{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,2]],"date-time":"2026-09-02T09:15:07Z","timestamp":1788340507856,"version":"build-2803163510"},"reference-count":48,"publisher":"MDPI AG","issue":"9","license":[{"start":{"date-parts":[[2026,9,2]],"date-time":"2026-09-02T00:00:00Z","timestamp":1788307200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Curr. Oncol.","Current Oncology"],"abstract":"<jats:p>Purpose: Although machine learning-based prediction of overall survival (OS) in palliative radiotherapy for bone metastases has been investigated, explainable deep learning (DL) models remain underexplored. This study aimed to develop and validate an explainable DL model to predict OS in this setting, and to examine whether this flexible model provides predictive value beyond a standard Cox model based on routinely collected baseline variables. Methods and Materials: We analyzed all 472 eligible patients who received palliative radiotherapy for bone metastases between January 2013 and August 2024; patients alive with less than one year of follow-up were retained as right-censored observations. The primary endpoint was OS over a fixed 1-year horizon. A DeepSurv model using 14 baseline predictors, including the planned prescribed dose (biologically effective dose, BED10), was developed with repeated 5-fold cross-validation (K = 5, R = 10) and compared with standard and ridge-penalized Cox models fitted on identical splits. Performance was assessed by the time-dependent concordance index (C-index), integrated Brier score (IBS), time-dependent area under the curve (AUC) at 90, 180, and 365 days, and a calibration analysis at one year; 95% confidence intervals (CI) were obtained by patient-level bootstrapping of the pooled out-of-fold predictions. Shapley Additive Explanations (SHAP) and SurvLIME were computed on the held-out test sets. Results: Within one year, 242 patients (51.3%) died; median OS was 225 days (95% CI: 189\u2013287). The DeepSurv model achieved a pooled time-dependent C-index of 0.779 (95% CI: 0.751\u20130.807), an IBS of 0.135 (95% CI: 0.122\u20130.149), and AUCs of 0.892 (0.857\u20130.925), 0.862 (0.822\u20130.895), and 0.856 (0.814\u20130.895) at 90, 180, and 365 days, with an observed\/expected ratio of 0.94 and a calibration slope of 1.02; discrimination was comparable to the Cox model (C-index 0.763, 95% CI: 0.737\u20130.789). SHAP identified poor performance status as the dominant predictor (mean |SHAP| 0.178), followed by male sex (0.067), high-risk primary tumor type (0.063), multiple bone metastases (0.047), and planned dose (0.033), the latter being the only leading feature associated with lower predicted mortality; SurvLIME gave consistent results. In multivariable Cox analysis, performance status (hazard ratio [HR] 2.21 per standard deviation [SD], p &lt; 0.001) and planned dose (HR 0.71 per SD, p &lt; 0.001) were independently associated with OS. Conclusions: The explainable DL model predicted OS after palliative radiotherapy for bone metastases with discrimination and calibration comparable to those of a well-specified Cox model, and its feature attributions agreed with the Cox coefficients, suggesting that the prognostic information in these baseline variables is essentially additive and can therefore be delivered at the bedside as a simple score, without dedicated AI infrastructure and without loss of predictive performance. The combined use of SHAP and SurvLIME verified that the model relies on established clinical factors, most prominently performance status, and provides patient-level explanations. Pending external validation, such prediction may support individualized decisions on treatment goals and radiation schedules.