{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T21:57:21Z","timestamp":1781647041856,"version":"3.54.5"},"reference-count":34,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,4,4]],"date-time":"2026-04-04T00:00:00Z","timestamp":1775260800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,5,27]],"date-time":"2026-05-27T00:00:00Z","timestamp":1779840000000},"content-version":"vor","delay-in-days":53,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Sci Rep"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>\n                    Simultaneous pancreas\u2013kidney transplantation (SPK) restores insulin independence for patients with diabetes and end-stage renal disease, yet early graft failure remains a major obstacle. We analyzed 6,725 adult SPK procedures recorded by UNOS between 2014 and 2024 to build a peri-operative risk model using Random Survival Forests (RSF). After preprocessing, MissForest imputation and LASSO screening, 21 predictors were retained. The RSF, trained on 80% of the data and tested on the remainder, achieved a Harrell C-index of 0.73 and a Uno C-index of 0.58; time-dependent AUCs were 0.75 and 0.74 at one and two years, with Brier scores of 0.075 and 0.090. Maximizing Youden\u2019s J produced a risk-score threshold of 105.24 that separated recipients into high- and low-risk strata with strongly divergent Kaplan\u2013Meier curves (log-rank\n                    <jats:italic>p<\/jats:italic>\n                    \u2009=\u20092.4e\u221216). Decision-curve analysis demonstrated net clinical benefit across threshold probabilities 0\u20130.25 and, at a 10% threshold, predicted 41 unnecessary interventions avoided per 100 patients relative to treating all. Pre-transplant insulin status, cold-ischemia time and recipient age dominated variable importance. A compact RSF based on routinely collected peri-operative data provided internally validated graft-failure risk stratification that may support peri-operative risk assessment and targeted surveillance. Prospective multi-center validation is required before clinical implementation.\n                  <\/jats:p>","DOI":"10.1038\/s41598-026-47730-0","type":"journal-article","created":{"date-parts":[[2026,4,4]],"date-time":"2026-04-04T16:27:50Z","timestamp":1775320070000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Machine learning-based risk stratification of early graft failure in simultaneous pancreas\u2013kidney transplantation"],"prefix":"10.1038","volume":"16","author":[{"given":"Omar","family":"Altamimi","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hamza","family":"Nabulsi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Majdi","family":"Al-Shehab","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yousef","family":"Abbasi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,4,4]]},"reference":[{"key":"47730_CR1","doi-asserted-by":"publisher","first-page":"208","DOI":"10.5500\/wjt.v13.i5.208","volume":"13","author":"L Nagendra","year":"2023","unstructured":"Nagendra, L., Fernandez, C. J. & Pappachan, J. M. Simultaneous pancreas-kidney transplantation for end-stage renal failure in type 1 diabetes mellitus: Current perspectives. World J. Transpl. 13, 208\u2013220 (2023).","journal-title":"World J. Transpl."},{"key":"47730_CR2","doi-asserted-by":"publisher","first-page":"2810","DOI":"10.1111\/ajt.16462","volume":"21","author":"PH Pham","year":"2021","unstructured":"Pham, P. H. et al. Large single center results of simultaneous pancreas-kidney transplantation in patients with type 2 diabetes. Am. J. Transpl. 21, 2810\u20132823 (2021).","journal-title":"Am. J. Transpl."},{"key":"47730_CR3","doi-asserted-by":"publisher","first-page":"S138","DOI":"10.1016\/j.ajt.2025.01.021","volume":"25","author":"R Kandaswamy","year":"2025","unstructured":"Kandaswamy, R. et al. OPTN\/SRTR 2023 Annual Data Report: Pancreas. Am. J. Transplant. 25, S138\u2013S192 (2025).","journal-title":"Am. J. Transplant."},{"key":"47730_CR4","first-page":"160","volume":"128","author":"RC Ziegelstein","year":"2017","unstructured":"Ziegelstein, R. C. Personomics and precision medicine. Trans. Am. Clin. Climatol. Assoc. 128, 160 (2017).","journal-title":"Trans. Am. Clin. Climatol. Assoc."