{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,20]],"date-time":"2026-01-20T09:02:43Z","timestamp":1768899763582,"version":"3.49.0"},"reference-count":48,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2023,10,26]],"date-time":"2023-10-26T00:00:00Z","timestamp":1698278400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2023,10,26]],"date-time":"2023-10-26T00:00:00Z","timestamp":1698278400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["npj Digit. Med."],"abstract":"<jats:title>Abstract<\/jats:title><jats:p>WHO grade II and III gliomas demonstrate diverse biological behaviors resulting in variable survival outcomes. In the context of glioma prognosis, machine learning (ML) approaches could facilitate the navigation through the maze of factors influencing survival, aiding clinicians in generating more precise and personalized survival predictions. Here we report the utilization of ML models in predicting survival at 12, 24, 36, and 60\u2009months following grade II and III glioma diagnosis. From the National Cancer Database, we analyze 10,001 WHO grade II and 11,456 grade III cranial gliomas. Using the area under the receiver operating characteristic (AUROC) values, we deploy the top-performing models in a web application for individualized predictions. SHapley Additive exPlanations (SHAP) enhance the interpretability of the models. Top-performing predictive models are the ones built with LightGBM and Random Forest algorithms. For grade II gliomas, the models yield AUROC values ranging from 0.813 to 0.896 for predicting mortality across different timeframes, and for grade III gliomas, the models yield AUROCs ranging from 0.855 to 0.878. ML models provide individualized survival forecasts for grade II and III glioma patients across multiple clinically relevant time points. The user-friendly web application represents a pioneering digital tool to potentially integrate predictive analytics into neuro-oncology clinical practice, to empower prognostication and personalize clinical decision-making.<\/jats:p>","DOI":"10.1038\/s41746-023-00948-y","type":"journal-article","created":{"date-parts":[[2023,10,26]],"date-time":"2023-10-26T18:04:58Z","timestamp":1698343498000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":19,"title":["Prognosis Individualized: Survival predictions for WHO grade II and III gliomas with a machine learning-based web application"],"prefix":"10.1038","volume":"6","author":[{"given":"Mert","family":"Karabacak","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6075-0255","authenticated-orcid":false,"given":"Pemla","family":"Jagtiani","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7304-1784","authenticated-orcid":false,"given":"Alejandro","family":"Carrasquilla","sequence":"additional","affiliation":[]},{"given":"Isabelle M.","family":"Germano","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3715-8093","authenticated-orcid":false,"given":"Konstantinos","family":"Margetis","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,10,26]]},"reference":[{"key":"948_CR1","doi-asserted-by":"publisher","first-page":"iv1","DOI":"10.1093\/neuonc\/noy131","volume":"20","author":"QT Ostrom","year":"2018","unstructured":"Ostrom, Q. T. et al. CBTRUS statistical report: primary brain and other central nervous system tumors diagnosed in the United States in 2011\u20132015. Neuro. Oncol. 20, iv1\u2013iv86 (2018).","journal-title":"Neuro. Oncol."},{"key":"948_CR2","doi-asserted-by":"publisher","first-page":"931","DOI":"10.1007\/s12094-017-1631-4","volume":"19","author":"PD Delgado-L\u00f3pez","year":"2017","unstructured":"Delgado-L\u00f3pez, P. D., Corrales-Garc\u00eda, E. M., Martino, J., Lastra-Aras, E. & Due\u00f1as-Polo, M. T. Diffuse low-grade glioma: a review on the new molecular classification, natural history and current management strategies. Clin. Transl. Oncol. 19, 931\u2013944 (2017).","journal-title":"Clin. Transl. Oncol."},{"key":"948_CR3","doi-asserted-by":"publisher","first-page":"8","DOI":"10.1016\/j.csbj.2014.11.005","volume":"13","author":"K 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. Comput. Struct. Biotechnol. J. 13, 8\u201317 (2015).","journal-title":"Comput. Struct. Biotechnol. J."