{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,16]],"date-time":"2026-10-16T19:56:50Z","timestamp":1792180610478,"version":"4.4.0"},"reference-count":33,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2025,10,2]],"date-time":"2025-10-02T00:00:00Z","timestamp":1759363200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Artif. Intell."],"abstract":"<jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Accurate prediction of kidney graft failure at different phases post-transplantation is critical for timely intervention and long-term allograft preservation. Traditional survival models offer limited capacity for dynamic, time-specific risk estimation. Machine learning (ML) approaches, with their ability to model complex patterns, present a promising alternative.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>This study developed and dynamically evaluated phase-specific ML models to predict kidney graft failure across five post-transplant intervals: 0\u20133\u202fmonths, 3\u20139\u202fmonths, 9\u201315\u202fmonths, 15\u201339\u202fmonths, and 39\u201372\u202fmonths. Clinically relevant retrospective data from deceased donor kidney transplant recipients were used for training and internal validation, with performance further confirmed on a blinded external validation cohort. Predictive performance was assessed using ROC AUC, F1 score, and G-mean.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>The ML models demonstrated varying performance across time intervals. Short-term predictions in the 0\u20133\u202fmonth and 3\u20139\u202fmonth intervals yielded moderate accuracy (ROC AUC\u202f=\u202f0.73\u202f\u00b1\u202f0.07 and 0.72\u202f\u00b1\u202f0.04, respectively). The highest predictive accuracy observed in mid-term or the 9\u201315-month window (ROC AUC\u202f=\u202f0.92\u202f\u00b1\u202f0.02; F1 score\u202f=\u202f0.85\u202f\u00b1\u202f0.03), followed by the 15\u201339-month period (ROC AUC\u202f=\u202f0.84\u202f\u00b1\u202f0.04; F1 score\u202f=\u202f0.76\u202f\u00b1\u202f0.04). Long-term prediction from 39 to 72 months was more challenging (ROC AUC\u202f=\u202f0.70\u202f\u00b1\u202f0.07; F1 score\u202f=\u202f0.65\u202f\u00b1\u202f0.06).<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>Phase-specific ML models offer robust predictive performance for kidney graft failure, particularly in mid-term periods, supporting their integration into dynamic post-transplant surveillance strategies. These models can aid clinicians in identifying high-risk patients and tailoring follow-up protocols to optimize long-term transplant outcomes.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/frai.2025.1682639","type":"journal-article","created":{"date-parts":[[2025,10,2]],"date-time":"2025-10-02T05:34:31Z","timestamp":1759383271000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":4,"title":["Phase-specific kidney graft failure prediction with machine learning model"],"prefix":"10.3389","volume":"8","author":[{"given":"Amankeldi A.","family":"Salybekov","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Markus","family":"Wolfien","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ainur","family":"Yerkos","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zholdas","family":"Buribayev","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sumi","family":"Hidaka","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shuzo","family":"Kobayashi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2025,10,2]]},"reference":[{"key":"ref1","doi-asserted-by":"publisher","first-page":"100253","DOI":"10.1016\/j.liver.2024.100253","article-title":"Predictive models for post-liver transplant survival using machine learning techniques in three critical time intervals","volume":"17","author":"Abdollahzade","year":"2025","journal-title":"J. Liver Transpl."},{"key":"ref2","doi-asserted-by":"publisher","first-page":"1790","DOI":"10.1093\/ndt\/gfu216","article-title":"European renal best practice guideline on kidney donor and recipient evaluation and perioperative care","volume":"30","author":"Abramowicz","year":"2015","journal-title":"Nephrol. Dial. Transplant."