{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,23]],"date-time":"2026-09-23T16:40:07Z","timestamp":1790181607512,"version":"4.1.0"},"reference-count":33,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2023,10,21]],"date-time":"2023-10-21T00:00:00Z","timestamp":1697846400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2023,10,21]],"date-time":"2023-10-21T00:00:00Z","timestamp":1697846400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100004063","name":"Knut and Alice Wallenberg Foundation","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100004063","id-type":"DOI","asserted-by":"crossref"}]},{"name":"ELLIIT Strategic Research Area"},{"DOI":"10.13039\/501100003252","name":"Lund University","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100003252","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Pharmacokinet Pharmacodyn"],"published-print":{"date-parts":[[2024,4]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Efficiently finding covariate model structures that minimize the need for random effects to describe pharmacological data is challenging. The standard approach focuses on identification of relevant covariates, and present methodology lacks tools for automatic identification of covariate model structures. Although neural networks could potentially be used to approximate covariate-parameter relationships, such approximations are not human-readable and come at the risk of poor generalizability due to high model complexity.In the present study, a novel methodology for the simultaneous selection of covariate model structure and optimization of its parameters is proposed. It is based on symbolic regression, posed as an optimization problem with a smooth loss function. This enables training of the model through back-propagation using efficient gradient computations.Feasibility and effectiveness are demonstrated by application to a clinical pharmacokinetic data set for propofol, containing infusion and blood sample time series from 1031 individuals. The resulting model is compared to a published state-of-the-art model for the same data set. Our methodology finds a covariate model structure and corresponding parameter values with a slightly better fit, while relying on notably fewer covariates than the state-of-the-art model. Unlike contemporary practice, finding the covariate model structure is achieved without an iterative procedure involving manual interactions.<\/jats:p>","DOI":"10.1007\/s10928-023-09887-3","type":"journal-article","created":{"date-parts":[[2023,10,21]],"date-time":"2023-10-21T04:02:27Z","timestamp":1697860947000},"page":"155-167","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":8,"title":["Learning pharmacometric covariate model structures with symbolic regression networks"],"prefix":"10.1007","volume":"51","author":[{"given":"Ylva","family":"Wahlquist","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jesper","family":"Sundell","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kristian","family":"Soltesz","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2023,10,21]]},"reference":[{"issue":"6","key":"9887_CR1","doi-asserted-by":"publisher","first-page":"553","DOI":"10.1007\/BF01060053","volume":"8","author":"LB Sheiner","year":"1980","unstructured":"Sheiner LB, Beal SL (1980) Evaluation of methods for estimating population pharmacokinetics parameters. i. Michaelis-Menten model: routine clinical pharmacokinetic data. J Pharmacokinet Biopharm 8(6):553\u2013571. https:\/\/doi.org\/10.1007\/BF01060053","journal-title":"J Pharmacokinet