},{"key":"948_CR4","first-page":"59","volume":"2","author":"JA Cruz","year":"2007","unstructured":"Cruz, J. A. & Wishart, D. S. Applications of machine learning in cancer prediction and prognosis. Cancer Inf. 2, 59\u201377 (2007).","journal-title":"Cancer Inf."},{"key":"948_CR5","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-017-11817-6","volume":"7","author":"S Yousefi","year":"2017","unstructured":"Yousefi, S. et al. Predicting clinical outcomes from large scale cancer genomic profiles with deep survival models. Sci. Rep. 7, 11707 (2017).","journal-title":"Sci. Rep."},{"key":"948_CR6","doi-asserted-by":"publisher","first-page":"812","DOI":"10.3390\/cancers15030812","volume":"15","author":"M Karabacak","year":"2023","unstructured":"Karabacak, M. & Margetis, K. A machine learning-based online prediction tool for predicting short-term postoperative outcomes following spinal tumor resections. Cancers 15, 812 (2023).","journal-title":"Cancers"},{"key":"948_CR7","doi-asserted-by":"publisher","DOI":"10.1177\/02841851221143496","author":"M Karabacak","year":"2022","unstructured":"Karabacak, M. et al. Radiomics-based machine learning models for prediction of medulloblastoma subgroups: a systematic review and meta-analysis of the diagnostic test performance. Acta Radiol. Stockh. Swed. 1987 2841851221143496. https:\/\/doi.org\/10.1177\/02841851221143496 (2022).","journal-title":"Acta Radiol. Stockh. Swed."},{"key":"948_CR8","doi-asserted-by":"publisher","first-page":"146045822211354","DOI":"10.1177\/14604582221135427","volume":"28","author":"R Zhao","year":"2022","unstructured":"Zhao, R., Zhuge, Y., Camphausen, K. & Krauze, A. V. Machine learning based survival prediction in Glioma using large-scale registry data. Health Inform. J. 28, 146045822211354 (2022).","journal-title":"Health Inform. J."},{"key":"948_CR9","doi-asserted-by":"publisher","first-page":"665","DOI":"10.1093\/neuonc\/noz191","volume":"22","author":"H Gittleman","year":"2020","unstructured":"Gittleman, H., Sloan, A. E. & Barnholtz-Sloan, J. S. An independently validated survival nomogram for lower-grade glioma. Neuro. Oncol. 22, 665\u2013674 (2020).","journal-title":"Neuro. Oncol."},{"key":"948_CR10","doi-asserted-by":"publisher","first-page":"1151","DOI":"10.1093\/brain\/awab340","volume":"145","author":"G Li","year":"2022","unstructured":"Li, G. et al. An MRI radiomics approach to predict survival and tumour-infiltrating macrophages in gliomas. Brain 145, 1151\u20131161 (2022).","journal-title":"Brain"},{"key":"948_CR11","doi-asserted-by":"publisher","first-page":"969907","DOI":"10.3389\/fonc.2022.969907","volume":"12","author":"C Xu","year":"2022","unstructured":"Xu, C. et al. An automated approach for predicting glioma grade and survival of LGG patients using CNN and radiomics. Front. Oncol. 12, 969907 (2022).","journal-title":"Front. Oncol."},{"key":"948_CR12","doi-asserted-by":"publisher","first-page":"4697","DOI":"10.2147\/IJGM.S352773","volume":"15","author":"L Sun","year":"2022","unstructured":"Sun, L., Li, B., Wang, B., Li, J. & Li, J. Construction of a risk model to predict the prognosis and immunotherapy of low-grade glioma ground on 7 ferroptosis-related genes. Int. J. Gen. Med. 15, 4697\u20134716 (2022).","journal-title":"Int. J. Gen. Med."},{"key":"948_CR13","doi-asserted-by":"publisher","first-page":"1517","DOI":"10.2147\/IJGM.S335571","volume":"15","author":"X Fu","year":"2022","unstructured":"Fu, X. et al. Identification of a nomogram with an autophagy-related risk signature for survival prediction in patients with Glioma. Int. J. Gen. Med. 15, 1517\u20131535 (2022).","journal-title":"Int. J. Gen. Med."},{"key":"948_CR14","doi-asserted-by":"publisher","first-page":"957059","DOI":"10.3389\/fgene.2022.957059","volume":"13","author":"Y Zhang","year":"2022","unstructured":"Zhang, Y. et al. A novel risk score model based on fourteen chromatin regulators-based genes for predicting overall survival of patients with lower-grade gliomas. Front. Genet. 13, 957059 (2022).","journal-title":"Front. Genet."