{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,27]],"date-time":"2026-08-27T17:50:00Z","timestamp":1787853000720,"version":"build-2784847793"},"reference-count":20,"publisher":"Wiley","issue":"2","license":[{"start":{"date-parts":[[2025,11,10]],"date-time":"2025-11-10T00:00:00Z","timestamp":1762732800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"},{"start":{"date-parts":[[2025,11,10]],"date-time":"2025-11-10T00:00:00Z","timestamp":1762732800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/doi.wiley.com\/10.1002\/tdm_license_1.1"}],"content-domain":{"domain":["ascpt.onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Clin Pharma and Therapeutics"],"published-print":{"date-parts":[[2026,2]]},"abstract":"<jats:p>\n                    Accurately labeling outcomes in real\u2010world data for machine learning is challenging due to data sparsity and imbalances. This study developed and evaluated a pharmacokinetic\u2013pharmacodynamic (PKPD)\u2010informed labeling strategy to enhance the risk prediction of docetaxel\u2010induced neutropenia. Machine learning models were trained on real\u2010world data from 4,248 patients using two approaches for comparison. The \u201cnaive\u201d labeling method used only neutrophil observations, while the \u201cPKPD\u2010informed\u201d method used simulations from a semi\u2010mechanistic model to determine the neutrophil nadir for each treatment cycle. Three machine learning models (logistic regression, XGBoost, TabPFN) were trained with baseline laboratory data to predict severe neutropenia (neutrophil count &lt;0.1 cells \u00d7\u200910\n                    <jats:sup>9<\/jats:sup>\n                    \/L) prior to the first docetaxel dose. The PKPD labeling approach enabled the labeling of 3.4 times more patient instances (7,719 vs. 2,283) than the naive method. Across all machine learning architectures, models trained with PKPD\u2010informed labels demonstrated significantly superior predictive performance (AUC\u2010ROC and AUC\u2010PR) compared to those trained with naive labels. This advantage was maintained even when training set sizes were matched. PKPD\u2010informed labeling overcomes limitations of sparse real\u2010world data, increasing both the quantity and apparent quality of labels for machine learning model training. This methodology enhances the performance of machine learning models for predicting severe neutropenia and represents a robust, generalizable framework for improving clinical outcome prediction.\n                  <\/jats:p>","DOI":"10.1002\/cpt.70116","type":"journal-article","created":{"date-parts":[[2025,11,10]],"date-time":"2025-11-10T09:14:28Z","timestamp":1762766068000},"page":"427-436","update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Enhancing Severe Neutropenia Prediction:\n                    <scp>PKPD<\/scp>\n                    \u2010Informed Labeling for Machine Learning Models Trained on Real\u2010World Data"],"prefix":"10.1002","volume":"119","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2369-2858","authenticated-orcid":false,"given":"Conor J","family":"O\u2019Hanlon","sequence":"first","affiliation":[{"name":"Roche Informatics, F. Hoffmann\u2010La Roche AG  Kaiseraugst Switzerland"},{"name":"Roche Pharmaceutical Research and Early Development, Roche Innovation Center  Basel Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1980-1073","authenticated-orcid":false,"given":"Jonas","family":"Denck","sequence":"additional","affiliation":[{"name":"Roche Informatics, F. Hoffmann\u2010La Roche AG  Kaiseraugst Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3206-8427","authenticated-orcid":false,"given":"Elif","family":"Ozkirimli","sequence":"additional","affiliation":[{"name":"Roche Informatics, F. Hoffmann\u2010La Roche AG  Kaiseraugst Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Stefanie","family":"Bendels","sequence":"additional","affiliation":[{"name":"Roche Informatics, F. Hoffmann\u2010La Roche AG  Kaiseraugst Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7018-9687","authenticated-orcid":false,"given":"Candice","family":"Jamois","sequence":"additional","affiliation":[{"name":"Roche Pharmaceutical Research and Early Development, Roche Innovation Center  Basel Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Clarisse","family":"Chavanne","sequence":"additional","affiliation":[{"name":"Roche Pharmaceutical Research and Early Development, Roche Innovation Center  