{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,3]],"date-time":"2026-06-03T08:11:47Z","timestamp":1780474307151,"version":"3.54.1"},"reference-count":66,"publisher":"IOP Publishing","issue":"2","license":[{"start":{"date-parts":[[2023,5,30]],"date-time":"2023-05-30T00:00:00Z","timestamp":1685404800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2023,5,30]],"date-time":"2023-05-30T00:00:00Z","timestamp":1685404800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/iopscience.iop.org\/info\/page\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/100019126","name":"Gujarat Council on Science and Technology","doi-asserted-by":"crossref","award":["GU JCOST \/ST I\/2021\u221222\/3858"],"award-info":[{"award-number":["GU JCOST \/ST I\/2021\u221222\/3858"]}],"id":[{"id":"10.13039\/100019126","id-type":"DOI","asserted-by":"crossref"}]},{"name":"CRG DST India","award":["CRG\/2020\/00086"],"award-info":[{"award-number":["CRG\/2020\/00086"]}]},{"name":"Seed Grant PDEU","award":["ORSP\/R&D\/P DP U\/2019\/M R\/RO051"],"award-info":[{"award-number":["ORSP\/R&D\/P DP U\/2019\/M R\/RO051"]}]}],"content-domain":{"domain":["iopscience.iop.org"],"crossmark-restriction":false},"short-container-title":["Mach. Learn.: Sci. Technol."],"published-print":{"date-parts":[[2023,6,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:p>An artificial intelligence (AI) model\u2019s performance is strongly influenced by the input features. Therefore, it is vital to find the optimal feature set. It is more crucial for the survival prediction of the glioblastoma multiforme (GBM) type of brain tumor. In this study, we identify the best feature set for predicting the survival days (SD) of GBM patients that outrank the current state-of-the-art methodologies. The proposed approach is an end-to-end AI model. This model first segments tumors from healthy brain parts in patients\u2019 MRI images, extracts features from the segmented results, performs feature selection, and makes predictions about patients\u2019 survival days (SD) based on selected features. The extracted features are primarily shape-based, location-based, and radiomics-based features. Additionally, patient metadata is also included as a feature. The selection methods include recursive feature elimination, permutation importance (PI), and finding the correlation between the features. Finally, we examined features\u2019 behavior at local (single sample) and global (all the samples) levels. In this study, we find that out of 1265 extracted features, only 29 dominant features play a crucial role in predicting patients\u2019 SD. Among these 29 features, one is metadata (age of patient), three are location-based, and the rest are radiomics features. Furthermore, we find explanations of these features using post-hoc interpretability methods to validate the model\u2019s robust prediction and understand its decision. Finally, we analyzed the behavioral impact of the top six features on survival prediction, and the findings drawn from the explanations were coherent with the medical domain. We find that after the age of 50 years, the likelihood of survival of a patient deteriorates, and survival after 80 years is scarce. Again, for location-based features, the SD is less if the tumor location is in the central or back part of the brain. All these trends derived from the developed AI model are in sync with medically proven facts. The results show an overall 33% improvement in the accuracy of SD prediction compared to the top-performing methods of the BraTS-2020 challenge.<\/jats:p>","DOI":"10.1088\/2632-2153\/acd5a9","type":"journal-article","created":{"date-parts":[[2023,5,15]],"date-time":"2023-05-15T22:44:30Z","timestamp":1684190670000},"page":"025025","update-policy":"https:\/\/doi.org\/10.1088\/crossmark-policy","source":"Crossref","is-referenced-by-count":22,"title":["Interpretable machine learning model to predict survival days of malignant brain tumor patients"],"prefix":"10.1088","volume":"4","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8240-3740","authenticated-orcid":false,"given":"Snehal","family":"Rajput","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1995-4149","authenticated-orcid":false,"given":"Rupal A","family":"Kapdi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3895-1448","authenticated-orcid":false,"given":"Mehul S","family":"Raval","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5815-3294","authenticated-orcid":true,"given":"Mohendra","family":"Roy","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"266","published-online":{"date-parts":[[2023,5,30]]},"reference":[{"key":"mlstacd5a9bib1","doi-asserted-by":"publisher","first-page":"3","DOI":"10.22034\/APJCP.2017.18.1.3","article-title":"Glioblastoma multiforme: a review of its epidemiology and pathogenesis through clinical presentation and treatment","volume":"18","author":"Hanif","year":"2017","journal-title":"Asian Pac. J. Cancer Prev."