<\/jats:p>","DOI":"10.3390\/curroncol33090528","type":"journal-article","created":{"date-parts":[[2026,9,2]],"date-time":"2026-09-02T07:53:11Z","timestamp":1788335591000},"page":"528","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Explainable Deep Learning Model for Predicting Overall Survival in Patients Receiving Palliative Radiotherapy for Bone Metastases"],"prefix":"10.3390","volume":"33","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1958-8196","authenticated-orcid":false,"given":"Yui","family":"Watanabe","sequence":"first","affiliation":[{"name":"Department of Radiology, Daiyukai General Hospital, Ichinomiya 491-8551, Japan"}],"role":[{"vocabulary":"crossref","role":"author"},{"role":"conceptualization","vocabulary":"credit"},{"role":"methodology","vocabulary":"credit"},{"role":"software","vocabulary":"credit"},{"role":"validation","vocabulary":"credit"},{"role":"formal-analysis","vocabulary":"credit"},{"role":"investigation","vocabulary":"credit"},{"role":"resources","vocabulary":"credit"},{"role":"data-curation","vocabulary":"credit"},{"role":"writing-original-draft","vocabulary":"credit"},{"role":"writing-review-editing","vocabulary":"credit"}]},{"given":"Takuya","family":"Tomoda","sequence":"additional","affiliation":[{"name":"Department of Radiology, Daiyukai General Hospital, Ichinomiya 491-8551, Japan"}],"role":[{"vocabulary":"crossref","role":"author"},{"role":"supervision","vocabulary":"credit"}]},{"given":"Akiko","family":"Iwata","sequence":"additional","affiliation":[{"name":"Department of Radiology, Daiyukai General Hospital, Ichinomiya 491-8551, Japan"}],"role":[{"vocabulary":"crossref","role":"author"},{"role":"supervision","vocabulary":"credit"}]},{"given":"Hirokazu","family":"Matsuno","sequence":"additional","affiliation":[{"name":"Department of Radiology, Daiyukai General Hospital, Ichinomiya 491-8551, Japan"}],"role":[{"vocabulary":"crossref","role":"author"},{"role":"supervision","vocabulary":"credit"}]},{"given":"Hiroto","family":"Hayakawa","sequence":"additional","affiliation":[{"name":"Department of Radiology, Daiyukai General Hospital, Ichinomiya 491-8551, Japan"}],"role":[{"vocabulary":"crossref","role":"author"},{"role":"supervision","vocabulary":"credit"}]},{"given":"Takeshi","family":"Nagata","sequence":"additional","affiliation":[{"name":"Department of Radiology, Daiyukai General Hospital, Ichinomiya 491-8551, Japan"}],"role":[{"vocabulary":"crossref","role":"author"},{"role":"supervision","vocabulary":"credit"}]}],"member":"1968","published-online":{"date-parts":[[2026,9,2]]},"reference":[{"key":"ref_1","first-page":"53","article-title":"Metastatic and histologic presentations in unknown primary cancer","volume":"4","author":"Nystrom","year":"1977","journal-title":"Semin. Oncol."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"165","DOI":"10.1053\/ctrv.2000.0210","article-title":"Metastatic bone disease: Clinical features, pathophysiology and treatment strategies","volume":"27","author":"Coleman","year":"2001","journal-title":"Cancer Treat. Rev."},{"key":"ref_3","first-page":"e2021552","article-title":"Surgical management of tibial metastases: A systematic review","volume":"92","author":"Greco","year":"2022","journal-title":"Acta Biomed."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"41","DOI":"10.1007\/s10555-007-9109-4","article-title":"The bone microenvironment in metastasis; what is special about bone?","volume":"27","author":"Bussard","year":"2008","journal-title":"Cancer Metastasis Rev."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"400","DOI":"10.1016\/j.jacr.2010.02.015","article-title":"ACR appropriateness criteria\u00ae on metastatic bone disease","volume":"7","author":"Roberts","year":"2010","journal-title":"J. Am. Coll. Radiol."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"20120519","DOI":"10.1259\/bjr.20120519","article-title":"SPECT-CT: Applications in musculoskeletal radiology","volume":"86","author":"Saha","year":"2013","journal-title":"Br. J. Radiol."},{"key":"ref_7","first-page":"374","article-title":"Diagnosis of bone metastasis: Recent comparative studies of imaging modalities","volume":"55","author":"Talbot","year":"2011","journal-title":"Q. J. Nucl. Med. Mol. Imaging"},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Watanabe, Y., Tomoda, T., Iwata, A., Matsuno, H., Hayakawa, H., and Nagata, T. (2026). A novel scoring system based on post-radiotherapy changes in pain, performance status, and adverse events to stratify survival in bone metastases. Sci. Rep., in press.","DOI":"10.1038\/s41598-026-61175-5"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1016\/j.radonc.2020.09.059","article-title":"Early alteration in apparent diffusion coefficient and tumor volume in cervical cancer treated with chemoradiotherapy or radiotherapy: Incremental prognostic value over pretreatment assessments","volume":"155","author":"Watanabe","year":"2021","journal-title":"Radiother. Oncol."