Basel Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dirk","family":"Fey","sequence":"additional","affiliation":[{"name":"iCAN Digital Precision Cancer Medicine Flagship, University of Helsinki and Helsinki University Hospital Comprehensive Cancer Center  Helsinki Finland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kimmo","family":"Porkka","sequence":"additional","affiliation":[{"name":"iCAN Digital Precision Cancer Medicine Flagship, University of Helsinki and Helsinki University Hospital Comprehensive Cancer Center  Helsinki Finland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7842-9419","authenticated-orcid":false,"given":"Oscar","family":"Br\u00fcck","sequence":"additional","affiliation":[{"name":"Hematoscope Lab, Comprehensive Cancer Center, Helsinki University Hospital  Helsinki Finland"},{"name":"Department of Oncology University of Helsinki  Helsinki Finland"},{"name":"Department of Clinical Chemistry, HUS Diagnostic Center, Helsinki University Hospital  Helsinki Finland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3497-5458","authenticated-orcid":false,"given":"Ken","family":"Wang","sequence":"additional","affiliation":[{"name":"Roche Pharmaceutical Research and Early Development, Roche Innovation Center  Basel Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2025,11,10]]},"reference":[{"key":"e_1_2_11_1_1","doi-asserted-by":"publisher","DOI":"10.1002\/cpt.2988"},{"key":"e_1_2_11_2_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.addr.2024.115421"},{"key":"e_1_2_11_3_1","doi-asserted-by":"publisher","DOI":"10.1186\/s12874-022-01768-6"},{"key":"e_1_2_11_4_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.drudis.2023.103715"},{"key":"e_1_2_11_5_1","doi-asserted-by":"publisher","DOI":"10.1002\/psp4.12684"},{"key":"e_1_2_11_6_1","doi-asserted-by":"publisher","DOI":"10.1002\/cpt.3176"},{"key":"e_1_2_11_7_1","doi-asserted-by":"publisher","DOI":"10.1002\/cpt.3371"},{"key":"e_1_2_11_8_1","doi-asserted-by":"publisher","DOI":"10.1002\/psp4.13019"},{"key":"e_1_2_11_9_1","doi-asserted-by":"publisher","DOI":"10.3390\/pharmaceutics14081530"},{"key":"e_1_2_11_10_1","doi-asserted-by":"publisher","DOI":"10.1182\/bloodadvances.2023012316"},{"key":"e_1_2_11_11_1","doi-asserted-by":"publisher","DOI":"10.1159\/000366466"},{"key":"e_1_2_11_12_1","doi-asserted-by":"publisher","DOI":"10.1093\/jamia\/ocad247"},{"key":"e_1_2_11_13_1","doi-asserted-by":"publisher","DOI":"10.3389\/fphar.2021.790952"},{"key":"e_1_2_11_14_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00280-016-3157-9"},{"key":"e_1_2_11_15_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cmpb.2003.11.003"},{"key":"e_1_2_11_16_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0169-2607(98)00098-4"},{"key":"e_1_2_11_17_1","unstructured":"Holford N.The visual predictive check\u2014superiority to standard diagnostic (Rorschach) plots. In: PAGE [Internet]. Pamploma Spain<https:\/\/www.page\u2010meeting.org\/?abstract=738> (2005)."},{"key":"e_1_2_11_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/2939672.2939785"},{"key":"e_1_2_11_19_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-024-08328-6"},{"key":"e_1_2_11_20_1","doi-asserted-by":"publisher","DOI":"10.1200\/JCO.2002.02.140"}],"container-title":["Clinical Pharmacology &amp; Therapeutics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/ascpt.onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/cpt.70116","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/ascpt.onlinelibrary.wiley.com\/doi\/full-xml\/10.1002\/cpt.70116","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/ascpt.onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/cpt.70116","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,12]],"date-time":"2026-02-12T11:15:39Z","timestamp":1770894939000},"score":1,"resource":{"primary":{"URL":"https:\/\/ascpt.onlinelibrary.wiley.com\/doi\/10.1002\/cpt.70116"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,10]]},"references-count":20,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2026,2]]}},"alternative-id":["10.1002\/cpt.70116"],"URL":"https:\/\/doi.org\/10.1002\/cpt.70116","archive":["Portico"],"relation":{},"ISSN":["0009-9236","1532-6535"],"issn-type":[{"value":"0009-9236","type":"print"},{"value":"1532-6535","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11,10]]},"assertion":[{"value":"2025-07-30","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-10-15","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-11-10","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}