},{"key":"mlstacd5a9bib2","doi-asserted-by":"publisher","first-page":"iii1","DOI":"10.1093\/neuonc\/noab200","article-title":"CBTRUS statistical report: primary brain and other central nervous system tumors diagnosed in the united states in 2014\u20132018","volume":"23","author":"Ostrom","year":"2021","journal-title":"Neuro-Oncology"},{"key":"mlstacd5a9bib3","doi-asserted-by":"publisher","first-page":"1770","DOI":"10.1038\/s41379-018-0110-y","article-title":"A common classification framework for neuroendocrine neoplasms: an international agency for research on cancer (IARC) and World Health Organization (WHO) expert consensus proposal","volume":"31","author":"Rindi","year":"2018","journal-title":"Mod. Pathol."},{"key":"mlstacd5a9bib4","doi-asserted-by":"publisher","first-page":"9193","DOI":"10.1038\/s41598-022-12378-z","article-title":"Towards fully automated segmentation of rat cardiac MRI by leveraging deep learning frameworks","volume":"12","author":"Fern\u00e1ndez-Llaneza","year":"2022","journal-title":"Sci. Rep."},{"key":"mlstacd5a9bib5","first-page":"pp 234","article-title":"U-net: convolutional networks for biomedical image segmentation","author":"Ronneberger","year":"2015"},{"key":"mlstacd5a9bib6","first-page":"pp 456","article-title":"Ensembles of densely-connected CNNs with label-uncertainty for brain tumor segmentation","author":"McKinley","year":"2018"},{"key":"mlstacd5a9bib7","article-title":"Uncertainty-driven refinement of tumor-core segmentation using 3D-to-2D networks with label uncertainty","author":"McKinley","year":"2020"},{"key":"mlstacd5a9bib8","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/sdata.2017.117","article-title":"Advancing the cancer genome atlas glioma MRI collections with expert segmentation labels and radiomic features","volume":"4","author":"Bakas","year":"2017","journal-title":"Sci. Data"},{"key":"mlstacd5a9bib9","article-title":"Identifying the best machine learning algorithms for brain tumor segmentation, progression assessment, and overall survival prediction in the brats challenge","author":"Bakas","year":"2018"},{"key":"mlstacd5a9bib10","doi-asserted-by":"publisher","first-page":"1993","DOI":"10.1109\/TMI.2014.2377694","article-title":"The multimodal brain tumor image segmentation benchmark (brats)","volume":"34","author":"Menze","year":"2014","journal-title":"IEEE Trans. Med. Imaging"},{"key":"mlstacd5a9bib11","doi-asserted-by":"crossref","DOI":"10.32010\/26166127.2020.3.1.119.138","article-title":"A review on end-to-end methods for brain tumor segmentation and overall survival prediction","author":"Rajput","year":"2020"},{"key":"mlstacd5a9bib12","article-title":"H2nf-net for brain tumor segmentation using multimodal MR imaging: 2nd place solution to brats challenge 2020 segmentation task","author":"Jia","year":"2020"},{"key":"mlstacd5a9bib13","article-title":"Modality-pairing learning for brain tumor segmentation","author":"Wang","year":"2020"},{"key":"mlstacd5a9bib14","first-page":"pp 379","article-title":"Triplanar ensemble of 3d-to-2d CNNS with label-uncertainty for brain tumor segmentation","author":"McKinley","year":"2019"},{"key":"mlstacd5a9bib15","first-page":"pp 354","article-title":"MRI brain tumor segmentation using a 2D-3D U-Net ensemble","author":"Asenjo","year":"2021"},{"key":"mlstacd5a9bib16","first-page":"pp 311","article-title":"3D MRI brain tumor segmentation using autoencoder regularization","author":"Myronenko","year":"2018"},{"key":"mlstacd5a9bib17","volume":"vol 11992","author":"Crimi","year":"2020"},{"key":"mlstacd5a9bib18","article-title":"nnU-Net for brain tumor segmentation","author":"Isensee","year":"2020"},{"key":"mlstacd5a9bib19","article-title":"Nvidia data scientists take top spots in miccai 2021 brain tumor segmentation challenge","author":"Braunstein","year":"2021"},{"key":"mlstacd5a9bib20","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s11831-021-09559-w","article-title":"A survey and analysis on automated glioma brain tumor segmentation and overall patient survival prediction","volume":"28","author":"Agravat","year":"2021","journal-title":"Arch. Comput. Methods Eng."