{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,18]],"date-time":"2026-05-18T14:26:35Z","timestamp":1779114395762,"version":"3.51.4"},"reference-count":44,"publisher":"Ovid Technologies (Wolters Kluwer Health)","issue":"1","license":[{"start":{"date-parts":[[2025,9,17]],"date-time":"2025-09-17T00:00:00Z","timestamp":1758067200000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["lww.com","ovid.com"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,1]]},"abstract":"<jats:sec>\n                    <jats:title>Background:<\/jats:title>\n                    <jats:p>Accurately predicting post-transplant renal function is essential for optimizing donor-recipient matching and improving long-term outcomes in kidney transplantation (KT). Traditional models using only structured clinical data often fail to account for complex biological and anatomical factors. This study aimed to develop and validate a multimodal deep learning model that integrates computed tomography (CT) imaging, radiology report text, and structured clinical variables to predict 1-year estimated glomerular filtration rate (eGFR) in living donor kidney transplantation (LDKT) recipients.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Materials and Methods:<\/jats:title>\n                    <jats:p>\n                      A retrospective cohort of 1,937 LDKT recipients was selected from 3772 KT cases. Exclusions included deceased donor KT, immunologic high-risk recipients (\n                      <jats:italic toggle=\"yes\">n<\/jats:italic>\n                      = 304), missing CT imaging, early graft complications, and anatomical abnormalities. eGFR at 1 year post-transplant was classified into four categories: &gt;90, 75\u201390, 60\u201375, and 45\u201360 mL\/min\/1.73 m\n                      <jats:sup>2<\/jats:sup>\n                      . Radiology reports were embedded using BioBERT, while CT videos were encoded using a CLIP-based visual extractor. These were fused with structured clinical features and input into ensemble classifiers including XGBoost. Model performance was evaluated using cross-validation and SHapley Additive exPlanations (SHAP) analysis.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results:<\/jats:title>\n                    <jats:p>The full multimodal model achieved a macro F1 score of 0.675, micro F1 score of 0.704, and weighted F1 score of 0.698 \u2013 substantially outperforming the clinical-only model (macro F1 = 0.292). CT imaging contributed more than text data (clinical + CT macro F1 = 0.651; clinical + text = 0.486). The model showed highest accuracy in the &gt;90 (F1 = 0.7773) and 60\u201375 (F1 = 0.7303) categories. SHAP analysis identified donor age, BMI, and donor sex as key predictors. Dimensionality reduction confirmed internal feature validity.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion:<\/jats:title>\n                    <jats:p>Multimodal deep learning integrating clinical, imaging, and textual data enhances prediction of post-transplant renal function. This framework offers a robust and interpretable approach for individualized risk stratification in LDKT, supporting precision medicine in transplantation.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1097\/js9.0000000000003494","type":"journal-article","created":{"date-parts":[[2025,9,17]],"date-time":"2025-09-17T18:01:12Z","timestamp":1758132072000},"page":"1153-1163","update-policy":"https:\/\/doi.org\/10.1097\/lww.0000000000001000","source":"Crossref","is-referenced-by-count":1,"title":["Multimodal deep learning integration for predicting renal function outcomes in living donor kidney transplantation: a retrospective cohort study"],"prefix":"10.1097","volume":"112","author":[{"given":"Jin-Myung","family":"Kim","sequence":"first","affiliation":[{"name":"Division of Kidney and Pancreas Transplantation, Department of Surgery, Asan Medical Center, University of Ulsan College of Medicine, Seoul, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"HyoJe","family":"Jung","sequence":"additional","affiliation":[{"name":"Department of Information Medicine, Asan Medical