy"},{"issue":"3","key":"6686_CR11","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., et al. (2008). Random survival forests. The Annals of Applied Statistics, 2(3), 841\u2013860.","journal-title":"The Annals of Applied Statistics"},{"issue":"282","key":"6686_CR12","doi-asserted-by":"publisher","first-page":"457","DOI":"10.1080\/01621459.1958.10501452","volume":"53","author":"EL Kaplan","year":"1958","unstructured":"Kaplan, E. L., & Meier, P. (1958). Nonparametric estimation from incomplete observations. Journal of the American Statistical Association, 53(282), 457\u2013481.","journal-title":"Journal of the American Statistical Association"},{"issue":"1","key":"6686_CR13","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s12874-018-0482-1","volume":"18","author":"JL Katzman","year":"2018","unstructured":"Katzman, J. L., Shaham, U., Cloninger, A., et al. (2018). Deepsurv: Personalized treatment recommender system using a cox proportional hazards deep neural network. BMC Medical Research Methodology, 18(1), 1\u201312.","journal-title":"BMC Medical Research Methodology"},{"issue":"3","key":"6686_CR14","doi-asserted-by":"publisher","first-page":"191","DOI":"10.7326\/0003-4819-122-3-199502010-00007","volume":"122","author":"WA Knaus","year":"1995","unstructured":"Knaus, W. A., Harrell, F. E., Lynn, J., et al. (1995). The support prognostic model: Objective estimates of survival for seriously ill hospitalized adults. Annals of Internal Medicine, 122(3), 191\u2013203.","journal-title":"Annals of Internal Medicine"},{"key":"6686_CR15","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2022.110234","volume":"262","author":"M Krzyzi\u0144ski","year":"2023","unstructured":"Krzyzi\u0144ski, M., Spytek, M., Baniecki, H., et al. (2023). Survshap (t): Time-dependent explanations of machine learning survival models. Knowledge-Based Systems, 262, 110234.","journal-title":"Knowledge-Based Systems"},{"issue":"5","key":"6686_CR16","doi-asserted-by":"publisher","first-page":"2088","DOI":"10.1177\/0962280213515571","volume":"25","author":"J Lambert","year":"2016","unstructured":"Lambert, J., & Chevret, S. (2016). Summary measure of discrimination in survival models based on cumulative\/dynamic time-dependent ROC curves. Statistical Methods in Medical Research, 25(5), 2088\u20132102.","journal-title":"Statistical Methods in Medical Research"},{"key":"6686_CR17","doi-asserted-by":"crossref","unstructured":"Lee, C., Zame, W., & Yoon, J., et\u00a0al. (2018). Deephit: A deep learning approach to survival analysis with competing risks. In Proceedings of the AAAI conference on artificial intelligence.","DOI":"10.1609\/aaai.v32i1.11842"},{"issue":"1","key":"6686_CR18","doi-asserted-by":"publisher","first-page":"122","DOI":"10.1109\/TBME.2019.2909027","volume":"67","author":"C Lee","year":"2019","unstructured":"Lee, C., Yoon, J., & Van Der Schaar, M. (2019). Dynamic-deephit: A deep learning approach for dynamic survival analysis with competing risks based on longitudinal data. IEEE Transactions on Biomedical Engineering, 67(1), 122\u2013133.","journal-title":"IEEE Transactions on Biomedical Engineering"},{"issue":"1","key":"6686_CR19","first-page":"501","volume":"21","author":"MLT Lee","year":"2006","unstructured":"Lee, M. L. T., & Whitmore, G. (2006). Threshold regression for survival analysis: Modeling event times by a stochastic process reaching a boundary. Statistical Science, 21(1), 501\u2013513.","journal-title":"Statistical Science"},{"issue":"1","key":"6686_CR20","doi-asserted-by":"publisher","first-page":"83","DOI":"10.1146\/annurev.publhealth.18.1.83","volume":"18","author":"KM Leung","year":"1997","unstructured":"Leung, K. M., Elashoff, R. M., & Afifi, A. A. (1997). Censoring issues in survival analysis. Annual Review of Public Health, 18(1), 83\u2013104.","journal-title":"Annual Review of Public Health"},{"key":"6686_CR21","unstructured":"Luck, M., Sylvain, T., & Cardinal, H., et\u00a0al. (2017). Deep learning for patient-specific kidney graft survival analysis. arXiv preprint arXiv:1705.10245."},{"issue":"20","key":"6686_CR22","doi-asserted-by":"publisher","first-page":"e2020","DOI":"10.1212\/WNL.0000000000012850","volume":"97","author":"D Merlo","year":"2021","unstructured":"Merlo, D., Stankovich, J., Bai, C., et al. (2021). Association between cognitive trajectories and disability progression in patients with relapsing-remitting multiple sclerosis. Neurology, 97(20), e2020\u2013e2031.","journal-title":"Neurology"},{"key":"6686_CR23","first-page":"184","volume-title":"Survival Prediction-Algorithms","author":"C Nagpal","year":"2021","unstructured":"Nagpal, C., Jeanselme, V., & Dubrawski, A. (2021). a) Deep parametric time-to-event regression with time-varying covariates. Survival Prediction-Algorithms (pp. 184\u2013193). PMLR: Challenges and Applications."},{"issue":"8","key":"6686_CR24","doi-asserted-by":"publisher","first-page":"3163","DOI":"10.1109\/JBHI.2021.3052441","volume":"25","author":"C Nagpal","year":"2021","unstructured":"Nagpal, C., Li, X., & Dubrawski, A. (2021). Deep survival machines: Fully parametric survival regression and representation learning for censored data with competing risks. IEEE Journal of Biomedical and Health Informatics, 25(8), 3163\u20133175.","journal-title":"IEEE Journal of Biomedical and Health Informatics"},{"key":"6686_CR25","unstructured":"Nagpal, C., Yadlowsky, S., & Rostamzadeh, N., et\u00a0al. (2021c). Deep cox mixtures for survival regression. In Machine learning for healthcare conference, PMLR (pp. 674\u2013708)."