{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,26]],"date-time":"2026-05-26T08:05:58Z","timestamp":1779782758925,"version":"3.53.1"},"reference-count":37,"publisher":"Wiley","issue":"6","license":[{"start":{"date-parts":[[2026,1,13]],"date-time":"2026-01-13T00:00:00Z","timestamp":1768262400000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"},{"start":{"date-parts":[[2026,1,13]],"date-time":"2026-01-13T00:00:00Z","timestamp":1768262400000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/doi.wiley.com\/10.1002\/tdm_license_1.1"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Br J Clin Pharmacol"],"published-print":{"date-parts":[[2026,6]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Aim<\/jats:title>\n                    <jats:p>Tacrolimus dosing in the early post\u2010kidney transplant period is challenging due to a narrow therapeutic index and substantial interindividual pharmacokinetic (PK) variability. This study aimed to develop and validate mechanism\u2010informed machine learning (ML) models to support individualized tacrolimus dosing during this critical period.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>\n                      A total of 4311 tacrolimus trough concentrations (C\n                      <jats:sub>trough<\/jats:sub>\n                      ) within 7\u00a0days post\u2010transplant were obtained from 1624 kidney transplant recipients. Two ML models, Gated Recurrent Unit (GRU) and eXtreme Gradient Boosting (XGBoost), were developed to predict C\n                      <jats:sub>trough<\/jats:sub>\n                      and recommend doses to achieve target levels. Both models incorporated PK principles based on linear pharmacokinetics. Model performance was compared to a traditional Bayesian population PK (PopPK) model and purely data\u2010driven ML models via internal cross\u2010validation and external validation.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>\n                      The mechanism\u2010informed GRU model outperformed the Bayesian PopPK model in both internal validation (MSE\u2009=\u00a07.81\n                      <jats:italic>vs<\/jats:italic>\n                      . 9.27\u2009ng\n                      <jats:sup>2<\/jats:sup>\n                      \/mL\n                      <jats:sup>2<\/jats:sup>\n                      , R\n                      <jats:sup>2<\/jats:sup>\n                      \u00a0=\u00a00.537\n                      <jats:italic>vs<\/jats:italic>\n                      . 0.450) and external validation (MSE\u2009=\u00a06.09\n                      <jats:italic>vs<\/jats:italic>\n                      . 8.96\u2009ng\n                      <jats:sup>2<\/jats:sup>\n                      \/mL\n                      <jats:sup>2<\/jats:sup>\n                      , R\n                      <jats:sup>2<\/jats:sup>\n                      \u00a0=\u00a00.397\n                      <jats:italic>vs<\/jats:italic>\n                      . 0.211). The mechanism\u2010informed XGBoost model performed comparably to the GRU model. The incorporation of PK principles enhanced model interpretability and generalizability without reducing accuracy. When clinically administered doses, determined by conventional therapeutic drug monitoring, fell within the GRU model's recommended range, subsequent C\n                      <jats:sub>trough<\/jats:sub>\n                      reached the therapeutic target (8\u201312\u2009ng\/mL) in 51.3% of cases, compared to 37.0% overall (p\u2009&lt;\u20090.01).\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>Mechanism\u2010informed ML models offer a robust and interpretable approach for individualized tacrolimus dosing, with the potential to improve therapeutic target attainment by enabling accurate dose adjustments in the early post\u2010transplant period.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1002\/bcp.70448","type":"journal-article","created":{"date-parts":[[2026,1,14]],"date-time":"2026-01-14T07:52:45Z","timestamp":1768377165000},"page":"1730-1743","source":"Crossref","is-referenced-by-count":1,"title":["Mechanism\u2010informed machine learning for individualized tacrolimus dose adjustment in the early post\u2010kidney transplant period"],"prefix":"10.1002","volume":"92","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-1957-4622","authenticated-orcid":false,"given":"Hui","family":"Yu","sequence":"first","affiliation":[{"name":"Department of Pharmaceutical Sciences University of Michigan  Ann Arbor MI 48109 USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zihan","family":"Qin","sequence":"additional","affiliation":[{"name":"Department of Clinical Pharmacy University of Michigan  Ann Arbor MI 48109 USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Logan S.","family":"Smith","sequence":"additional","affiliation":[{"name":"Department of Clinical Pharmacy University of Michigan  Ann Arbor MI 48109 USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jeong M.","family":"Park","sequence":"additional","affiliation":[{"name":"Department