},{"key":"47730_CR5","doi-asserted-by":"publisher","first-page":"132","DOI":"10.1002\/phar.2484","volume":"41","author":"AQ Maldonado","year":"2021","unstructured":"Maldonado, A. Q., West-Thielke, P., Joyal, K. & Rogers, C. Advances in personalized medicine and noninvasive diagnostics in solid organ transplantation. Pharmacotherapy 41, 132\u2013143 (2021).","journal-title":"Pharmacotherapy"},{"key":"47730_CR6","doi-asserted-by":"publisher","first-page":"10639","DOI":"10.3389\/ti.2022.10639","volume":"35","author":"J Rovira","year":"2022","unstructured":"Rovira, J. et al. Immune profiling of peripheral blood mononuclear cells at pancreas acute rejection episodes in kidney-pancreas transplant recipients. Transpl. Int. 35, 10639 (2022).","journal-title":"Transpl. Int."},{"key":"47730_CR7","first-page":"228","volume":"16","author":"CE Duff","year":"2017","unstructured":"Duff, C. E. & Simmonds, M. J. Genetic predictors of long-term graft function in kidney and pancreas transplant patients. Brief. Funct. Genomics. 16, 228\u2013237 (2017).","journal-title":"Brief. Funct. Genomics"},{"key":"47730_CR8","doi-asserted-by":"publisher","first-page":"11792","DOI":"10.3389\/ti.2023.11792","volume":"36","author":"RV Owen","year":"2024","unstructured":"Owen, R. V. et al. Multi-Centre UK analysis of simultaneous pancreas and kidney (SPK) transplant in recipients with type 2 diabetes mellitus. Transpl. Int. 36, 11792 (2024).","journal-title":"Transpl. Int."},{"key":"47730_CR9","doi-asserted-by":"publisher","first-page":"12864","DOI":"10.3389\/ti.2024.12864","volume":"37","author":"NX Ho","year":"2024","unstructured":"Ho, N. X. et al. Donor blood tests do not predict pancreas graft survival after simultaneous pancreas kidney transplantation; a National Cohort Study. Transpl. Int. 37, 12864 (2024).","journal-title":"Transpl. Int."},{"key":"47730_CR10","doi-asserted-by":"publisher","first-page":"1071","DOI":"10.3390\/jpm13071071","volume":"13","author":"E Vigia","year":"2023","unstructured":"Vigia, E. et al. Pancreas rejection in the artificial intelligence era: New tool for signal patients at risk. J. Pers. Med. 13, 1071 (2023).","journal-title":"J. Pers. Med."},{"key":"47730_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. & Lauer, M. S. Random survival forests. Annals Appl. Stat. 2, 841\u2013860 (2008).","journal-title":"Annals Appl. Stat."},{"key":"47730_CR12","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2502.03119","author":"R Graf","year":"2025","unstructured":"Graf, R., Todd, S. & Baksh, M. F. Comparison of the Cox proportional hazards model and Random Survival Forest algorithm for predicting patient-specific survival probabilities in clinical trial data. Preprint at. https:\/\/doi.org\/10.48550\/arXiv.2502.03119 (2025).","journal-title":"Preprint at."},{"key":"47730_CR13","unstructured":"Kidney allocation system - OPTN. https:\/\/optn.transplant.hrsa.gov\/professionals\/by-organ\/kidney-pancreas\/kidney-allocation-system\/"},{"key":"47730_CR14","unstructured":"OPTN Policies. (2025). https:\/\/optn.transplant.hrsa.gov\/media\/eavh5bf3\/optn_policies.pdf"},{"key":"47730_CR15","unstructured":"Python Language Reference, Version 3.11.4. (Python Software Foundation, Wilmington, DE, (2023)."},{"key":"47730_CR16","doi-asserted-by":"publisher","unstructured":"The pandas development team. pandas-dev\/pandas: Pandas. Zenodo. https:\/\/doi.org\/10.5281\/zenodo.13819579 (2024).","DOI":"10.5281\/zenodo.13819579"},{"key":"47730_CR17","doi-asserted-by":"publisher","first-page":"162","DOI":"10.1186\/s12874-017-0442-1","volume":"17","author":"JC Jakobsen","year":"2017","unstructured":"Jakobsen, J. C., Gluud, C., Wetterslev, J. & Winkel, P. When and how should multiple imputation be used for handling missing data in randomised clinical trials \u2013 a practical guide with flowcharts. BMC Med. Res. Methodol. 17, 162 (2017).","journal-title":"BMC Med. Res. Methodol."