{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,3]],"date-time":"2026-08-03T22:11:11Z","timestamp":1785795071708,"version":"3.56.0"},"reference-count":16,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2020,2,6]],"date-time":"2020-02-06T00:00:00Z","timestamp":1580947200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2020,2,6]],"date-time":"2020-02-06T00:00:00Z","timestamp":1580947200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"name":"National R&D Program for Cancer Control, Ministry of Health&Welfare, Republic of Korea"},{"name":"National R&D Program for Cancer Control, Ministry of Health&Welfare, Republic of Korea"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Sci Rep"],"abstract":"<jats:title>Abstract<\/jats:title><jats:p>Accurate prediction of non-small cell lung cancer (NSCLC) prognosis after surgery remains challenging. The Cox proportional hazard (PH) model is widely used, however, there are some limitations associated with it. In this study, we developed novel neural network models called binned time survival analysis (DeepBTS) models using 30 clinico-pathological features of surgically resected NSCLC patients (training cohort, <jats:italic>n<\/jats:italic>\u2009=\u20091,022; external validation cohort, <jats:italic>n<\/jats:italic>\u2009=\u2009298). We employed the root-mean-square error (in the supervised learning model, s- DeepBTS) or negative log-likelihood (in the semi-unsupervised learning model, su-DeepBTS) as the loss function. The su-DeepBTS algorithm achieved better performance (C-index\u2009=\u20090.7306; AUC\u2009=\u20090.7677) than the other models (Cox PH: C-index\u2009=\u20090.7048 and AUC\u2009=\u20090.7390; s-DeepBTS: C-index\u2009=\u20090.7126 and AUC\u2009=\u20090.7420). The top 14 features were selected using su-DeepBTS model as a selector and could distinguish the low- and high-risk groups in the training cohort (<jats:italic>p<\/jats:italic>\u2009=\u20091.86\u2009\u00d7\u200910<jats:sup>\u221211<\/jats:sup>) and validation cohort (<jats:italic>p<\/jats:italic>\u2009=\u20091.04\u2009\u00d7\u200910<jats:sup>\u221210<\/jats:sup>). When trained with the optimal feature set for each model, the su-DeepBTS model could predict the prognoses of NSCLC better than the traditional model, especially in stage I patients. Follow-up studies using combined radiological, pathological imaging, and genomic data to enhance the performance of our model are ongoing.<\/jats:p>","DOI":"10.1038\/s41598-020-58722-z","type":"journal-article","created":{"date-parts":[[2020,2,6]],"date-time":"2020-02-06T11:04:48Z","timestamp":1580987088000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":33,"title":["DeepBTS: Prediction of Recurrence-free Survival of Non-small Cell Lung Cancer Using a Time-binned Deep Neural Network"],"prefix":"10.1038","volume":"10","author":[{"given":"Bora","family":"Lee","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sang Hoon","family":"Chun","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ji Hyung","family":"Hong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"In Sook","family":"Woo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Seoree","family":"Kim","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Joon Won","family":"Jeong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jae Jun","family":"Kim","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hyun Woo","family":"Lee","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sae Jung","family":"Na","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kyongmin Sarah","family":"Beck","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bomi","family":"Gil","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sungsoo","family":"Park","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ho Jung","family":"An","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2506-3740","authenticated-orcid":false,"given":"Yoon Ho","family":"Ko","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2020,2,6]]},"reference":[{"issue":"1","key":"58722_CR1","doi-asserted-by":"publisher","first-page":"33","DOI":"10.1515\/slgr-2015-0040","volume":"43","author":"Magdalena Babi\u0144ska","year":"2015","unstructured":"Babi\u0144ska, M. et al. Limitations of Cox Proportional Hazards Analysis in Mortality Prediction of Patients with Acute Coronary Syndrome,\u00a0Studies in Logic. Grammar and Rhetoric,\u00a043(1), 33\u201348. https:\/\/doi.org\/10.1515\/slgr-2015-0040\u00a0(2015).","journal-title":"Studies in Logic, Grammar and Rhetoric"},{"key":"58722_CR2","doi-asserted-by":"publisher","unstructured":"Davidson-Pilon, C. et al.CamDavidsonPilon\/lifelines: v0.23.4 (Version v0.23.4). Zenodo, https:\/\/doi.org\/10.5281\/zenodo.3576382 (2019).","DOI":"10.5281\/zenodo.3576382"},{"key":"58722_CR3","doi-asserted-by":"publisher","first-page":"8","DOI":"10.1016\/j.csbj.2014.11.005","volume":"13","author":"Konstantina Kourou","year":"2015","unstructured":"Kourou, K., Exarchos, T. P., Exarchos, K. P., Karamouzis, M. V. & Fotiadis, D. I. Machine learning applications in cancer prognosis and prediction. Computational and Structural Biotechnology Journal 13, 8\u201317, https:\/\/doi.org\/10.1016\/j.csbj.2014.11.005 (2015).","journal-title":"Computational and Structural Biotechnology Journal"},{"key":"58722_CR4","doi-asserted-by":"crossref","unstructured":"Katzman, J. L.