},{"key":"ref4","doi-asserted-by":"publisher","first-page":"1265","DOI":"10.1681\/ASN.2021071020","article-title":"Transplantation mediates much of the racial disparity in survival from childhood-onset kidney failure","volume":"33","author":"Becerra","year":"2022","journal-title":"J Am Soc Nephrol"},{"key":"ref5","doi-asserted-by":"publisher","first-page":"709","DOI":"10.1016\/S0140-6736(20)30045-3","article-title":"Global, regional, and National Burden of chronic kidney disease, 1990\u20132017: a systematic analysis for the global burden of disease study 2017","volume":"395","author":"Bikbov","year":"2020","journal-title":"Lancet"},{"key":"ref6","doi-asserted-by":"publisher","first-page":"e16186","DOI":"10.1097\/MD.0000000000016186","article-title":"A predictive model for progression of CKD","volume":"98","author":"Chang","year":"2019","journal-title":"Medicine"},{"key":"ref7","doi-asserted-by":"publisher","first-page":"1369225","DOI":"10.3389\/fmed.2024.1369225","article-title":"Collapsing glomerulopathy is likely a major contributing factor for worse allograft survival in patients receiving kidney transplants from black donors","volume":"11","author":"DiFranza","year":"2024","journal-title":"Front. Med."},{"key":"ref8","volume-title":"A guide to calculating and interpreting the estimated post-transplant survival","year":"2020"},{"key":"ref9","doi-asserted-by":"publisher","first-page":"5909","DOI":"10.3390\/app14135909","article-title":"Impact of hyperparameter optimization to enhance machine learning performance: a case study on breast cancer recurrence prediction","volume":"14","author":"Gonz\u00e1lez-Castro","year":"2024","journal-title":"Appl. Sci."},{"key":"ref10","doi-asserted-by":"publisher","first-page":"359","DOI":"10.1186\/s12882-022-02996-0","article-title":"Individual dynamic prediction and prognostic analysis for long-term allograft survival after kidney transplantation","volume":"23","author":"Huang","year":"2022","journal-title":"BMC Nephrol."},{"key":"ref11","doi-asserted-by":"publisher","first-page":"4405","DOI":"10.1007\/s12325-023-02608-9","article-title":"Global economic burden associated with chronic kidney disease: a pragmatic review of medical costs for the inside CKD research programme","volume":"40","author":"Jha","year":"2023","journal-title":"Adv. Ther."},{"key":"ref12","doi-asserted-by":"publisher","first-page":"1774","DOI":"10.2215\/CJN.01230211","article-title":"Monitoring and managing graft health in the kidney transplant recipient","volume":"6","author":"Josephson","year":"2011","journal-title":"Clin. J. Am. Soc. Nephrol."},{"key":"ref13","doi-asserted-by":"publisher","first-page":"2","DOI":"10.1186\/s12963-025-00364-2","article-title":"How much missing data is too much to impute for longitudinal health indicators? A preliminary guideline for the choice of the extent of missing proportion to impute with multiple imputation by chained equations","volume":"23","author":"Junaid","year":"2025","journal-title":"Popul. Health Metrics"},{"key":"ref14","volume-title":"A guide to calculating and interpreting the kidney donor profile index","year":"2020"},{"key":"ref15","doi-asserted-by":"publisher","first-page":"1003","DOI":"10.1007\/s40615-017-0447-9","article-title":"Donor and recipient ethnicity impacts renal graft adverse outcomes","volume":"5","author":"Kwan","year":"2018","journal-title":"J. Racial Ethn. Health Disparities"},{"key":"ref16","doi-asserted-by":"publisher","first-page":"396","DOI":"10.1097\/TP.0000000000003209","article-title":"External validation of the DynPG for kidney transplant recipients","volume":"105","author":"Lenain","year":"2021","journal-title":"Transplantation"},{"key":"ref17","doi-asserted-by":"publisher","first-page":"1113","DOI":"10.1097\/TP.0000000000003943","article-title":"Global estimates of capacity for kidney transplantation in world countries and regions","volume":"106","author":"Mudiayi","year":"2022","journal-title":"Transplantation"},{"key":"ref18","doi-asserted-by":"publisher","first-page":"54","DOI":"10.1186\/s12911-025-02906-y","article-title":"Developing clinical prognostic models to predict graft survival after renal transplantation: comparison of statistical and machine learning models","volume":"25","author":"Mulugeta","year":"2025","journal-title":"BMC Med. Inform. Decis. Mak."},{"key":"ref19","doi-asserted-by":"publisher","first-page":"e26843","DOI":"10.2196\/26843","article-title":"Predicting kidney graft survival using machine learning methods: prediction model development and feature significance analysis study","volume":"23","author":"Naqvi","year":"2021","journal-title":"J. Med. Internet Res."},{"key":"ref20","doi-asserted-by":"publisher","first-page":"2824","DOI":"10.1111\/ajt.16463","article-title":"Long-term kidney transplant graft survival\u2014making Progress when Most needed","volume":"21","author":"Poggio","year":"2021","journal-title":"Am. J. Transplant."