},{"key":"47730_CR18","doi-asserted-by":"publisher","first-page":"112","DOI":"10.1093\/bioinformatics\/btr597","volume":"28","author":"DJ Stekhoven","year":"2012","unstructured":"Stekhoven, D. J. & B\u00fchlmann, P. MissForest\u2014non-parametric missing value imputation for mixed-type data. Bioinformatics 28, 112\u2013118 (2012).","journal-title":"Bioinformatics"},{"key":"47730_CR19","doi-asserted-by":"publisher","unstructured":"Ness, M. V., Bosschieter, T. M., Halpin-Gregorio, R. & Udell, M. The Missing Indicator Method: From Low to High Dimensions. in Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining 5004\u20135015 (2023). https:\/\/doi.org\/10.1145\/3580305.3599911","DOI":"10.1145\/3580305.3599911"},{"key":"47730_CR20","doi-asserted-by":"publisher","unstructured":"Akiba, T. et al. A next-generation hyperparameter optimization framework. In Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining 2623\u20132631 (Association for Computing Machinery, 2019). https:\/\/doi.org\/10.1145\/3292500.3330701","DOI":"10.1145\/3292500.3330701"},{"key":"47730_CR21","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., D\u2019Agostino, R. B. & Wei, L. J. On the C-statistics for evaluating overall adequacy of risk prediction procedures with censored survival data. Stat. Med. 30, 1105\u20131117 (2011).","journal-title":"Stat. Med."},{"key":"47730_CR22","doi-asserted-by":"publisher","first-page":"32","DOI":"10.1002\/1097-0142(1950)3:1<32::AID-CNCR2820030106>3.0.CO;2-3","volume":"3","author":"WJ Youden","year":"1950","unstructured":"Youden, W. J. Index for rating diagnostic tests. Cancer 3, 32\u201335 (1950).","journal-title":"Cancer"},{"key":"47730_CR23","doi-asserted-by":"publisher","first-page":"565","DOI":"10.1177\/0272989X06295361","volume":"26","author":"AJ Vickers","year":"2006","unstructured":"Vickers, A. J. & Elkin, E. B. Decision curve analysis: a novel method for evaluating prediction models. Med. Decis. Mak. 26, 565\u2013574 (2006).","journal-title":"Med. Decis. Mak."},{"key":"47730_CR24","unstructured":"Sharma, A. et al. Machine learning prediction for De Novo Donor specific antibodies (dnDSA), antibody-mediated rejection and graft loss in simultaneous kidney\u2013pancreas (SPK) transplant recipients. In 60th Annual Scientific Meeting of the Australian and New Zealand Society of Nephrology (ANZSN 2018) \u2013 Abstracts (Sydney, 2018)."},{"key":"47730_CR25","doi-asserted-by":"publisher","first-page":"277","DOI":"10.1186\/s12874-020-01153-1","volume":"20","author":"G Kantidakis","year":"2020","unstructured":"Kantidakis, G. et al. Survival prediction models since liver transplantation - comparisons between Cox models and machine learning techniques. BMC Med. Res. Methodol. 20, 277 (2020).","journal-title":"BMC Med. Res. Methodol."},{"key":"47730_CR26","doi-asserted-by":"publisher","first-page":"e0313600","DOI":"10.1371\/journal.pone.0313600","volume":"20","author":"L Liou","year":"2025","unstructured":"Liou, L. et al. Survival machine learning methods for mortality prediction after heart transplantation in the contemporary era. PLoS One. 20, e0313600 (2025).","journal-title":"PLoS One"},{"key":"47730_CR27","doi-asserted-by":"publisher","first-page":"359","DOI":"10.1186\/s12882-022-02996-0","volume":"23","author":"B Huang","year":"2022","unstructured":"Huang, B. et al. Individual dynamic prediction and prognostic analysis for long-term allograft survival after kidney transplantation. BMC Nephrol. 23, 359 (2022).","journal-title":"BMC Nephrol."},{"key":"47730_CR28","doi-asserted-by":"publisher","first-page":"18","DOI":"10.1186\/s41512-019-0064-7","volume":"3","author":"AJ Vickers","year":"2019","unstructured":"Vickers, A. J., van Calster, B. & Steyerberg, E. W. A simple, step-by-step guide to interpreting decision curve analysis. Diagn. Prognostic Res. 3, 18 (2019).","journal-title":"Diagn. Prognostic Res."},{"key":"47730_CR29","doi-asserted-by":"publisher","first-page":"186","DOI":"10.4103\/ijnpnd.ijnpnd_32_22","volume":"12","author":"T Tunthanathip","year":"2022","unstructured":"Tunthanathip, T., Sae-Heng, S., Oearsakul, T., Kaewborisutsakul, A. & Taweesomboonyat, C. Impact of machine learning prediction on intraoperative transfusion in cranial operation: Classification, regression, and decision curve analysis. Int. J. Nutr. Pharmacol. Neurol. Dis. 12, 186 (2022).","journal-title":"Int. J. Nutr. Pharmacol. Neurol. Dis."