{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,18]],"date-time":"2026-06-18T04:55:28Z","timestamp":1781758528921,"version":"3.54.5"},"reference-count":22,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,6,18]],"date-time":"2026-06-18T00:00:00Z","timestamp":1781740800000},"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. Med."],"abstract":"<jats:sec>\n                    <jats:title>Background and aim<\/jats:title>\n                    <jats:p>Antithymocyte globulin (ATG) therapy is conventionally monitored by measuring peripheral blood CD3+\u202fT-cell counts. However, CD3+\u202fT-cell quantification requires flow cytometry and may not be routinely available in centers. This study aimed to identify clinical and laboratory predictors of CD3+\u202fT-cell depletion and to develop a machine learning model for predicting attainment of predefined therapeutic CD3+\u202fT-cell thresholds following ATG induction therapy in kidney transplant recipients.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Materials and methods<\/jats:title>\n                    <jats:p>Adult transplant patients who underwent kidney transplantation were retrospectively evaluated. ATG doses were administered as induction therapy, and the subsequent peripheral blood CD3+\u202fT-cell counts were obtained. Demographic, anthropometric features, and laboratory results were recorded. Statistical and machine learning methods were applied to identify parameters predictive of CD3+\u202fT-cell counts. Prediction models were developed and compared to the logistic regression model to estimate the likelihood of reaching certain CD3+\u202fT-cell count cut-offs after transplantation to evaluate and monitor ATG effect.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>In the analysis of 397 transplant patients of 99.2% grafts from living donors, 57.2% of patients achieved the predefined day-1 CD3+\u202fT-cell &amp;lt; 50 cell\/\u03bcl threshold, while 57.5% of patients reached the predefined day-2 CD3+\u202fT-cell &amp;lt; 30 cell\/\u03bcl threshold. The machine learning model\u2019s performance in predicting target threshold attainment resulted in ROC-AUC values of 0.75 and 0.80 for Day 1 (test and validation sets), whereas Day 2 predictions yielded ROC-AUC scores of 0.70 and 0.66, respectively. The predictive performance of the machine learning model was superior to logistic regression prediction, and decision curve analysis showed that the model provided clinically meaningful net benefit for decision-making for Day 1 and Day 2 predictions.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>The clinical response to ATG treatment for induction immunosuppression in kidney transplant patients may be adequately predicted using low-cost and accessible laboratory tests alongside patient-specific characteristics without the need for CD3+\u202fT-cell quantification, through machine learning prediction models. This study provides an initial framework for further development of more accurate machine learning models with higher prediction power for clinical use in ATG effect prediction.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fmed.2026.1869846","type":"journal-article","created":{"date-parts":[[2026,6,18]],"date-time":"2026-06-18T04:40:25Z","timestamp":1781757625000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["CD3+\u202fT-cell count prediction for anti-thymocyte globulin treatment monitorization in kidney transplant recipients: a machine learning model"],"prefix":"10.3389","volume":"13","author":[{"given":"Ahmet B.","family":"Ak","sequence":"first","affiliation":[{"name":"Department of Internal Medicine, Koc University School of Medicine","place":["Istanbul, T\u00fcrkiye"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hayri K.","family":"Goren","sequence":"additional","affiliation":[{"name":"Department of Internal Medicine, Koc University School of Medicine","place":["Istanbul, T\u00fcrkiye"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nuri B.","family":"Hasbal","sequence":"additional","affiliation":[{"name":"Division of Nephrology, Department of Internal Medicine, Koc University School of Medicine","place":["Istanbul, T\u00fcrkiye"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nur I.","family":"Genc","sequence":"additional","affiliation":[{"name":"Department of Internal Medicine, Koc University School of Medicine","place":["Istanbul, T\u00fcrkiye"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sidar","family":"Copur","sequence":"additional","affiliation":[{"name":"Department