},{"key":"ref22","doi-asserted-by":"publisher","first-page":"473","DOI":"10.1093\/ckj\/sfac243","article-title":"Kidney donor profile index and allograft outcomes: interactive effects of estimated post-transplant survival score and ischaemic time","volume":"16","author":"Prunster","year":"2023","journal-title":"Clin. Kidney J."},{"key":"ref23","volume-title":"Python release Python 3.11.5","year":"2023"},{"key":"ref24","doi-asserted-by":"publisher","first-page":"zrad011","DOI":"10.1093\/bjsopen\/zrad011","article-title":"Machine learning models in predicting graft survival in kidney transplantation: Meta-analysis","volume":"7","author":"Ravindhran","year":"2023","journal-title":"BJS Open"},{"key":"ref25","doi-asserted-by":"publisher","first-page":"e795","DOI":"10.1016\/S2589-7500(21)00209-0","article-title":"Dynamic prediction of renal survival among deeply phenotyped kidney transplant recipients using artificial intelligence: an observational, international, multicohort study","volume":"3","author":"Raynaud","year":"2021","journal-title":"Lancet Digit. Health"},{"key":"ref26","doi-asserted-by":"publisher","first-page":"3","DOI":"10.3390\/biomedicines12030606","article-title":"Artificial intelligence reporting guidelines\u2019 adherence in nephrology for improved research and clinical outcomes","volume":"12","author":"Salybekov","year":"2024","journal-title":"Biomedicine"},{"key":"ref27","doi-asserted-by":"publisher","first-page":"8","DOI":"10.3390\/jcm14082775","article-title":"Ethics and algorithms to navigate AI\u2019s emerging role in organ transplantation","volume":"14","author":"Salybekov","year":"2025","journal-title":"J. Clin. Med."},{"key":"ref28","doi-asserted-by":"publisher","first-page":"139","DOI":"10.1038\/s43856-023-00356-z","article-title":"The impact of imputation quality on machine learning classifiers for datasets with missing values","volume":"3","author":"Shadbahr","year":"2023","journal-title":"Commun. Med."},{"key":"ref29","doi-asserted-by":"publisher","first-page":"1463","DOI":"10.2215\/CJN.09131010","article-title":"Associations of pretransplant weight and muscle mass with mortality in renal transplant recipients","volume":"6","author":"Streja","year":"2011","journal-title":"Clin. J. Am. Soc. Nephrol."},{"key":"ref31","doi-asserted-by":"publisher","first-page":"2307","DOI":"10.1097\/TP.0000000000003623","article-title":"Determining the level of importance of variables in predicting kidney transplant survival based on a novel ranking method","volume":"105","author":"Taherkhani","year":"2021","journal-title":"Transplantation"},{"key":"ref32","volume-title":"TRIPOD+AI statement: Updated guidance for reporting clinical prediction models that use regression or machine learning methods | EQUATOR network","year":"2015"},{"key":"ref33","doi-asserted-by":"publisher","first-page":"1453","DOI":"10.1016\/S0140-6736(07)61602-X","article-title":"The strengthening the reporting of observational studies in epidemiology (STROBE) statement: guidelines for reporting observational studies","volume":"370","author":"von Elm","year":"2007","journal-title":"Lancet"},{"key":"ref34","doi-asserted-by":"publisher","first-page":"8904","DOI":"10.1038\/s41598-017-08008-8","article-title":"A machine learning approach using survival statistics to predict graft survival in kidney transplant recipients: a Multicenter cohort study","volume":"7","author":"Yoo","year":"2017","journal-title":"Sci. Rep."},{"key":"ref35","doi-asserted-by":"publisher","first-page":"10730","DOI":"10.1038\/s41598-023-37814-6","article-title":"Healthcare costs after kidney transplantation compared to Dialysis based on propensity score methods and real world longitudinal register data from Sweden","volume":"13","author":"Zhang","year":"2023","journal-title":"Sci. Rep."},{"key":"ref36","doi-asserted-by":"publisher","first-page":"4917","DOI":"10.3390\/jcm14144917","article-title":"Arthroscopic arthrolysis of the knee joint following Total knee arthroplasty","volume":"14","author":"Zhunussov","year":"2025","journal-title":"J. Clin. Med."}],"container-title":["Frontiers in Artificial Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2025.1682639\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,2]],"date-time":"2025-10-02T05:34:33Z","timestamp":1759383273000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2025.1682639\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,2]]},"references-count":33,"alternative-id":["10.3389\/frai.2025.1682639"],"URL":"https:\/\/doi.org\/10.3389\/frai.2025.1682639","relation":{},"ISSN":["2624-8212"],"issn-type":[{"value":"2624-8212","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10,2]]},"article-number":"1682639"}}