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"104","DOI":"10.1016\/j.radonc.2021.02.011","article-title":"Survival after palliative radiation therapy for cancer: The METSSS model","volume":"158","author":"Zaorsky","year":"2021","journal-title":"Radiother. Oncol."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"303","DOI":"10.1093\/jrr\/rrab121","article-title":"Prediction of post-radiotherapy survival for bone metastases: A comparison of the 3-variable number of risk factors model with the new Katagiri scoring system","volume":"63","author":"Sakurai","year":"2022","journal-title":"J. Radiat. Res."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"1900","DOI":"10.21037\/apm-21-2657","article-title":"Palliative radiation for bone metastases from hepatocellular carcinoma: Practice patterns and the amount of remaining life spent receiving treatment","volume":"11","author":"Schmid","year":"2022","journal-title":"Ann. Palliat. Med."},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Papalia, G.F., Brigato, P., Sisca, L., Maltese, G., Faiella, E., Santucci, D., Pantano, F., Vincenzi, B., Tonini, G., and Papalia, R. (2024). Artificial intelligence in detection, management, and prognosis of bone metastasis: A systematic review. Cancers, 16.","DOI":"10.3390\/cancers16152700"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"e2400027","DOI":"10.1200\/CCI.24.00027","article-title":"Explainable machine learning model to predict overall survival in patients treated with palliative radiotherapy for bone metastases","volume":"8","author":"Cilla","year":"2024","journal-title":"JCO Clin. Cancer Inform."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"159","DOI":"10.1016\/j.radonc.2022.08.029","article-title":"Prognostic significance of lab data and performance comparison by validating survival prediction models for patients with spinal metastases after radiotherapy","volume":"175","author":"Yen","year":"2022","journal-title":"Radiother. Oncol."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"304","DOI":"10.1200\/CCI.20.00128","article-title":"External validation of the bone metastases ensemble trees for survival (BMETS) machine learning model to predict survival in patients with symptomatic bone metastases","volume":"5","author":"Elledge","year":"2021","journal-title":"JCO Clin. Cancer Inform."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"1471","DOI":"10.21873\/anticanres.14905","article-title":"Independent validation of a comprehensive machine learning approach predicting survival after radiotherapy for bone metastases","volume":"41","author":"Nieder","year":"2021","journal-title":"Anticancer Res."},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Ong, W., Lee, A., Tan, W.C., Fong, K.T., Lai, D.D., Tan, Y.L., Low, X.Z., Ge, S., Makmur, A., and Ong, S.J. (2024). Oncologic applications of artificial intelligence and deep learning methods in CT spine imaging\u2014A systematic review. Cancers, 16.","DOI":"10.3390\/cancers16172988"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"100682","DOI":"10.1016\/j.jbo.2025.100682","article-title":"Artificial Intelligence in bone Metastases: A systematic review in guideline adherence of 92 studies","volume":"52","author":"Vavliakis","year":"2025","journal-title":"J. Bone Oncol."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"210","DOI":"10.1177\/21925682241261342","article-title":"Machine learning in spine oncology: A narrative review","volume":"15","author":"Wilson","year":"2025","journal-title":"Glob. Spine J."},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Sanker, V., Dawer, P., Thaller, A., Li, Z., Heesen, P., Hariharan, S., Nordin, E.O.R., Cavagnaro, M.J., Ratliff, J., and Desai, A. (2025). Artificial Intelligence Models for Predicting Outcomes in Spinal Metastasis: A Systematic Review and Meta-Analysis. J. Clin. Med., 14.","DOI":"10.3390\/jcm14165885"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"110084","DOI":"10.1016\/j.radonc.2024.110084","article-title":"Explainable deep learning-based survival prediction for non-small cell lung cancer patients undergoing radical radiotherapy","volume":"193","author":"Astley","year":"2024","journal-title":"Radiother. Oncol."