of Internal Medicine, Koc University School of Medicine","place":["Istanbul, T\u00fcrkiye"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lasin","family":"Ozbek","sequence":"additional","affiliation":[{"name":"Koc University, School of Medicine","place":["Istanbul, T\u00fcrkiye"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Burak","family":"Kocak","sequence":"additional","affiliation":[{"name":"Department of Urology, Koc University School of Medicine","place":["Istanbul, T\u00fcrkiye"]},{"name":"Munci Kalayoglu Organ Transplant Center, Koc University Hospital","place":["Istanbul, T\u00fcrkiye"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Adrian","family":"Covic","sequence":"additional","affiliation":[{"name":"Nephrology Clinic, Dialysis and Renal Transplant Center\u2014'C.I. Parhon' University Hospital and 'Grigore T. Popa' University of Medicine","place":["Iasi, Romania"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mehmet","family":"Kanbay","sequence":"additional","affiliation":[{"name":"Division of Nephrology, Department of Internal Medicine, Koc University School of Medicine","place":["Istanbul, T\u00fcrkiye"]},{"name":"Munci Kalayoglu Organ Transplant Center, Koc University Hospital","place":["Istanbul, T\u00fcrkiye"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,6,18]]},"reference":[{"key":"ref1","doi-asserted-by":"publisher","first-page":"S1","DOI":"10.1111\/j.1600-6143.2009.02834.x","article-title":"KDIGO clinical practice guideline for the care of kidney transplant recipients","volume":"9","year":"2009","journal-title":"Am J Transplant"},{"key":"ref2","doi-asserted-by":"publisher","first-page":"5938","DOI":"10.3390\/jcm12185938","article-title":"Preventing rejection of the kidney transplant","volume":"12","author":"Malhotra","year":"2023","journal-title":"J Clin Med"},{"key":"ref3","doi-asserted-by":"publisher","first-page":"1387","DOI":"10.1038\/sj.leu.2404683","article-title":"Mechanisms of action of antithymocyte globulin: T-cell depletion and beyond","volume":"21","author":"Mohty","year":"2007","journal-title":"Leukemia"},{"key":"ref4","doi-asserted-by":"publisher","first-page":"260.e1","DOI":"10.1016\/j.jtct.2022.02.016","article-title":"Cytokine release syndrome during antithymocyte globulin\/anti-T lymphocyte globulin Serotherapy for graft-versus-host disease prophylaxis before allogeneic hematopoietic stem cell transplantation: incidence and early clinical impact according to American Society of Transplantation and cellular therapy grading criteria","volume":"28","author":"Knaus","year":"2022","journal-title":"Transplant Cell Ther"},{"key":"ref5","doi-asserted-by":"publisher","first-page":"769","DOI":"10.1681\/ASN.V133769","article-title":"Association of Antibody Induction with short and long-term cause-specific mortality in renal transplant recipients","volume":"13","author":"Meier-Kriesche","year":"2002","journal-title":"J Am Soc Nephrol"},{"key":"ref6","doi-asserted-by":"publisher","first-page":"463","DOI":"10.1016\/j.transproceed.2007.01.024","article-title":"Thymoglobulin and rate of infectious complications after transplantation","volume":"39","author":"Clesca","year":"2007","journal-title":"Transplant Proc"},{"key":"ref7","doi-asserted-by":"publisher","first-page":"1227","DOI":"10.1097\/01.tp.0000219817.18049.36","article-title":"Disassociation between risk of graft loss and risk of non-Hodgkin lymphoma with induction agents in renal transplant recipients","volume":"81","author":"Opelz","year":"2006","journal-title":"Transplantation"},{"key":"ref8","doi-asserted-by":"publisher","first-page":"1601","DOI":"10.1093\/ndt\/gfw368","article-title":"Anti-thymocyte globulins in kidney transplantation: focus on current indications and long-term immunological side effects","volume":"32","author":"Bamoulid","year":"2017","journal-title":"Nephrol Dial Transplant"},{"key":"ref9","doi-asserted-by":"publisher","first-page":"18","DOI":"10.1111\/j.1432-2277.1993.tb00738.x","article-title":"Administration of ATG according to the absolute T lymphocyte count during therapy for steroid-resistant rejection","volume":"6","author":"Clark","year":"1993","journal-title":"Transpl Int"},{"key":"ref10","doi-asserted-by":"publisher","first-page":"1715","DOI":"10.1016\/j.transproceed.2025.06.016","article-title":"Monitoring CD3(+) T cells in kidney transplantation and immunosuppression adequacy","volume":"57","author":"Eyvaz","year":"2025","journal-title":"Transplant