{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,13]],"date-time":"2026-03-13T20:45:45Z","timestamp":1773434745316,"version":"3.50.1"},"reference-count":22,"publisher":"Ovid Technologies (Wolters Kluwer Health)","issue":"6","funder":[{"DOI":"10.13039\/501100001665","name":"Agence Nationale de la Recherche","doi-asserted-by":"crossref","award":["ANR-22-PESN-0017"],"award-info":[{"award-number":["ANR-22-PESN-0017"]}],"id":[{"id":"10.13039\/501100001665","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["lww.com","ovid.com"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,12]]},"abstract":"<jats:sec>\n                    <jats:title>Background:<\/jats:title>\n                    <jats:p>\n                      Cyclosporine (CsA), an immunosuppressant widely used in solid-organ transplantation, requires precise therapeutic drug monitoring to balance its efficacy and toxicity. The interdose area under the concentration\u2013time curve (AUC\n                      <jats:sub>0\u201312 h<\/jats:sub>\n                      ) is considered to be a superior metric of drug exposure compared with single concentration measurements but is, nevertheless, resource-intensive. Machine learning (ML) offers a novel approach for AUC prediction by leveraging patient-specific data without relying on traditional pharmacokinetic assumptions. This study intended to develop and evaluate XGBoost ML models for predicting CsA AUC\n                      <jats:sub>0\u201312 h<\/jats:sub>\n                      using either two or three blood concentrations and to compare their performance against maximum a posteriori Bayesian estimation (MAP-BE) based on population pharmacokinetic models.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods:<\/jats:title>\n                    <jats:p>Using data from 2009 patients and 6360 dose-adjustment requests on the Immunosuppressant Bayesian Dose Adjustment website (https:\/\/abis.chu-limoges.fr\/), supervised ML models were trained with predictors including CsA concentrations at predefined time points (C0, C1, and C3), dose, age, and sampling time deviations. External validation was performed using rich pharmacokinetic profiles of kidney, heart, lung, and bone marrow transplant recipients.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results:<\/jats:title>\n                    <jats:p>The three-sample XGBoost model achieved high accuracy in kidney transplant recipients (root mean square error [RMSE] &lt;3%, RMSE&lt;8.2%), closely matching the MAP-BE performance (rMPE &lt;3%, RMSE &lt;8.7%). The two-sample ML model demonstrated lower precision and higher variability but remained applicable in constrained sampling scenarios. The performance was reduced in heart and lung recipients for both ML and MAP-BE, reflecting the limited representation of these populations in the data set.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions:<\/jats:title>\n                    <jats:p>ML-based AUC prediction is a promising alternative to MAP-BE, particularly for kidney transplantation. Future studies should focus on expanding datasets, incorporating additional transplant types, and refining ML models for broader applicability.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1097\/ftd.0000000000001346","type":"journal-article","created":{"date-parts":[[2025,7,23]],"date-time":"2025-07-23T12:01:39Z","timestamp":1753272099000},"page":"779-789","update-policy":"https:\/\/doi.org\/10.1097\/lww.0000000000001000","source":"Crossref","is-referenced-by-count":2,"title":["Estimation of Overall Cyclosporine Exposure Using Machine Learning"],"prefix":"10.1097","volume":"47","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1695-0695","authenticated-orcid":false,"given":"Jean-Baptiste","family":"Woillard","sequence":"first","affiliation":[{"name":"Univ. Limoges, P&T, Limoges, France;"},{"name":"INSERM, P&T, U1248, Limoges, France; and"},{"name":"Department of Pharmacology and Toxicology, CHU Limoges, Limoges, France."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Marc","family":"Labriffe","sequence":"additional","affiliation":[{"name":"Univ. Limoges, P&T, Limoges, France;"},{"name":"INSERM, P&T, U1248, Limoges, France; and"},{"name":"Department of Pharmacology and Toxicology, CHU Limoges, Limoges, France."