},{"key":"mlstacd5a9bib21","doi-asserted-by":"publisher","first-page":"4976","DOI":"10.3390\/cancers13194976","article-title":"Predicting overall survival time in glioblastoma patients using gradient boosting machines algorithm and recursive feature elimination technique","volume":"13","author":"Karami","year":"2021","journal-title":"Cancers"},{"key":"mlstacd5a9bib22","doi-asserted-by":"publisher","first-page":"61","DOI":"10.3389\/fncom.2020.00061","article-title":"Overall survival prediction in glioblastoma with radiomic features using machine learning","volume":"14","author":"Baid","year":"2020","journal-title":"Front. Comput. Neurosci."},{"key":"mlstacd5a9bib23","doi-asserted-by":"publisher","first-page":"2022","DOI":"10.1038\/s41467-022-29701-x","article-title":"Predicting cancer prognosis and drug response from the tumor microbiome","volume":"13","author":"Hermida","year":"2022","journal-title":"Nat. Commun."},{"key":"mlstacd5a9bib24","doi-asserted-by":"publisher","first-page":"45","DOI":"10.7812\/TPP\/08-027","article-title":"Prognostic factors for long-term survival after glioblastoma","volume":"12","author":"Walid","year":"2008","journal-title":"Perm. J."},{"key":"mlstacd5a9bib25","first-page":"pp 304","article-title":"Brain tumor segmentation with uncertainty estimation and overall survival prediction","author":"Feng","year":"2019"},{"key":"mlstacd5a9bib26","doi-asserted-by":"publisher","first-page":"2021","DOI":"10.1038\/s41598-021-81825-0","article-title":"Long-term cancer survival prediction using multimodal deep learning","volume":"11","author":"Vale-Silva","year":"2021","journal-title":"Sci. Rep."},{"key":"mlstacd5a9bib27","first-page":"pp 331","article-title":"PieceNet: a redundant UNet ensemble","author":"Bommineni","year":"2021"},{"key":"mlstacd5a9bib28","first-page":"pp 287","article-title":"Brain tumor segmentation and radiomics survival prediction: contribution to the brats 2017 challenge","author":"Isensee","year":"2017"},{"key":"mlstacd5a9bib29","article-title":"Validation survival leaderboard 2020","author":"","year":"2021"},{"key":"mlstacd5a9bib30","doi-asserted-by":"publisher","first-page":"1189","DOI":"10.1214\/aos\/1013203451","article-title":"Greedy function approximation: a gradient boosting machine","volume":"29","author":"Friedman","year":"2001","journal-title":"Ann. Stat."},{"key":"mlstacd5a9bib31","doi-asserted-by":"publisher","first-page":"916","DOI":"10.1214\/07-AOAS148","article-title":"Predictive learning via rule ensembles","volume":"2","author":"Friedman","year":"2008","journal-title":"Ann. Appl. Stat."},{"key":"mlstacd5a9bib32","first-page":"pp 4768","article-title":"A unified approach to interpreting model predictions","author":"Lundberg","year":"2017"},{"key":"mlstacd5a9bib33","doi-asserted-by":"publisher","first-page":"56","DOI":"10.1038\/s42256-019-0138-9","article-title":"From local explanations to global understanding with explainable AI for trees","volume":"2","author":"Lundberg","year":"2020","journal-title":"Nat. Mach. Intell."},{"key":"mlstacd5a9bib34","doi-asserted-by":"publisher","first-page":"274","DOI":"10.4103\/0974-7788.76794","article-title":"Understanding survival analysis: Kaplan-meier estimate","volume":"1","author":"Goel","year":"2010","journal-title":"Int. J. Ayurveda Res."},{"key":"mlstacd5a9bib35","doi-asserted-by":"publisher","first-page":"e104","DOI":"10.1158\/0008-5472.CAN-17-0339","article-title":"Computational radiomics system to decode the radiographic phenotype","volume":"77","author":"Van Griethuysen","year":"2017","journal-title":"Cancer Res."},{"key":"mlstacd5a9bib36","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1504\/IJBET.2015.071405","article-title":"Wavelets: biomedical applications","volume":"19","author":"Singh","year":"2015","journal-title":"Int. J. Biomed. Eng. Technol."},{"key":"mlstacd5a9bib37","doi-asserted-by":"publisher","first-page":"1719","DOI":"10.1109\/TSMCB.2012.2228639","article-title":"A generalized Laplacian of gaussian filter for blob detection and its applications","volume":"43","author":"Kong","year":"2013","journal-title":"IEEE Trans. Cybern."