},{"key":"948_CR15","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-023-38629-1","volume":"13","author":"C Zhang","year":"2023","unstructured":"Zhang, C. et al. A novel NFAT1-IL6\/JAK\/STAT3 signaling pathway related nomogram predicts overall survival in gliomas. Sci. Rep. 13, 11401 (2023).","journal-title":"Sci. Rep."},{"key":"948_CR16","doi-asserted-by":"publisher","DOI":"10.1007\/s00432-023-05155-6","author":"Y Cai","year":"2023","unstructured":"Cai, Y. et al. An alternative extension of telomeres related prognostic model to predict survival in lower grade glioma. J. Cancer Res. Clin. Oncol. https:\/\/doi.org\/10.1007\/s00432-023-05155-6 (2023).","journal-title":"J. Cancer Res. Clin. Oncol."},{"key":"948_CR17","doi-asserted-by":"publisher","first-page":"323","DOI":"10.1016\/j.ygeno.2012.04.003","volume":"99","author":"X Chen","year":"2012","unstructured":"Chen, X. & Ishwaran, H. Random forests for genomic data analysis. Genom. 99, 323\u2013329 (2012).","journal-title":"Genom."},{"key":"948_CR18","unstructured":"Fernandez-Delgado, M., Cernadas, E., Barro, S. & Amorim, D. Do we need hundreds of classifiers to solve real world classification problems? J. Mach. Learning Res. 15, 3133\u20133181 (2014)."},{"key":"948_CR19","doi-asserted-by":"publisher","first-page":"21","DOI":"10.3389\/fnbot.2013.00021","volume":"7","author":"A Natekin","year":"2013","unstructured":"Natekin, A. & Knoll, A. Gradient boosting machines, a tutorial. Front. Neurorobot. 7, 21 (2013).","journal-title":"Front. Neurorobot."},{"key":"948_CR20","unstructured":"Ke, G. et al. LightGBM: in Advances in Neural Information Processing Systems (eds. Guyon, I. et al.) http:\/\/dblp.uni-trier.de\/db\/conf\/nips\/nips2017.html (Curran Associates, Inc., 2017)."},{"key":"948_CR21","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1023\/A:1010933404324","volume":"45","author":"L Breiman","year":"2001","unstructured":"Breiman, L. Random forests. Mach. Learn. 45, 5\u201332 (2001).","journal-title":"Mach. Learn."},{"key":"948_CR22","doi-asserted-by":"publisher","first-page":"458","DOI":"10.1038\/ng.3273","volume":"47","author":"H Suzuki","year":"2015","unstructured":"Suzuki, H. et al. Mutational landscape and clonal architecture in grade II and III gliomas. Nat. Genet. 47, 458\u2013468 (2015).","journal-title":"Nat. Genet."},{"key":"948_CR23","doi-asserted-by":"publisher","first-page":"1157","DOI":"10.3171\/2013.1.JNS121","volume":"118","author":"L Capelle","year":"2013","unstructured":"Capelle, L. et al. Spontaneous and therapeutic prognostic factors in adult hemispheric World Health Organization grade II gliomas: a series of 1097 cases: clinical article. J. Neurosurg. 118, 1157\u20131168 (2013).","journal-title":"J. Neurosurg."},{"key":"948_CR24","doi-asserted-by":"publisher","first-page":"359","DOI":"10.1111\/ane.12973","volume":"138","author":"A Corell","year":"2018","unstructured":"Corell, A., Carstam, L., Smits, A., Henriksson, R. & Jakola, A. S. Age and surgical outcome of low-grade glioma in Sweden. Acta Neurol. Scand. 138, 359\u2013368 (2018).","journal-title":"Acta Neurol. Scand."},{"key":"948_CR25","doi-asserted-by":"publisher","first-page":"v1","DOI":"10.1093\/neuonc\/noz150","volume":"21","author":"QT Ostrom","year":"2019","unstructured":"Ostrom, Q. T. et al. CBTRUS statistical report: primary brain and other central nervous system tumors diagnosed in the United States in 2012\u20132016. Neuro. Oncol. 21, v1\u2013v100 (2019).","journal-title":"Neuro. Oncol."},{"key":"948_CR26","doi-asserted-by":"publisher","first-page":"1131642","DOI":"10.3389\/fonc.2023.1131642","volume":"13","author":"X Guo","year":"2023","unstructured":"Guo, X. et al. Clinical updates on gliomas and implications of the 5th edition of the WHO classification of central nervous system tumors. Front. Oncol. 13, 1131642 (2023).","journal-title":"Front. Oncol."},{"key":"948_CR27","doi-asserted-by":"publisher","first-page":"1321","DOI":"10.3171\/2022.1.JNS212514","volume":"137","author":"AS Jakola","year":"2022","unstructured":"Jakola, A. S. et al. The impact of resection in IDH-mutant WHO grade 2 gliomas: a retrospective population-based parallel cohort study. J. Neurosurg. 