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pierre","family":"Marquet","sequence":"additional","affiliation":[{"name":"Univ. Limoges, P&T, Limoges, France;"},{"name":"INSERM, P&T, U1248, Limoges, France; and"},{"name":"Department of Pharmacology and Toxicology, CHU Limoges, Limoges, France."}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"276","published-online":{"date-parts":[[2025,7,23]]},"reference":[{"key":"R1-20251107","doi-asserted-by":"crossref","first-page":"378S","DOI":"10.1016\/j.transproceed.2004.01.091","article-title":"Therapeutic drug monitoring of cyclosporine: 20 years of progress","volume":"36","author":"Kahan","year":"2004","journal-title":"Transpl Proc"},{"key":"R2-20251107","doi-asserted-by":"crossref","first-page":"1356","DOI":"10.1097\/00007890-199911150-00023","article-title":"The temporal profile of calcineurin inhibition by cyclosporine in vivo","volume":"68","author":"Halloran","year":"1999","journal-title":"Transplantation"},{"key":"R3-20251107","doi-asserted-by":"crossref","first-page":"621","DOI":"10.1097\/00007691-199512000-00013","article-title":"Challenges in cyclosporine therapy: the role of therapeutic monitoring by area under the curve monitoring","volume":"17","author":"Kahan","year":"1995","journal-title":"Ther Drug Monit"},{"key":"R4-20251107","doi-asserted-by":"crossref","first-page":"55","DOI":"10.1097\/00007890-199907150-00011","article-title":"Neoral monitoring by simplified sparse sampling area under the concentration-time curve: its relationship to acute rejection and cyclosporine nephrotoxicity early after kidney transplantation","volume":"68","author":"Mahalati","year":"1999","journal-title":"Transplantation"},{"key":"R5-20251107","doi-asserted-by":"crossref","first-page":"375","DOI":"10.2165\/00003088-200140050-00004","article-title":"Application of a gamma model of absorption to oral cyclosporin","volume":"40","author":"Debord","year":"2001","journal-title":"Clin Pharmacokinet"},{"key":"R6-20251107","doi-asserted-by":"crossref","first-page":"361","DOI":"10.1002\/cpt.2123","article-title":"Tacrolimus exposure prediction using machine learning","volume":"110","author":"Woillard","year":"2021","journal-title":"Clin Pharmacol Ther"},{"key":"R7-20251107","doi-asserted-by":"crossref","first-page":"105578","DOI":"10.1016\/j.phrs.2021.105578","article-title":"Estimation of drug exposure by machine learning based on simulations from published pharmacokinetic models: the example of tacrolimus","volume":"167","author":"Woillard","year":"2021","journal-title":"Pharmacol Res"},{"key":"R8-20251107","doi-asserted-by":"crossref","first-page":"370","DOI":"10.1002\/cpt.2216","article-title":"Mycophenolic acid exposure prediction using machine learning","volume":"110","author":"Woillard","year":"2021","journal-title":"Clin Pharmacol Ther"},{"key":"R9-20251107","doi-asserted-by":"crossref","first-page":"1686","DOI":"10.21105\/joss.01686","article-title":"Welcome to the tidyverse","volume":"4","author":"Wickham","year":"2019","journal-title":"J Open Source Softw"},{"key":"R11-20251107","doi-asserted-by":"crossref","first-page":"71","DOI":"10.2165\/00003088-200241010-00006","article-title":"Maximum a posteriori Bayesian estimation of oral cyclosporin pharmacokinetics in patients with stable renal transplants","volume":"41","author":"Leger","year":"2002","journal-title":"Clin Pharmacokinet"},{"key":"R12-20251107","doi-asserted-by":"crossref","first-page":"1055","DOI":"10.2165\/00003088-200443140-00007","article-title":"Modelling ciclosporin double-peak absorption profiles in the early post-transplantation period","volume":"43","author":"Rousseau","year":"2004","journal-title":"Clin Pharmacokinet"},{"key":"R13-20251107","doi-asserted-by":"crossref","first-page":"277","DOI":"10.1007\/s40262-013-0037-x","article-title":"Ciclosporin population pharmacokinetics and Bayesian estimation in thoracic transplant recipients","volume":"52","author":"Fruit","year":"2013","journal-title":"Clin