Biopharm"},{"key":"9887_CR2","doi-asserted-by":"publisher","unstructured":"Rackauckas C, Ma Y, Noack A, et\u00a0al (2020) Accelerated predictive healthcare analytics with pumas, a high performance pharmaceutical modeling and simulation platform. bioRxiv https:\/\/doi.org\/10.1101\/2020.11.28.402297","DOI":"10.1101\/2020.11.28.402297"},{"issue":"1","key":"9887_CR3","doi-asserted-by":"publisher","first-page":"41","DOI":"10.1093\/bja\/67.1.41","volume":"67","author":"B Marsh","year":"1991","unstructured":"Marsh B, White M, Morton N et al (1991) Pharmacokinetic model driven infusion of propofol in children. Brit J Anaesth 67(1):41\u201348. https:\/\/doi.org\/10.1093\/bja\/67.1.41","journal-title":"Brit J Anaesth"},{"issue":"5","key":"9887_CR4","doi-asserted-by":"publisher","first-page":"942","DOI":"10.1016\/j.bja.2018.01.018","volume":"120","author":"DJ Eleveld","year":"2018","unstructured":"Eleveld DJ, Colin P, Absalom AR et al (2018) Pharmacokinetic\u2013pharmacodynamic model for propofol for broad application in anaesthesia and sedation. Brit J Anaesth 120(5):942\u2013959. https:\/\/doi.org\/10.1016\/j.bja.2018.01.018","journal-title":"Brit J Anaesth"},{"issue":"9","key":"9887_CR5","doi-asserted-by":"publisher","first-page":"1463","DOI":"10.1023\/a:1011970125687","volume":"15","author":"EN Jonsson","year":"1998","unstructured":"Jonsson EN, Karlsson MO (1998) Automated covariate model building within NONMEM. Pharm Res 15(9):1463\u20131468. https:\/\/doi.org\/10.1023\/a:1011970125687","journal-title":"Pharm Res"},{"issue":"4","key":"9887_CR6","doi-asserted-by":"publisher","first-page":"1482","DOI":"10.1111\/bcp.14801","volume":"88","author":"M McComb","year":"2022","unstructured":"McComb M, Bies R, Ramanathan M (2022) Machine learning in pharmacometrics: opportunities and challenges. British J Clin Pharmacol 88(4):1482\u20131499. https:\/\/doi.org\/10.1111\/bcp.14801","journal-title":"British J Clin Pharmacol"},{"issue":"6","key":"9887_CR7","doi-asserted-by":"publisher","first-page":"745","DOI":"10.1002\/psp4.12786","volume":"11","author":"DS Br\u00e4m","year":"2022","unstructured":"Br\u00e4m DS, Parrott N, Hutchinson L et al (2022) Introduction of an artificial neural network-based method for concentration-time predictions. Pharmacometr Syst Pharmacol 11(6):745\u2013754. https:\/\/doi.org\/10.1002\/psp4.12786","journal-title":"Pharmacometr Syst Pharmacol"},{"issue":"8","key":"9887_CR8","doi-asserted-by":"publisher","first-page":"1100","DOI":"10.1002\/psp4.12828","volume":"11","author":"A Janssen","year":"2022","unstructured":"Janssen A, Hoogendoorn M, Cnossen MH et al (2022) Application of SHAP values for inferring the optimal functional form of covariates in pharmacokinetic modeling. Pharmacometr Syst Pharmacol 11(8):1100\u20131110. https:\/\/doi.org\/10.1002\/psp4.12828","journal-title":"Pharmacometr Syst Pharmacol"},{"issue":"4","key":"9887_CR9","doi-asserted-by":"publisher","first-page":"597","DOI":"10.1007\/s10928-021-09757-w","volume":"48","author":"E Sibieude","year":"2021","unstructured":"Sibieude E, Khandelwal A, Hesthaven JS et al (2021) Fast screening of covariates in population models empowered by machine learning. J Pharmacokinet Pharmacodyn 48(4):597\u2013609. https:\/\/doi.org\/10.1007\/s10928-021-09757-w","journal-title":"J Pharmacokinet Pharmacodyn"},{"issue":"2","key":"9887_CR10","doi-asserted-by":"publisher","first-page":"257","DOI":"10.1007\/s10928-021-09793-6","volume":"49","author":"E Sibieude","year":"2022","unstructured":"Sibieude E, Khandelwal A, Girard P et al (2022) Population pharmacokinetic model selection