Center, Seoul, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hye Eun","family":"Kwon","sequence":"additional","affiliation":[{"name":"Division of Kidney and Pancreas Transplantation, Department of Surgery, Asan Medical Center, University of Ulsan College of Medicine, Seoul, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Youngmin","family":"Ko","sequence":"additional","affiliation":[{"name":"Division of Kidney and Pancreas Transplantation, Department of Surgery, Asan Medical Center, University of Ulsan College of Medicine, Seoul, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Joo Hee","family":"Jung","sequence":"additional","affiliation":[{"name":"Division of Kidney and Pancreas Transplantation, Department of Surgery, Asan Medical Center, University of Ulsan College of Medicine, Seoul, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sung","family":"Shin","sequence":"additional","affiliation":[{"name":"Division of Kidney and Pancreas Transplantation, Department of Surgery, Asan Medical Center, University of Ulsan College of Medicine, Seoul, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Young Hoon","family":"Kim","sequence":"additional","affiliation":[{"name":"Division of Kidney and Pancreas Transplantation, Department of Surgery, Asan Medical Center, University of Ulsan College of Medicine, Seoul, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Young-Hak","family":"Kim","sequence":"additional","affiliation":[{"name":"Division of Cardiology, Department of Internal Medicine, Asan Medical Center, University of Ulsan College of Medicine, Seoul, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tae Joon","family":"Jun","sequence":"additional","affiliation":[{"name":"Department of Medical Informatics and Statistics, Asan Medical Center, University of Ulsan College of Medicine, Seoul, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5018-5304","authenticated-orcid":false,"given":"Hyunwook","family":"Kwon","sequence":"additional","affiliation":[{"name":"Division of Kidney and Pancreas Transplantation, Department of Surgery, Asan Medical Center, University of Ulsan College of Medicine, Seoul, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"276","published-online":{"date-parts":[[2025,9,17]]},"reference":[{"key":"R1-20260518","doi-asserted-by":"crossref","first-page":"e4352","DOI":"10.1097\/MD.0000000000004352","article-title":"Superior outcomes of kidney transplantation compared with dialysis: an optimal matched analysis of a national population-based cohort study between 2005 and 2008 in Korea","volume":"95","author":"Yoo","year":"2016","journal-title":"Medicine (Baltimore)"},{"key":"R2-20260518","doi-asserted-by":"crossref","first-page":"1725\u201330","DOI":"10.1056\/NEJM199912023412303","article-title":"Comparison of mortality in all patients on dialysis, patients on dialysis awaiting transplantation, and recipients of a first cadaveric transplant","volume":"341","author":"Wolfe","year":"1999","journal-title":"N Engl J Med"},{"key":"R3-20260518","doi-asserted-by":"crossref","first-page":"2093\u2013109","DOI":"10.1111\/j.1600-6143.2011.03686.x","article-title":"Systematic review: kidney transplantation compared with dialysis in clinically relevant outcomes","volume":"11","author":"Tonelli","year":"2011","journal-title":"Am J Transplant"},{"key":"R4-20260518","doi-asserted-by":"crossref","first-page":"e2234971","DOI":"10.1001\/jamanetworkopen.2022.34971","article-title":"Survival benefit of first single-organ deceased donor kidney transplantation compared with long-term dialysis across ages in transplant-eligible patients with kidney failure","volume":"5","author":"Strohmaier","year":"2022","journal-title":"JAMA Network Open"},{"key":"R5-20260518","doi-asserted-by":"crossref","first-page":"210","DOI":"10.1186\/s12882-021-02412-z","article-title":"Quality of life for kidney transplant recipients and hemodialysis patients in Palestine: a cross-sectional study","volume":"22","author":"Sarhan","year":"2021","journal-title":"BMC Nephrol"},{"key":"R6-20260518","doi-asserted-by":"crossref","first-page":"791\u2013802","DOI":"10.1093\/ckj\/sfaa044","article-title":"Prognostic