},{"key":"6686_CR26","doi-asserted-by":"crossref","unstructured":"Pan, H., Han, H., & Shan, S., et\u00a0al. (2018). Mean-variance loss for deep age estimation from a face. In Proceedings of the IEEE conference on computer vision and pattern recognition (pp. 5285\u20135294).","DOI":"10.1109\/CVPR.2018.00554"},{"issue":"1","key":"6686_CR27","doi-asserted-by":"publisher","first-page":"36","DOI":"10.1038\/s41746-021-00401-y","volume":"4","author":"L Pham","year":"2021","unstructured":"Pham, L., Harris, T., Varosanec, M., et al. (2021). Smartphone-based symbol-digit modalities test reliably captures brain damage in multiple sclerosis. NPJ Digital Medicine, 4(1), 36.","journal-title":"NPJ Digital Medicine"},{"key":"6686_CR28","doi-asserted-by":"crossref","unstructured":"Pieszko, K., Shanbhag, A. D., & Singh, A., et\u00a0al. (2023). Time and event-specific deep learning for personalized risk assessment after cardiac perfusion imaging. npj Digital Medicine 6(1), 78.","DOI":"10.1038\/s41746-023-00806-x"},{"key":"6686_CR29","unstructured":"P\u00f6lsterl, S. (2020). scikit-survival: A library for time-to-event analysis built on top of scikit-learn. Journal of Machine Learning Research 21(212), 1\u20136."},{"key":"6686_CR30","unstructured":"Pourjafari, E., Ziaei, N., & Rezaei, M. R., et\u00a0al. (2022). Survival seq2seq: A survival model based on sequence to sequence architecture. In Machine learning for healthcare conference, PMLR (pp. 79\u2013100)."},{"key":"6686_CR31","unstructured":"Rindt, D., Hu, R., & Steinsaltz, D., et\u00a0al. (2022). Survival regression with proper scoring rules and monotonic neural networks. In International conference on artificial intelligence and statistics PMLR (pp. 1190\u20131205)."},{"key":"6686_CR32","doi-asserted-by":"crossref","unstructured":"Singer, J. D., & Willett, J. B. (1991). Modeling the days of our lives: using survival analysis when designing and analyzing longitudinal studies of duration and the timing of events. Psychological Bulletin 110(2), 268.","DOI":"10.1037\/\/0033-2909.110.2.268"},{"issue":"10","key":"6686_CR33","doi-asserted-by":"publisher","first-page":"1105","DOI":"10.1002\/sim.4154","volume":"30","author":"H Uno","year":"2011","unstructured":"Uno, H., Cai, T., Pencina, M. J., et al. (2011). On the c-statistics for evaluating overall adequacy of risk prediction procedures with censored survival data. Statistics in Medicine, 30(10), 1105\u20131117.","journal-title":"Statistics in Medicine"},{"key":"6686_CR34","unstructured":"Vaswani, A., Shazeer, N., & Parmar, N., et\u00a0al. (2017). Attention is all you need. Advances in Neural Information Processing Systems 30."},{"key":"6686_CR35","doi-asserted-by":"crossref","unstructured":"Vinzamuri, B., & Reddy, C. K. (2013). Cox regression with correlation based regularization for electronic health records. In: 2013 IEEE 13th international conference on data mining, IEEE (pp. 757\u2013766).","DOI":"10.1109\/ICDM.2013.89"},{"key":"6686_CR36","doi-asserted-by":"crossref","unstructured":"Wang, Z., & Sun, J. (2022). Survtrace: Transformers for survival analysis with competing events. In Proceedings of the 13th ACM international conference on bioinformatics, computational biology and health informatics (pp. 1\u20139).","DOI":"10.1145\/3535508.3545521"},{"issue":"5","key":"6686_CR37","doi-asserted-by":"publisher","first-page":"e406","DOI":"10.1212\/WNL.0000000000006854","volume":"92","author":"CE Whitehouse","year":"2019","unstructured":"Whitehouse, C. E., Fisk, J. D., Bernstein, C. N., et al. (2019). Comorbid anxiety, depression, and cognition in MS and other immune-mediated disorders. Neurology, 92(5), e406\u2013e417.","journal-title":"Neurology"}],"container-title":["Machine Learning"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10994-024-06686-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10994-024-06686-w\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10994-024-06686-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,2,18]],"date-time":"2025-02-18T02:01:59Z","timestamp":1739844119000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10994-024-06686-w"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,1,27]]},"references-count":37,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2025,2]]}},"alternative-id":["6686"],"URL":"https:\/\/doi.org\/10.1007\/s10994-024-06686-w","relation":{},"ISSN":["0885-6125","1573-0565"],"issn-type":[{"value":"0885-6125","type":"print"},{"value":"1573-0565","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,1,27]]},"assertion":[{"value":"30 May 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"6 August 2024","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"12 December 2024","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"27 January 2025","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare that they have no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}],"article-number":"31"}}