Pharmacokinet"},{"key":"R14-20251107","doi-asserted-by":"crossref","first-page":"813","DOI":"10.1007\/s00228-003-0559-5","article-title":"Limited sampling strategies using Bayesian estimation or multilinear regression for cyclosporin AUC(0-12) monitoring in cardiac transplant recipients over the first year post-transplantation","volume":"58","author":"Monchaud","year":"2003","journal-title":"Eur J Clin Pharmacol"},{"key":"R15-20251107","doi-asserted-by":"crossref","first-page":"836","DOI":"10.1111\/bcp.12394","article-title":"Pharmacokinetic tools for the dose adjustment of ciclosporin in haematopoietic stem cell transplant patients","volume":"78","author":"Woillard","year":"2014","journal-title":"Br J Clin Pharmacol"},{"key":"R16-20251107","doi-asserted-by":"crossref","first-page":"545","DOI":"10.1016\/j.clpt.2004.08.022","article-title":"Population pharmacokinetics of cyclosporine in kidney and heart transplant recipients and the influence of ethnicity and genetic polymorphisms in the MDR-1, CYP3A4, and CYP3A5 genes","volume":"76","author":"Hesselink","year":"2004","journal-title":"Clin Pharmacol Ther"},{"key":"R17-20251107","doi-asserted-by":"crossref","first-page":"82","DOI":"10.1002\/psp4.13240","article-title":"To be or not to be, when synthetic data meet clinical pharmacology: a focused study on pharmacogenetics","volume":"14","author":"Woillard","year":"2025","journal-title":"CPT Pharmacometrics Syst Pharmacol"},{"key":"R18-20251107","doi-asserted-by":"crossref","first-page":"37","DOI":"10.1038\/s41746-023-00771-5","article-title":"Patient-centric synthetic data generation, no reason to risk re-identification in biomedical data analysis","volume":"6","author":"Guillaudeux","year":"2023","journal-title":"NPJ Digit Med"},{"key":"R19-20251107","doi-asserted-by":"crossref","first-page":"1016399","DOI":"10.3389\/fphar.2022.1016399","article-title":"Applying machine learning to the pharmacokinetic modeling of cyclosporine in adult renal transplant recipients: a multi-method comparison","volume":"13","author":"Mao","year":"2022","journal-title":"Front Pharmacol"},{"key":"R20-20251107","doi-asserted-by":"crossref","first-page":"83","DOI":"10.1080\/17512433.2023.2142561","article-title":"A model based on machine learning for the prediction of cyclosporin A trough concentration in Chinese allo-HSCT patients","volume":"16","author":"Song","year":"2023","journal-title":"Expert Rev Clin Pharmacol"},{"key":"R21-20251107","doi-asserted-by":"crossref","first-page":"396S","DOI":"10.1016\/j.transproceed.2004.01.013","article-title":"Therapeutic drug monitoring of cyclosporine","volume":"36","author":"Jorga","year":"2004","journal-title":"Transpl Proc"},{"key":"R22-20251107","doi-asserted-by":"crossref","first-page":"813","DOI":"10.1373\/49.5.813","article-title":"Influence of sampling-time error on cyclosporine measurements nominally at 2 hours after administration","volume":"49","author":"Saint-Marcoux","year":"2003","journal-title":"Clin Chem"},{"key":"R23-20251107","doi-asserted-by":"crossref","first-page":"495","DOI":"10.4155\/bio-2018-0312","article-title":"A volumetric absorptive microsampling LC-MS\/MS method for five immunosuppressants and their hematocrit effects","volume":"11","author":"Koster","year":"2019","journal-title":"Bioanalysis"}],"container-title":["Therapeutic Drug Monitoring"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/journals.lww.com\/10.1097\/FTD.0000000000001346","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,7]],"date-time":"2025-11-07T19:00:41Z","timestamp":1762542041000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.lww.com\/10.1097\/FTD.0000000000001346"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,23]]},"references-count":22,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2025]]}},"URL":"https:\/\/doi.org\/10.1097\/ftd.0000000000001346","relation":{},"ISSN":["0163-4356","1536-3694"],"issn-type":[{"value":"0163-4356","type":"print"},{"value":"1536-3694","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,7,23]]},"assertion":[{"value":"2024-11-20","name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-02-03","name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}}]}}