value for long-term graft survival of estimated glomerular filtration rate and proteinuria quantified at 3\u2009months after kidney transplantation","volume":"13","author":"Mottola","year":"2020","journal-title":"Clin Kidney J"},{"key":"R7-20260518","doi-asserted-by":"crossref","first-page":"10136","DOI":"10.3389\/ti.2022.10136","article-title":"Surrogate endpoints for late kidney transplantation failure","volume":"35","author":"Naesens","year":"2022","journal-title":"Transpl Int"},{"key":"R8-20260518","doi-asserted-by":"crossref","first-page":"1303746","DOI":"10.3389\/fimmu.2024.1303746","article-title":"Impact of deceased-donor characteristics on early graft function: outcome of kidney donor pairs accepted for transplantation","volume":"15","author":"Mahler","year":"2024","journal-title":"Front Immunol"},{"key":"R9-20260518","doi-asserted-by":"crossref","first-page":"68\u201375","DOI":"10.1034\/j.1600-6143.2002.020112.x","article-title":"Effect of donor factors on early graft survival in adult cadaveric renal transplantation","volume":"2","author":"Swanson","year":"2002","journal-title":"Am J Transplant"},{"key":"R10-20260518","first-page":"e35438","article-title":"The predictive value of donor renal functions, graft weight, recipient body mass index, and human leucocyte antigen match regarding early graft functions","volume":"15","author":"A\u00e7\u0131kg\u00f6z","year":"2023","journal-title":"Cureus"},{"key":"R11-20260518","doi-asserted-by":"crossref","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":"R12-20260518","doi-asserted-by":"crossref","first-page":"1472\u201380","DOI":"10.1111\/tri.13695","article-title":"Machine learning to predict transplant outcomes: helpful or hype? A national cohort study","volume":"33","author":"Bae","year":"2020","journal-title":"Transpl Int"},{"key":"R13-20260518","doi-asserted-by":"crossref","first-page":"1236\u201346","DOI":"10.1093\/bib\/bbx044","article-title":"Deep learning for healthcare: review, opportunities and challenges","volume":"19","author":"Miotto","year":"2018","journal-title":"Brief Bioinform"},{"key":"R14-20260518","doi-asserted-by":"crossref","first-page":"4\u201321","DOI":"10.1109\/JBHI.2016.2636665","article-title":"Deep learning for health informatics","volume":"21","author":"Ravi","year":"2017","journal-title":"IEEE J Biomed Health Inform"},{"key":"R15-20260518","first-page":"3\u201321","article-title":"Deep learning in medical image analysis","volume":"1213","author":"Chan","year":"2020","journal-title":"Adv Exp Med Biol"},{"key":"R16-20260518","doi-asserted-by":"crossref","first-page":"e188","DOI":"10.7861\/fhj.2021-0095","article-title":"Artificial intelligence in healthcare: transforming the practice of medicine","volume":"8","author":"Bajwa","year":"2021","journal-title":"Future Healthc J"},{"key":"R17-20260518","doi-asserted-by":"crossref","first-page":"1438247","DOI":"10.3389\/fimmu.2024.1438247","article-title":"Deep learning-enabled classification of kidney allograft rejection on whole slide histopathologic images","volume":"15","author":"Ye","year":"2024","journal-title":"Front Immunol"},{"key":"R18-20260518","doi-asserted-by":"crossref","first-page":"19281","DOI":"10.1038\/s41598-024-69981-5","article-title":"Multi-modal transformer architecture for medical image analysis and automated report generation","volume":"14","author":"Raminedi","year":"2024","journal-title":"Sci Rep"},{"key":"R19-20260518","doi-asserted-by":"crossref","first-page":"99","DOI":"10.1007\/s10462-024-10721-6","article-title":"A review of convolutional neural networks in computer vision","volume":"57","author":"Zhao","year":"2024","journal-title":"Artif Intell Rev"},{"key":"R20-20260518","doi-asserted-by":"crossref","first-page":"512","DOI":"10.3390\/biomimetics8070512","article-title":"Application of machine learning based on structured medical data in gastroenterology","volume":"8","author":"Kim","year":"2023","journal-title":"Biomimetics (Basel)"},{"key":"R21-20260518","doi-asserted-by":"crossref","first-page":"178","DOI":"10.3390\/diagnostics9040178","article-title":"A machine-learning-based