\u00a0et al. DeepSurv: personalized treatment recommender system using a Cox proportional hazards deep neural network.\u00a018, 24 (2018).","DOI":"10.1186\/s12874-018-0482-1"},{"key":"58722_CR5","unstructured":"Luck, M., Sylvain, T., Cardinal, H., Lodi, A. & Bengio, Y. J. A. P. A. Deep learning for patient-specific kidney graft survival analysis (2018)."},{"key":"58722_CR6","unstructured":"Lee, C., Zame, W. R., Yoon, J. & van der Schaar, M. In\u00a0Thirty-Second AAAI Conference on Artificial Intelligence (2018)."},{"key":"58722_CR7","unstructured":"Fotso, S. Deep Neural Networks for Survival Analysis Based on a Multi-Task Framework. arXiv preprint arXiv:1801.05512 (2018)."},{"key":"58722_CR8","unstructured":"Shwartz-Ziv, R. & Tishby, N. Opening the black box of deep neural networks via information. arXiv preprint arXiv:1703.00810 (2017)."},{"key":"58722_CR9","doi-asserted-by":"publisher","first-page":"230","DOI":"10.4048\/jbc.2012.15.2.230","volume":"15","author":"W Kim","year":"2012","unstructured":"Kim, W.\u00a0et al. Development of novel breast cancer recurrence prediction model using support vector machine.\u00a0Journal of breast cancer\u00a015, 230\u2013238,\u00a0https:\/\/doi.org\/10.4048\/jbc.2012.15.2.230\u00a0(2012).","journal-title":"Journal of breast cancer"},{"issue":"3","key":"58722_CR10","doi-asserted-by":"publisher","first-page":"328","DOI":"10.3390\/cancers11030328","volume":"11","author":"Patrizia Ferroni","year":"2019","unstructured":"Ferroni, P.\u00a0et al. Breast Cancer Prognosis Using a Machine Learning Approach.\u00a0Cancers\u00a011,\u00a0https:\/\/doi.org\/10.3390\/cancers11030328\u00a0(2019).","journal-title":"Cancers"},{"key":"58722_CR11","doi-asserted-by":"publisher","DOI":"10.1186\/s12885-017-3806-3","volume":"17","author":"B Obrzut","year":"2017","unstructured":"Obrzut, B., Kusy, M., Semczuk, A., Obrzut, M. & Kluska, J. Prediction of 5-year overall survival in cervical cancer patients treated with radical hysterectomy using computational intelligence methods.\u00a0BMC Cancer\u00a017, 840,\u00a0https:\/\/doi.org\/10.1186\/s12885-017-3806-3\u00a0(2017).","journal-title":"BMC Cancer"},{"key":"58722_CR12","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.ijmedinf.2017.09.013","volume":"108","author":"Chip M. Lynch","year":"2017","unstructured":"Lynch, C. M.\u00a0et al. Prediction of lung cancer patient survival via supervised machine learning classification techniques.\u00a0International Journal of Medical Informatics 108, 1\u20138,\u00a0https:\/\/doi.org\/10.1016\/j.ijmedinf.2017.09.013\u00a0(2017).","journal-title":"International Journal of Medical Informatics"},{"key":"58722_CR13","doi-asserted-by":"publisher","first-page":"41","DOI":"10.1023\/a:1007379606734","volume":"28","author":"R Caruana","year":"1997","unstructured":"Caruana, R. Multitask Learning.\u00a0Machine Learning\u00a028, 41\u201375,\u00a0https:\/\/doi.org\/10.1023\/a:1007379606734\u00a0(1997).","journal-title":"Machine Learning"},{"key":"58722_CR14","unstructured":"Amin, M. B.\u00a0et al. Eds.\u00a0AJCC Cancer Staging Manual. (Springer, 2017)."},{"issue":"8","key":"58722_CR15","doi-asserted-by":"publisher","first-page":"706","DOI":"10.1097\/JTO.0b013e31812f3c1a","volume":"2","author":"Peter Goldstraw","year":"2007","unstructured":"Goldstraw, P. et al. The IASLC Lung Cancer Staging Project: Proposals for the Revision of the TNM Stage Groupings in the Forthcoming (Seventh) Edition of the TNM Classification of Malignant Tumours. Journal of Thoracic Oncology 2(8), 706\u2013714\u00a0(2007).","journal-title":"Journal of Thoracic Oncology"},{"key":"58722_CR16","unstructured":"In Biostatistics 515 (washington.edu, 2004)."}],"container-title":["Scientific Reports"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41598-020-58722-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-020-58722-z","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-020-58722-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,2]],"date-time":"2023-01-02T15:01:04Z","timestamp":1672671664000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41598-020-58722-z"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,2,6]]},"references-count":16,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2020,12]]}},"alternative-id":["58722"],"URL":"https:\/\/doi.org\/10.1038\/s41598-020-58722-z","relation":{},"ISSN":["2045-2322"],"issn-type":[{"value":"2045-2322","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,2,6]]},"assertion":[{"value":"8 July 2019","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"20 January 2020","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"6 February 2020","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":"1952"}}