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"1359","DOI":"10.1002\/cam4.292","article-title":"New prognostic factors and scoring system for patients with skeletal metastasis","volume":"3","author":"Katagiri","year":"2014","journal-title":"Cancer Med."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"2816","DOI":"10.1002\/cncr.23888","article-title":"Prognostic factors and a scoring system for survival after radiotherapy for metastases to the spinal column: A review of 544 patients at Shizuoka Cancer Center Hospital","volume":"113","author":"Mizumoto","year":"2008","journal-title":"Cancer"},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"13","DOI":"10.1186\/s13014-019-1218-z","article-title":"Predicting the survival of patients with bone metastases treated with radiation therapy: A validation study of the Katagiri scoring system","volume":"14","author":"Kubota","year":"2019","journal-title":"Radiat. Oncol."},{"key":"ref_26","first-page":"646","article-title":"Survival prediction nomogram for patients with vertebral bone metastases treated with palliative radiotherapy","volume":"28","author":"Takeda","year":"2023","journal-title":"Rep. Pract. Oncol. Radiother."},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Katzman, J.L., Shaham, U., Cloninger, A., Bates, J., Jiang, T., and Kluger, Y. (2018). DeepSurv: Personalized treatment recommender system using a Cox proportional hazards deep neural network. BMC Med. Res. Methodol., 18.","DOI":"10.1186\/s12874-018-0482-1"},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"3927","DOI":"10.1002\/sim.2427","article-title":"A time-dependent discrimination index for survival data","volume":"24","author":"Antolini","year":"2005","journal-title":"Stat. Med."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"2529","DOI":"10.1002\/(SICI)1097-0258(19990915\/30)18:17\/18<2529::AID-SIM274>3.0.CO;2-5","article-title":"Assessment and comparison of prognostic classification schemes for survival data","volume":"18","author":"Graf","year":"1999","journal-title":"Stat. Med."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"527","DOI":"10.1198\/016214507000000149","article-title":"Evaluating prediction rules for t-year survivors with censored regression models","volume":"102","author":"Uno","year":"2007","journal-title":"J. Am. Stat. Assoc."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"e87","DOI":"10.1016\/j.clon.2021.12.002","article-title":"Deep learning for radiotherapy outcome prediction using dose data\u2014A review","volume":"34","author":"Appelt","year":"2022","journal-title":"Clin. Oncol."},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Tam, A., Scarpi, E., Maltoni, M.C., Rossi, R., Fairchild, A., Dennis, K., Vaska, M., and Kerba, M. (2024). A Systematic Review of Prognostic Factors in Patients with Cancer Receiving Palliative Radiotherapy: Evidence-Based Recommendations. Cancers, 16.","DOI":"10.3390\/cancers16091654"},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"320","DOI":"10.1002\/cncr.20756","article-title":"Dutch Bone Metastasis Study Group. Prediction of survival in patients with metastases in the spinal column: Results based on a randomized trial of radiotherapy","volume":"103","author":"Dijkstra","year":"2005","journal-title":"Cancer"},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"739","DOI":"10.1016\/j.ijrobp.2014.07.051","article-title":"An easy tool to predict survival in patients receiving radiation therapy for painful bone metastases","volume":"90","author":"Westhoff","year":"2014","journal-title":"Int. J. Radiat. Oncol. Biol. Phys."},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"Watanabe, Y., Koide, Y., Shimizu, H., Aoyama, T., Shindo, Y., Hashimoto, S., Tachibana, H., and Kodaira, T. (2024). Risk stratification by combination of heart and lung dose in locally advanced non-small-cell lung cancer after radiotherapy. Cancers, 16.","DOI":"10.3390\/cancers16193255"},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"e420","DOI":"10.1016\/j.cllc.2025.05.002","article-title":"Combined Impact of Coronary Artery Calcification and Heart Radiation Dose on Overall Survival in Locally Advanced Non-Small Cell Lung Cancer: Who Benefits Most from Reducing Heart Radiation Dose?","volume":"26","author":"Watanabe","year":"2025","journal-title":"Clin. Lung Cancer"},{"key":"ref_37","doi-asserted-by":"crossref","unstructured":"Lehtonen, M., Heiskanen, L., Reinikainen, P., and