},{"key":"mlstacd5a9bib38","article-title":"Scikit-learn: machine learning in python","author":"Pedregosa","year":"2012"},{"key":"mlstacd5a9bib39","article-title":"permutation_importance","author":"MIT","year":"1965"},{"key":"mlstacd5a9bib40","first-page":"3133","article-title":"Do we need hundreds of classifiers to solve real world classification problems?","volume":"15","author":"Fern\u00e1andez-Delgado","year":"2014","journal-title":"J. Mach. Learn. Res."},{"key":"mlstacd5a9bib41","first-page":"pp 199","article-title":"Segmentation of gliomas and prediction of patient overall survival: a simple and fast procedure","author":"Puybareau","year":"2019","edition":"ed"},{"key":"mlstacd5a9bib42","first-page":"pp 338","article-title":"Brain tumor segmentation and survival prediction","author":"Agravat","year":"2019"},{"key":"mlstacd5a9bib43","doi-asserted-by":"publisher","first-page":"841","DOI":"10.1214\/08-AOAS169","article-title":"Random survival forests","volume":"2","author":"Ishwaran","year":"2008","journal-title":"Annals of Applied Statistics"},{"key":"mlstacd5a9bib44","article-title":"Glioblastoma multiforme patient survival prediction","author":"Rajput","year":"2021"},{"key":"mlstacd5a9bib45","doi-asserted-by":"crossref","DOI":"10.24963\/ijcai.2022\/778","article-title":"The shapley value in machine learning","author":"Rozemberczki","year":"2022"},{"key":"mlstacd5a9bib46","author":"Molnar","year":"2021"},{"key":"mlstacd5a9bib47","doi-asserted-by":"publisher","DOI":"10.1259\/bjr.20190825","article-title":"Survival prediction for oral tongue cancer patients via probabilistic genetic algorithm optimized neural network models","volume":"93","author":"Pan","year":"2020","journal-title":"The British Journal of Radiology"},{"key":"mlstacd5a9bib48","doi-asserted-by":"publisher","first-page":"395","DOI":"10.1200\/jco.2019.37.4_suppl.395.","article-title":"The correlation between the proportion of patients with pancreatic ductal adenocarcinoma who received neoadjuvant therapy and overall survival between 2004 and 2015","volume":"37","author":"Molina","year":"2019","journal-title":"J. Clin. Oncol."},{"key":"mlstacd5a9bib49","article-title":"Regression\u2014what does the median absolute error metric say about the models? (Version: 13 April 2017)","author":"Minoru","year":"2021"},{"key":"mlstacd5a9bib50","first-page":"pp 189","article-title":"Glioma segmentation using ensemble of 2D\/3D U-Nets and survival prediction using multiple features fusion","author":"Ali","year":"2021"},{"key":"mlstacd5a9bib51","doi-asserted-by":"publisher","first-page":"269","DOI":"10.3390\/jimaging7120269","article-title":"Brain tumor segmentation based on deep learning\u2019s feature representation","volume":"7","author":"Aboussaleh","year":"2021","journal-title":"J. Imaging"},{"key":"mlstacd5a9bib52","doi-asserted-by":"publisher","first-page":"797","DOI":"10.1148\/radiol.2018180200","article-title":"Radiomic MRI phenotyping of glioblastoma: improving survival prediction","volume":"289","author":"Bae","year":"2018","journal-title":"Radiology"},{"key":"mlstacd5a9bib53","article-title":"Texture description of low grade and high grade glioma using statistical features in brain MRIs (ACEEE)","volume":"4","author":"Tessamma","year":"2010","journal-title":"Int. J. Eng. Technol."},{"key":"mlstacd5a9bib54","article-title":"Brain tumor: statistics","author":""},{"key":"mlstacd5a9bib55","doi-asserted-by":"publisher","DOI":"10.1117\/1.JMI.1.3.034007","article-title":"Interpolation-based super-resolution reconstruction: effects of slice thickness","volume":"1","author":"Mahmoudzadeh","year":"2014","journal-title":"J. Med. Imaging"},{"key":"mlstacd5a9bib56","doi-asserted-by":"publisher","first-page":"1895","DOI":"10.1007\/s00701-021-04802-6","article-title":"Survival of glioblastoma in relation to tumor location: a statistical tumor atlas of a population-based cohort","volume":"163","author":"Fyllingen","year":"2021","journal-title":"Acta Neurochir."},{"key":"mlstacd5a9bib57","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s41747-018-0068-z","article-title":"Radiomics: the facts and the challenges of image analysis","volume":"2","author":"Rizzo","year":"2018","journal-title":"Eur. Radiol. Exp."