137, 1321\u20131328 (2022).","journal-title":"J. Neurosurg."},{"key":"948_CR28","doi-asserted-by":"publisher","first-page":"1338","DOI":"10.1200\/JCO.2007.13.9337","volume":"26","author":"JS Smith","year":"2008","unstructured":"Smith, J. S. et al. Role of extent of resection in the long-term outcome of low-grade hemispheric gliomas. J. Clin. Oncol. 26, 1338\u20131345 (2008).","journal-title":"J. Clin. Oncol."},{"key":"948_CR29","doi-asserted-by":"publisher","first-page":"9523","DOI":"10.2147\/IJGM.S337227","volume":"14","author":"K Jin","year":"2021","unstructured":"Jin, K. et al. Prognosis of Oligodendroglioma patients stratified by age: a SEER population-based analysis. Int. J. Gen. Med. 14, 9523\u20139536 (2021).","journal-title":"Int. J. Gen. Med."},{"key":"948_CR30","doi-asserted-by":"publisher","DOI":"10.1186\/s12883-022-02879-9","volume":"22","author":"Z Jia","year":"2022","unstructured":"Jia, Z. et al. Exploring the relationship between age and prognosis in glioma: rethinking current age stratification. BMC Neurol. 22, 350 (2022).","journal-title":"BMC Neurol."},{"key":"948_CR31","doi-asserted-by":"publisher","unstructured":"Jacobs, C. D. et al. Radiation records in the National Cancer Database: variations in coding and\/or practice can significantly alter survival results. JCO Clin. Cancer Inform. https:\/\/doi.org\/10.1200\/CCI.18.00118 (2019).","DOI":"10.1200\/CCI.18.00118"},{"key":"948_CR32","doi-asserted-by":"publisher","first-page":"e211793","DOI":"10.1001\/jamanetworkopen.2021.1793","volume":"4","author":"DX Yang","year":"2021","unstructured":"Yang, D. X. et al. Prevalence of missing data in the National Cancer Database and association with overall survival. JAMA Netw. Open 4, e211793 (2021).","journal-title":"JAMA Netw. Open"},{"key":"948_CR33","doi-asserted-by":"publisher","first-page":"199","DOI":"10.1007\/s11060-023-04286-7","volume":"162","author":"M Sharma","year":"2023","unstructured":"Sharma, M. et al. Demographic variations and time to initiation of adjunct treatment following surgical resection of anaplastic astrocytoma in the United States: a National Cancer Database analysis. J. Neuro. Oncol. 162, 199\u2013210 (2023).","journal-title":"J. Neuro. Oncol."},{"key":"948_CR34","doi-asserted-by":"publisher","first-page":"799","DOI":"10.1093\/neuonc\/noac198","volume":"25","author":"QT Ostrom","year":"2023","unstructured":"Ostrom, Q. T. et al. National-level overall survival patterns for molecularly-defined diffuse glioma types in the United States. Neuro. Oncol. 25, 799\u2013807 (2023).","journal-title":"Neuro. Oncol."},{"key":"948_CR35","doi-asserted-by":"publisher","first-page":"683","DOI":"10.1245\/s10434-007-9747-3","volume":"15","author":"KY Bilimoria","year":"2008","unstructured":"Bilimoria, K. Y., Stewart, A. K., Winchester, D. P. & Ko, C. Y. The national cancer data base: a powerful initiative to improve cancer care in the United States. Ann. Surg. Oncol. 15, 683\u2013690 (2008).","journal-title":"Ann. Surg. Oncol."},{"key":"948_CR36","doi-asserted-by":"publisher","DOI":"10.1186\/s12916-014-0241-z","volume":"13","author":"GS Collins","year":"2015","unstructured":"Collins, G. S., Reitsma, J. B., Altman, D. G. & Moons, K. Transparent reporting of a multivariable prediction model for individual prognosis or diagnosis (TRIPOD): the TRIPOD Statement. BMC Med. 13, 1 (2015).","journal-title":"BMC Med."},{"key":"948_CR37","first-page":"e323","volume":"18","author":"W Luo","year":"2016","unstructured":"Luo, W. et al. Guidelines for developing and reporting machine learning predictive models in biomedical research: a multidisciplinary view. J. Med. Inter. Res. 18, e323 (2016).","journal-title":"J. Med. Inter. Res."