prediction method for hypertension outcomes based on medical data","volume":"9","author":"Chang","year":"2019","journal-title":"Diagnostics (Basel)"},{"key":"R22-20260518","doi-asserted-by":"crossref","first-page":"1175\u201387","DOI":"10.2147\/RMHP.S297838","article-title":"The random forest model has the best accuracy among the four pressure ulcer prediction models using machine learning algorithms","volume":"14","author":"Song","year":"2021","journal-title":"Risk Manag Healthc Policy"},{"key":"R23-20260518","doi-asserted-by":"crossref","first-page":"101814","DOI":"10.1016\/j.artmed.2020.101814","article-title":"A multicenter random forest model for effective prognosis prediction in collaborative clinical research network","volume":"103","author":"Li","year":"2020","journal-title":"Artif Intell Med"},{"key":"R24-20260518","doi-asserted-by":"crossref","first-page":"12309","DOI":"10.3389\/ti.2024.12309","article-title":"Characteristics of delayed graft function and long-term outcomes after kidney transplantation from brain-dead donors: a single-center and multicenter registry-based retrospective study","volume":"37","author":"Ahlmark","year":"2024","journal-title":"Transpl Int"},{"key":"R25-20260518","doi-asserted-by":"crossref","first-page":"277\u201389","DOI":"10.5500\/wjt.v11.i7.277","article-title":"Artificial intelligence and kidney transplantation","volume":"11","author":"Seyahi","year":"2021","journal-title":"World J Transplant"},{"key":"R26-20260518","doi-asserted-by":"crossref","first-page":"407","DOI":"10.1186\/s12916-024-03624-4","article-title":"An integrated machine learning model enhances delayed graft function prediction in pediatric renal transplantation from deceased donors","volume":"22","author":"Liu","year":"2024","journal-title":"BMC Med"},{"key":"R27-20260518","doi-asserted-by":"crossref","first-page":"7502","DOI":"10.3390\/jcm13247502","article-title":"Integrating clinical and histopathological data to predict delayed graft function in kidney transplant recipients using machine learning techniques","volume":"13","author":"Tirasattayapitak","year":"2024","journal-title":"J Clin Med"},{"key":"R28-20260518","doi-asserted-by":"crossref","first-page":"2058\u201362","DOI":"10.1016\/j.transproceed.2023.07.021","article-title":"Machine learning model to predict graft rejection after kidney transplantation","volume":"55","author":"Minato","year":"2023","journal-title":"Transplant Proc"},{"key":"R29-20260518","doi-asserted-by":"crossref","first-page":"1679\u201387","DOI":"10.1007\/s40620-024-02027-1","article-title":"Prediction of post-donation renal function using machine learning techniques and conventional regression models in living kidney donors","volume":"37","author":"Jeon","year":"2024","journal-title":"J Nephrol"},{"key":"R30-20260518","doi-asserted-by":"crossref","first-page":"212\u201321","DOI":"10.1093\/ndt\/gfac202","article-title":"Prediction of measured GFR after living kidney donation from pre-donation parameters","volume":"38","author":"van Londen","year":"2023","journal-title":"Nephrol Dial Transplant"},{"key":"R31-20260518","doi-asserted-by":"crossref","first-page":"2088\u201399","DOI":"10.1093\/ndt\/gfae088","article-title":"Live-donor kidney transplant outcome prediction (L-TOP) using artificial intelligence","volume":"39","author":"Ali","year":"2024","journal-title":"Nephrol Dial Transplant"},{"key":"R32-20260518","doi-asserted-by":"crossref","first-page":"280","DOI":"10.1186\/s12911-020-01297-6","article-title":"Combining structured and unstructured data for predictive models: a deep learning approach","volume":"20","author":"Zhang","year":"2020","journal-title":"BMC Med. Inf. Decis. Making"},{"key":"R33-20260518","doi-asserted-by":"crossref","first-page":"116\u201319","DOI":"10.1038\/s41586-019-1390-1","article-title":"A clinically applicable approach to continuous prediction of future acute kidney injury","volume":"572","author":"Toma\u0161ev","year":"2019","journal-title":"Nature"},{"key":"R34-20260518","doi-asserted-by":"crossref","first-page":"18","DOI":"10.1038\/s41746-018-0029-1","article-title":"Scalable and