Proc"},{"key":"ref11","doi-asserted-by":"publisher","first-page":"1419726","DOI":"10.3389\/fimmu.2024.1419726","article-title":"Interruption of anti-thymocyte globuline treatment in solid organ transplantation is effectively monitored through a low total lymphocyte count","volume":"15","author":"Rasander","year":"2024","journal-title":"Front Immunol"},{"key":"ref12","doi-asserted-by":"publisher","first-page":"181","DOI":"10.5935\/0101-2800.20170032","article-title":"Cut-off value for absolute lymphocytes as an alternative for the immunophenotypic analysis of CD3+ T cells in the monitoring of immunosuppressive therapy with thymoglobulin","volume":"39","author":"Furlanetto","year":"2017","journal-title":"J Bras Nefrol"},{"key":"ref13","doi-asserted-by":"publisher","first-page":"389","DOI":"10.1016\/S0140-6736(25)00195-3","article-title":"Advancing patient monitoring, diagnostics, and treatment strategies for transplant precision medicine","volume":"406","author":"Loupy","year":"2025","journal-title":"Lancet"},{"key":"ref14","doi-asserted-by":"publisher","first-page":"799","DOI":"10.1097\/00007890-200003150-00021","article-title":"Low dose antithymocyte globulins in renal transplantation: daily versus intermittent administration based on T-cell monitoring","volume":"69","author":"Djamali","year":"2000","journal-title":"Transplantation"},{"key":"ref15","doi-asserted-by":"publisher","first-page":"271","DOI":"10.1111\/tri.12249","article-title":"Risk factors for impaired CD4+ T-cell reconstitution following rabbit antithymocyte globulin treatment in kidney transplantation","volume":"27","author":"Longuet","year":"2014","journal-title":"Transpl Int"},{"key":"ref16","doi-asserted-by":"publisher","first-page":"1514","DOI":"10.1097\/00007890-200205150-00025","article-title":"Safety, efficacy, and cost analysis of thymoglobulin induction therapy with intermittent dosing based on CD3+ lymphocyte counts in kidney and kidney-pancreas transplant recipients","volume":"73","author":"Peddi","year":"2002","journal-title":"Transplantation"},{"key":"ref17","doi-asserted-by":"publisher","first-page":"e14582","DOI":"10.1111\/ctr.14582","article-title":"Rabbit antithymocyte globulin dose and early subclinical and clinical rejections in kidney transplantation","volume":"36","author":"Mehta","year":"2022","journal-title":"Clin Transpl"},{"key":"ref18","doi-asserted-by":"publisher","first-page":"203","DOI":"10.1186\/s12882-025-04128-w","article-title":"Development of explainable artificial intelligence based machine learning model for predicting 30-day hospital readmission after renal transplantation","volume":"26","author":"Alnazari","year":"2025","journal-title":"BMC Nephrol"},{"key":"ref19","doi-asserted-by":"publisher","first-page":"1565","DOI":"10.1186\/s12885-025-14973-5","article-title":"Machine learning predicts post-transplant muscle loss in hepatocellular carcinoma patients without sarcopenia","volume":"25","author":"Chen","year":"2025","journal-title":"BMC Cancer"},{"key":"ref20","doi-asserted-by":"publisher","first-page":"e70043","DOI":"10.1111\/petr.70043","article-title":"Identifying risk factors for graft failure due to chronic rejection\u202f<\u202f15\u202fyears post-transplant in pediatric kidney transplants using random Forest machine-learning techniques","volume":"29","author":"Suh","year":"2025","journal-title":"Pediatr Transplant"},{"key":"ref21","doi-asserted-by":"publisher","first-page":"1349","DOI":"10.1097\/LVT.0000000000000685","article-title":"Machine learning improves post-transplantation HCC recurrence prediction","volume":"31","author":"Li","year":"2025","journal-title":"Liver Transpl"},{"key":"ref22","doi-asserted-by":"publisher","first-page":"2493231","DOI":"10.1080\/0886022X.2025.2493231","article-title":"Prediction of peripheral blood lymphocyte subpopulations after renal transplantation","volume":"47","author":"Peng","year":"2025","journal-title":"Ren Fail"}],"container-title":["Frontiers in Medicine"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fmed.2026.1869846\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,18]],"date-time":"2026-06-18T04:40:37Z","timestamp":1781757637000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fmed.2026.1869846\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,18]]},"references-count":22,"alternative-id":["10.3389\/fmed.2026.1869846"],"URL":"https:\/\/doi.org\/10.3389\/fmed.2026.1869846","relation":{},"ISSN":["2296-858X"],"issn-type":[{"value":"2296-858X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6,18]]},"article-number":"1869846"}}