},{"key":"mlstacd5a9bib58","doi-asserted-by":"publisher","first-page":"57","DOI":"10.1080\/0952813X.2018.1518997","article-title":"Glioma grade classification using wavelet transform-local binary pattern based statistical texture features and geometric measures extracted from MRI","volume":"31","author":"Gupta","year":"2019","journal-title":"J. Exp. Theor. Artif. Intell."},{"key":"mlstacd5a9bib59","first-page":"pp 637","article-title":"Weiner filter based hough transform and wavelet feature extraction with neural network for classifying brain tumor","author":"Deepa","year":"2021"},{"key":"mlstacd5a9bib60","doi-asserted-by":"publisher","first-page":"W26","DOI":"10.2214\/AJR.13.11365","article-title":"Diffusion kurtosis imaging: an emerging technique for evaluating the microstructural environment of the brain","volume":"202","author":"Steven","year":"2014","journal-title":"Am. J. Roentgenol."},{"key":"mlstacd5a9bib61","doi-asserted-by":"crossref","DOI":"10.1201\/9781420057225-17","article-title":"Survival analysis","author":"Der","year":"2005"},{"key":"mlstacd5a9bib62","doi-asserted-by":"publisher","first-page":"709","DOI":"10.1016\/j.suronc.2018.09.002","article-title":"Overall survival prediction in glioblastoma multiforme patients from volumetric, shape and texture features using machine learning","volume":"27","author":"Sanghani","year":"2018","journal-title":"Surg. Oncol."},{"key":"mlstacd5a9bib63","article-title":"A neural ordinary differential equation model for visualizing deep neural network behaviors in multi-parametric MRI based glioma segmentation","author":"Yang","year":"2022"},{"key":"mlstacd5a9bib64","doi-asserted-by":"publisher","DOI":"10.3389\/fonc.2021.690036","article-title":"Survival prediction analysis in glioblastoma with diffusion kurtosis imaging","volume":"11","author":"Li","year":"2021","journal-title":"Front. Oncol."},{"key":"mlstacd5a9bib65","doi-asserted-by":"publisher","first-page":"293","DOI":"10.1016\/j.nic.2010.04.003","article-title":"Imaging of brain tumors: MR spectroscopy and metabolic imaging","volume":"20","author":"Horsk\u00e1","year":"2010","journal-title":"Neuroimaging Clin."},{"key":"mlstacd5a9bib66","first-page":"1989","article-title":"Glioma grading: sensitivity, specificity and predictive values of perfusion MR imaging and proton MR spectroscopic imaging compared with conventional MR imaging","volume":"24","author":"Law","year":"2003","journal-title":"Am. J. Neuroradiol."}],"container-title":["Machine Learning: Science and Technology"],"original-title":[],"link":[{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/acd5a9","content-type":"text\/html","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/acd5a9\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/acd5a9","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/acd5a9\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/acd5a9\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/acd5a9\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/acd5a9\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"similarity-checking"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/acd5a9\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,5,30]],"date-time":"2023-05-30T05:59:52Z","timestamp":1685426392000},"score":1,"resource":{"primary":{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/acd5a9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,5,30]]},"references-count":66,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2023,5,30]]},"published-print":{"date-parts":[[2023,6,1]]}},"URL":"https:\/\/doi.org\/10.1088\/2632-2153\/acd5a9","relation":{},"ISSN":["2632-2153"],"issn-type":[{"value":"2632-2153","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,5,30]]},"assertion":[{"value":"Interpretable machine learning model to predict survival days of malignant brain tumor patients","name":"article_title","label":"Article Title"},{"value":"Machine Learning: Science and Technology","name":"journal_title","label":"Journal Title"},{"value":"paper","name":"article_type","label":"Article Type"},{"value":"\u00a9 2023 The Author(s). Published by IOP Publishing Ltd","name":"copyright_information","label":"Copyright Information"},{"value":"2023-01-19","name":"date_received","label":"Date Received","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2023-05-15","name":"date_accepted","label":"Date Accepted","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2023-05-30","name":"date_epub","label":"Online publication date","group":{"name":"publication_dates","label":"Publication dates"}}]}}