accurate deep learning with electronic health records","volume":"1","author":"Rajkomar","year":"2018","journal-title":"NPJ Digit Med"},{"key":"R35-20260518","first-page":"100081","article-title":"Revised strengthening the reporting of cohort, cross-sectional and case-control studies in surgery (STROCSS) guideline: an update for the age of artificial intelligence","volume":"2","author":"Riaz","journal-title":"Premier Journal of Science"},{"key":"R36-20260518","doi-asserted-by":"crossref","first-page":"2671\u201392","DOI":"10.1007\/s00180-022-01207-6","article-title":"Regularized target encoding outperforms traditional methods in supervised machine learning with high cardinality features","volume":"37","author":"Pargent","year":"2022","journal-title":"Comput Stat"},{"key":"R37-20260518","doi-asserted-by":"crossref","first-page":"1234\u201340","DOI":"10.1093\/bioinformatics\/btz682","article-title":"BioBERT: a pre-trained biomedical language representation model for biomedical text mining","volume":"36","author":"Lee","year":"2020","journal-title":"Bioinformatics"},{"key":"R39-20260518","doi-asserted-by":"crossref","first-page":"18409","DOI":"10.1038\/s41598-020-75473-z","article-title":"Personalized prediction of delayed graft function for recipients of deceased donor kidney transplants with machine learning","volume":"10","author":"Kawakita","year":"2020","journal-title":"Sci Rep"},{"key":"R40-20260518","doi-asserted-by":"crossref","first-page":"2279\u201396","DOI":"10.1111\/j.1600-6143.2011.03754.x","article-title":"Delayed graft function in the kidney transplant","volume":"11","author":"Siedlecki","year":"2011","journal-title":"Am J Transplant"},{"key":"R41-20260518","doi-asserted-by":"crossref","first-page":"871\u201376","DOI":"10.1097\/00007890-199403270-00018","article-title":"Effect of donor age on outcome of kidney transplantation. A two-year analysis of transplants reported to the United Network for organ sharing registry","volume":"57","author":"Alexander","year":"1994","journal-title":"Transplantation"},{"key":"R42-20260518","doi-asserted-by":"crossref","first-page":"524\u201329","DOI":"10.1097\/TP.0b013e318243c6e4","article-title":"Recipient and donor body mass index as important risk factors for delayed kidney graft function","volume":"93","author":"Weissenbacher","year":"2012","journal-title":"Transplantation"},{"key":"R43-20260518","doi-asserted-by":"crossref","first-page":"7159\u201368","DOI":"10.1097\/JS9.0000000000002028","article-title":"Predicting prognostic factors in kidney transplantation using a machine learning approach to enhance outcome predictions: a retrospective cohort study","volume":"110","author":"Kim","year":"2024","journal-title":"Int J Surg"},{"key":"R44-20260518","first-page":"303","article-title":"The future of multimodal artificial intelligence models for integrating imaging and clinical metadata: a narrative review","volume":"31","author":"Simon","journal-title":"Diagn Interv Radiol"},{"key":"R45-20260518","doi-asserted-by":"crossref","first-page":"854\u201360","DOI":"10.1097\/RLI.0000000000001102","article-title":"Multimodal AI combining clinical and imaging inputs improves prostate cancer detection","volume":"59","author":"Roest","year":"2024","journal-title":"Invest Radiol"}],"container-title":["International Journal of Surgery"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/journals.lww.com\/10.1097\/JS9.0000000000003494","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,18]],"date-time":"2026-05-18T13:21:23Z","timestamp":1779110483000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.lww.com\/10.1097\/JS9.0000000000003494"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,17]]},"references-count":44,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2026]]}},"URL":"https:\/\/doi.org\/10.1097\/js9.0000000000003494","relation":{},"ISSN":["1743-9159"],"issn-type":[{"value":"1743-9159","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,9,17]]},"assertion":[{"value":"2025-05-29","name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-08-28","name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}}]}}