of Clinical Pharmacy University of Michigan  Ann Arbor MI 48109 USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hao\u2010Jie","family":"Zhu","sequence":"additional","affiliation":[{"name":"Department of Clinical Pharmacy University of Michigan  Ann Arbor MI 48109 USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2026,1,13]]},"reference":[{"key":"e_1_2_11_2_1","doi-asserted-by":"publisher","DOI":"10.1517\/14656566.9.4.635"},{"key":"e_1_2_11_3_1","doi-asserted-by":"publisher","DOI":"10.1002\/cpt.1618"},{"key":"e_1_2_11_4_1","doi-asserted-by":"publisher","DOI":"10.1093\/ndt\/16.9.1905"},{"key":"e_1_2_11_5_1","doi-asserted-by":"publisher","DOI":"10.1111\/aor.13551"},{"key":"e_1_2_11_6_1","doi-asserted-by":"publisher","DOI":"10.1111\/j.1399\u20100012.2009.01021.x"},{"key":"e_1_2_11_7_1","doi-asserted-by":"publisher","DOI":"10.1111\/j.1432\u20102277.2012.01553.x"},{"key":"e_1_2_11_8_1","doi-asserted-by":"publisher","DOI":"10.1097\/FTD.0b013e3181a8f02a"},{"key":"e_1_2_11_9_1","doi-asserted-by":"publisher","DOI":"10.1111\/j.1600\u20106143.2009.02834.x"},{"key":"e_1_2_11_10_1","doi-asserted-by":"publisher","DOI":"10.1097\/FTD.0000000000000640"},{"key":"e_1_2_11_11_1","doi-asserted-by":"publisher","DOI":"10.1111\/j.1600\u20106143.2004.00383.x"},{"key":"e_1_2_11_12_1","doi-asserted-by":"publisher","DOI":"10.1097\/TP.0000000000000708"},{"key":"e_1_2_11_13_1","doi-asserted-by":"publisher","DOI":"10.1111\/bcp.12361"},{"key":"e_1_2_11_14_1","doi-asserted-by":"publisher","DOI":"10.2165\/00003088\u2010200443100\u201000001"},{"key":"e_1_2_11_15_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.phrs.2018.02.016"},{"key":"e_1_2_11_16_1","doi-asserted-by":"publisher","DOI":"10.1002\/cpt.2163"},{"key":"e_1_2_11_17_1","doi-asserted-by":"publisher","DOI":"10.1111\/bcp.13838"},{"key":"e_1_2_11_18_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.addr.2024.115421"},{"key":"e_1_2_11_19_1","doi-asserted-by":"publisher","DOI":"10.1007\/s40262\u2010024\u201001414\u2010y"},{"key":"e_1_2_11_20_1","doi-asserted-by":"publisher","DOI":"10.1007\/s40262\u2010020\u201000925\u20108"},{"key":"e_1_2_11_21_1","doi-asserted-by":"publisher","DOI":"10.1111\/bcp.12830"},{"key":"e_1_2_11_22_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41598\u2010024\u201071032\u2010y"},{"key":"e_1_2_11_23_1","doi-asserted-by":"publisher","DOI":"10.1111\/jcpt.13579"},{"key":"e_1_2_11_24_1","doi-asserted-by":"publisher","DOI":"10.1002\/cpt.3049"},{"key":"e_1_2_11_25_1","doi-asserted-by":"publisher","DOI":"10.1097\/FTD.0000000000001078"},{"key":"e_1_2_11_26_1","doi-asserted-by":"publisher","DOI":"10.1038\/srep42192"},{"key":"e_1_2_11_27_1","doi-asserted-by":"publisher","DOI":"10.3390\/biomedinformatics3040057"},{"key":"e_1_2_11_28_1","doi-asserted-by":"publisher","DOI":"10.3389\/fmed.2022.813117"},{"key":"e_1_2_11_29_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.healun.2024.10.026"},{"key":"e_1_2_11_30_1","doi-asserted-by":"publisher","DOI":"10.12659\/AOT.947768"},{"key":"e_1_2_11_31_1","unstructured":"Research C for DE and. Drug Development and Drug Interactions|Table of Substrates Inhibitors and Inducers. FDA;2024;https:\/\/www.fda.gov\/drugs\/drug-interactions-labeling\/drug-development-and-drug-interactions-table-substrates-inhibitors-and-inducers"},{"key":"e_1_2_11_32_1","doi-asserted-by":"publisher","DOI":"10.1007\/s40262\u2010025\u201001533\u20100"},{"key":"e_1_2_11_33_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijmedinf.2021.104679"},{"key":"e_1_2_11_34_1","doi-asserted-by":"publisher","DOI":"10.1002\/jcph.1325"},{"key":"e_1_2_11_35_1","doi-asserted-by":"publisher","DOI":"10.1080\/17425255.2023.2250251"},{"key":"e_1_2_11_36_1","doi-asserted-by":"publisher","DOI":"10.2165\/00003088\u2010200140040\u201000004"},{"key":"e_1_2_11_37_1","doi-asserted-by":"publisher","DOI":"10.3389\/fphar.2020.01142"},{"key":"e_1_2_11_38_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.trim.2023.101906"}],"container-title":["British Journal of Clinical Pharmacology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/bpspubs.onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/bcp.70448","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/bpspubs.onlinelibrary.wiley.com\/doi\/full-xml\/10.1002\/bcp.70448","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/bpspubs.onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/bcp.70448","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,26]],"date-time":"2026-05-26T07:45:34Z","timestamp":1779781534000},"score":1,"resource":{"primary":{"URL":"https:\/\/bpspubs.onlinelibrary.wiley.com\/doi\/10.1002\/bcp.70448"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1,13]]},"references-count":37,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2026,6]]}},"alternative-id":["10.1002\/bcp.70448"],"URL":"https:\/\/doi.org\/10.1002\/bcp.70448","archive":["Portico"],"relation":{},"ISSN":["0306-5251","1365-2125"],"issn-type":[{"value":"0306-5251","type":"print"},{"value":"1365-2125","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1,13]]}}}