},{"key":"948_CR38","doi-asserted-by":"publisher","unstructured":"Hollmann, N., M\u00fcller, S., Eggensperger, K. & Hutter, F. TabPFN: A transformer that solves small tabular classification problems in a second. arXiv https:\/\/doi.org\/10.48550\/arXiv.2207.01848 (2023).","DOI":"10.48550\/arXiv.2207.01848"},{"key":"948_CR39","doi-asserted-by":"publisher","unstructured":"Arik, S. O. & Pfister, T. TabNet: Attentive interpretable tabular learning. arXiv https:\/\/doi.org\/10.48550\/arXiv.1908.07442 (2020).","DOI":"10.48550\/arXiv.1908.07442"},{"key":"948_CR40","doi-asserted-by":"publisher","unstructured":"Chen, T. & Guestrin, C. XGBoost: in Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. https:\/\/doi.org\/10.1145\/2939672.2939785 (2016).","DOI":"10.1145\/2939672.2939785"},{"key":"948_CR41","doi-asserted-by":"publisher","unstructured":"Akiba, T., Sano, S., Yanase, T., Ohta, T. & Koyama, M. Optuna: A next-generation hyperparameter optimization framework. arXiv https:\/\/doi.org\/10.48550\/arXiv.1907.10902 (2019).","DOI":"10.48550\/arXiv.1907.10902"},{"key":"948_CR42","doi-asserted-by":"publisher","first-page":"321","DOI":"10.1613\/jair.953","volume":"16","author":"NV Chawla","year":"2002","unstructured":"Chawla, N. V., Bowyer, K. W., Hall, L. O. & Kegelmeyer, W. P. SMOTE: synthetic minority over-sampling technique. J. Artif. Intell. Res. 16, 321\u2013357 (2002).","journal-title":"J. Artif. Intell. Res."},{"key":"948_CR43","doi-asserted-by":"publisher","first-page":"593","DOI":"10.1148\/radiol.2533091633","volume":"253","author":"CA Gatsonis","year":"2009","unstructured":"Gatsonis, C. A. Receiver operating characteristic analysis for the evaluation of diagnosis and prediction. Radiol. 253, 593\u2013596 (2009).","journal-title":"Radiol."},{"key":"948_CR44","doi-asserted-by":"publisher","DOI":"10.1186\/s12916-019-1466-7","volume":"17","author":"On behalf of Topic Group \u2018Evaluating diagnostic tests and prediction models\u2019 of the STRATOS initiative.","year":"2019","unstructured":"On behalf of Topic Group \u2018Evaluating diagnostic tests and prediction models\u2019 of the STRATOS initiative. et al. Calibration: the Achilles heel of predictive analytics. BMC Med 17, 230 (2019).","journal-title":"BMC Med"},{"key":"948_CR45","doi-asserted-by":"publisher","unstructured":"Niculescu-Mizil, A. & Caruana, R. in Proceedings of the 22nd International Conference on Machine Learning - ICML. https:\/\/doi.org\/10.1145\/1102351.1102430. (ACM Press, 2005).","DOI":"10.1145\/1102351.1102430"},{"key":"948_CR46","doi-asserted-by":"publisher","first-page":"1145","DOI":"10.1016\/S0031-3203(96)00142-2","volume":"30","author":"AP Bradley","year":"1997","unstructured":"Bradley, A. P. The use of the area under the ROC curve in the evaluation of machine learning algorithms. Pattern Recognit. 30, 1145\u20131159 (1997).","journal-title":"Pattern Recognit."},{"key":"948_CR47","unstructured":"Lundberg, S. M. & Lee, S.-I. in Advances in Neural Information Processing Systems (eds. Guyon, I. et al.) http:\/\/dblp.uni-trier.de\/db\/conf\/nips\/nips2017.html (Curran Associates, Inc., 2017)."},{"key":"948_CR48","doi-asserted-by":"publisher","first-page":"44","DOI":"10.1080\/10618600.2014.907095","volume":"24","author":"A Goldstein","year":"2015","unstructured":"Goldstein, A., Kapelner, A., Bleich, J. & Pitkin, E. Peeking inside the black box: visualizing statistical learning with plots of individual conditional expectation. J. Comput. Graph. Stat. 24, 44\u201365 (2015).","journal-title":"J. Comput. Graph. Stat."}],"container-title":["npj Digital Medicine"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41746-023-00948-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41746-023-00948-y","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41746-023-00948-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,10,26]],"date-time":"2023-10-26T18:10:55Z","timestamp":1698343855000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41746-023-00948-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,26]]},"references-count":48,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2023,12]]}},"alternative-id":["948"],"URL":"https:\/\/doi.org\/10.1038\/s41746-023-00948-y","relation":{},"ISSN":["2398-6352"],"issn-type":[{"value":"2398-6352","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,10,26]]},"assertion":[{"value":"20 August 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"13 October 2023","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"26 October 2023","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":"200"}}