Kellokumpu-Lehtinen, P.L. (2020). Both comorbidity and worse performance status are associated with poorer overall survival after external beam radiotherapy for prostate cancer. BMC Cancer, 20.","DOI":"10.1186\/s12885-020-06812-6"},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"98974","DOI":"10.18632\/oncotarget.21940","article-title":"Pretreatment nutritional risk scores and performance status are prognostic factors in esophageal cancer patients treated with definitive chemoradiotherapy","volume":"8","author":"Song","year":"2017","journal-title":"Oncotarget"},{"key":"ref_39","first-page":"100352","article-title":"The prognostic effect of coronary artery calcification in locally advanced non-small cell lung cancer: An independent prognostic factor after adjustment for clinical and dosimetric variables","volume":"3","author":"Watanabe","year":"2025","journal-title":"RCR Open"},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"1722","DOI":"10.21873\/invivo.14323","article-title":"Impact of heart dose on survival in palliative radiotherapy for bone metastases: Propensity score-matched analysis","volume":"40","author":"Watanabe","year":"2026","journal-title":"In Vivo"},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"377","DOI":"10.1016\/j.prro.2024.04.018","article-title":"External beam radiation therapy for palliation of symptomatic bone metastases: An ASTRO clinical practice guideline","volume":"14","author":"Alcorn","year":"2024","journal-title":"Pract. Radiat. Oncol."},{"key":"ref_42","doi-asserted-by":"crossref","first-page":"245","DOI":"10.1016\/j.radonc.2006.02.007","article-title":"Patients with a favourable prognosis are equally palliated with single and multiple fraction radiotherapy: Results on survival in the Dutch Bone Metastasis Study","volume":"78","author":"Steenland","year":"2006","journal-title":"Radiother. Oncol."},{"key":"ref_43","doi-asserted-by":"crossref","first-page":"2087","DOI":"10.1002\/cam4.1150","article-title":"Dose-escalated radiation therapy is associated with better overall survival in patients with bone metastases from solid tumors: A propensity score-matched study","volume":"6","author":"Chou","year":"2017","journal-title":"Cancer Med."},{"key":"ref_44","doi-asserted-by":"crossref","first-page":"7934","DOI":"10.1002\/cam4.4304","article-title":"Association of radiation dose intensity with overall survival in patients with distant metastases","volume":"10","author":"Kao","year":"2021","journal-title":"Cancer Med."},{"key":"ref_45","doi-asserted-by":"crossref","first-page":"674","DOI":"10.1016\/j.clon.2020.05.003","article-title":"Palliative lung radiotherapy: Higher dose leads to improved survival?","volume":"32","author":"Lewis","year":"2020","journal-title":"Clin. Oncol."},{"key":"ref_46","doi-asserted-by":"crossref","first-page":"134","DOI":"10.1002\/cncr.28408","article-title":"Predicting life expectancy in patients with metastatic cancer receiving palliative radiotherapy: The TEACHH model","volume":"120","author":"Krishnan","year":"2014","journal-title":"Cancer"},{"key":"ref_47","doi-asserted-by":"crossref","first-page":"5863","DOI":"10.1200\/JCO.2008.17.1363","article-title":"Predictive model for survival in patients with advanced cancer","volume":"26","author":"Chow","year":"2008","journal-title":"J. Clin. Oncol."},{"key":"ref_48","doi-asserted-by":"crossref","unstructured":"Rades, D., Haus, R., Schild, S.E., and Janssen, S. (2019). Prognostic factors and a new scoring system for survival of patients irradiated for bone metastases. BMC Cancer, 19.","DOI":"10.1186\/s12885-019-6385-7"}],"container-title":["Current Oncology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1718-7729\/33\/9\/528\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,2]],"date-time":"2026-09-02T08:25:34Z","timestamp":1788337534000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1718-7729\/33\/9\/528"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,2]]},"references-count":48,"journal-issue":{"issue":"9","published-online":{"date-parts":[[2026,9]]}},"alternative-id":["curroncol33090528"],"URL":"https:\/\/doi.org\/10.3390\/curroncol33090528","relation":{},"ISSN":["1718-7729"],"issn-type":[{"value":"1718-7729","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,2]]}}}