},{"key":"47730_CR30","unstructured":"Kidney\/Pancreas Post 5-Year Transplant Recipient Follow-up (TRF) Record Field Descriptions. (2014). https:\/\/omb.report\/icr\/201411-0915-004\/doc\/52091101.pdf"},{"key":"47730_CR31","doi-asserted-by":"crossref","unstructured":"Lum, E. L., Homkrailas, P., Abdalla, B., Danovitch, G. M. & Bunnapradist, S. Cold ischemia time, kidney donor profile index, and kidney transplant outcomes: A cohort study. Kidney Medicine 5, 100570 (2023).","DOI":"10.1016\/j.xkme.2022.100570"},{"key":"47730_CR32","doi-asserted-by":"publisher","first-page":"1270","DOI":"10.3390\/jcm13051270","volume":"13","author":"M\u00c1 P\u00e9rez Valdivia","year":"2024","unstructured":"P\u00e9rez Valdivia, M. \u00c1. et al. Predicting kidney transplantation outcomes from donor and recipient characteristics at time zero: Development of a mobile application for nephrologists. J. Clin. Med. 13, 1270 (2024).","journal-title":"J. Clin. Med."},{"key":"47730_CR33","doi-asserted-by":"publisher","first-page":"10656","DOI":"10.3389\/ti.2022.10656","volume":"35","author":"F Jarrar","year":"2022","unstructured":"Jarrar, F., Tennankore, K. K. & Vinson, A. J. Combined donor-recipient obesity and the risk of graft loss after kidney transplantation. Transpl. Int. 35, 10656 (2022).","journal-title":"Transpl. Int."},{"key":"47730_CR34","doi-asserted-by":"publisher","first-page":"1106087","DOI":"10.3389\/fendo.2023.1106087","volume":"14","author":"MI Bellini","year":"2023","unstructured":"Bellini, M. I., Deurloo, E., Consorti, F. & Herbert, P. E. Body mass index affects kidney transplant outcomes: A cohort study over 5 years using a steroid sparing protocol. Front. Endocrinol. (Lausanne). 14, 1106087 (2023).","journal-title":"Front. Endocrinol. (Lausanne)"}],"container-title":["Scientific Reports"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-47730-0","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-47730-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-47730-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T21:29:13Z","timestamp":1781645353000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-47730-0"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,4]]},"references-count":34,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,12]]}},"alternative-id":["47730"],"URL":"https:\/\/doi.org\/10.1038\/s41598-026-47730-0","relation":{},"ISSN":["2045-2322"],"issn-type":[{"value":"2045-2322","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4,4]]},"assertion":[{"value":"29 August 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"2 April 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"4 April 2026","order":3,"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 no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}},{"value":"This study used secondary de-identified registry data obtained from the Organ Procurement and Transplantation Network (OPTN) \/ United Network for Organ Sharing (UNOS) through a formal data request process and under a Data Use Agreement. The dataset provided to the authors did not contain direct personal identifiers, and individual participants were not directly traceable by the study team. Per institutional policy at the University of Jordan, the use of these de-identified registry data was exempt from IRB review. OPTN data are collected under the oversight of institutional review boards at participating U.S. transplant centers at the time of data acquisition. The present study included adult recipients only (aged\u2009\u2265\u200918 years) and did not involve direct participant contact, newly collected biospecimens, identifiable participant information, or participant images; therefore, parental\/guardian consent and consent for publication of identifiable material were not applicable. The UNOS Ethics Committee has published an ethics statement expressing opposition to organ donation from condemned prisoners. This study was a secondary analysis of OPTN\/UNOS registry data from transplant procedures performed in the United States. The authors had no role in organ or tissue procurement. The organs and tissues represented in the dataset were procured through U.S. transplant centers and organ procurement organizations participating in the OPTN. Additionally, as this was a registry-based secondary analysis, the authors do not maintain an independent center-by-center procurement listing beyond the OPTN\/UNOS registry framework.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical approval"}}],"article-number":"16323"}}