assisted by machine learning. J Pharmacokin Pharmacodyn 49(2):257\u2013270. https:\/\/doi.org\/10.1007\/s10928-021-09793-6","journal-title":"J Pharmacokin Pharmacodyn"},{"issue":"1","key":"9887_CR11","doi-asserted-by":"publisher","first-page":"95","DOI":"10.1016\/S0020-0255(02)00371-7","volume":"150","author":"JW Davidson","year":"2003","unstructured":"Davidson JW, Savic DA, Walters GA (2003) Symbolic and numerical regression: experiments and applications. Inf Sci 150(1):95\u2013117. https:\/\/doi.org\/10.1016\/S0020-0255(02)00371-7","journal-title":"Inf Sci"},{"issue":"5","key":"9887_CR12","doi-asserted-by":"publisher","first-page":"1170","DOI":"10.1097\/00000542-199805000-00006","volume":"88","author":"TW Schnider","year":"1998","unstructured":"Schnider TW, Minto CF, Gambus PL et al (1998) The influence of method of administration and covariates on the pharmacokinetics of propofol in adult volunteers. Anesthesiology 88(5):1170\u20131182. https:\/\/doi.org\/10.1097\/00000542-199805000-00006","journal-title":"Anesthesiology"},{"key":"9887_CR13","doi-asserted-by":"crossref","unstructured":"Wahlquist Y, Bagge Carlson F, Soltesz K (2023) Fast simulation of pharmacokinetics. IFAC PapersOnline","DOI":"10.1016\/j.ifacol.2023.10.1425"},{"issue":"2","key":"9887_CR14","doi-asserted-by":"publisher","first-page":"368","DOI":"10.1213\/ANE.0b013e3181bdcf5b","volume":"111","author":"K Masui","year":"2010","unstructured":"Masui K, Upton RN, Doufas AG et al (2010) The performance of compartmental and physiologically based recirculatory pharmacokinetic models for propofol: a comparison using bolus, continuous, and target-controlled infusion data. Anesth Analg 111(2):368\u2013379. https:\/\/doi.org\/10.1213\/ANE.0b013e3181bdcf5b","journal-title":"Anesth Analg"},{"issue":"1","key":"9887_CR15","doi-asserted-by":"publisher","first-page":"63","DOI":"10.1007\/BF01143186","volume":"20","author":"JR Varvel","year":"1992","unstructured":"Varvel JR, Donoho DL, Shafer SL (1992) Measuring the predictive performance of computer-controlled infusion pumps. J Pharmacokinet Biopharm 20(1):63\u201394. https:\/\/doi.org\/10.1007\/BF01143186","journal-title":"J Pharmacokinet Biopharm"},{"issue":"s1","key":"9887_CR16","doi-asserted-by":"publisher","first-page":"2","DOI":"10.1111\/j.1365-2044.1988.tb09059.x","volume":"43","author":"J Sch\u00fcttler","year":"1988","unstructured":"Sch\u00fcttler J, Kloos S, Schwilden H et al (1988) Total intravenous anaesthesia with propofol and alfentanil by computer-assisted infusion. Anaesthesia 43(s1):2\u20137. https:\/\/doi.org\/10.1111\/j.1365-2044.1988.tb09059.x","journal-title":"Anaesthesia"},{"key":"9887_CR17","doi-asserted-by":"publisher","unstructured":"Martius G, Lampert CH (2017) Extrapolation and learning equations. In: 5th International Conference on Learning Representations, ICLR 2017, Toulon https:\/\/doi.org\/10.48550\/arXiv.1610.02995","DOI":"10.48550\/arXiv.1610.02995"},{"key":"9887_CR18","doi-asserted-by":"publisher","first-page":"92","DOI":"10.1016\/j.neucom.2022.06.111","volume":"503","author":"SR Dubey","year":"2022","unstructured":"Dubey SR, Singh SK, Chaudhuri BB (2022) Activation functions in deep learning: a comprehensive survey and benchmark. Neurocomputing 503:92\u2013108. https:\/\/doi.org\/10.1016\/j.neucom.2022.06.111","journal-title":"Neurocomputing"},{"key":"9887_CR19","doi-asserted-by":"publisher","unstructured":"Orzechowski P, La Cava W, Moore JH (2018) Where are we now? a large benchmark study of recent symbolic regression methods. In: Proceedings of the Genetic and Evolutionary Computation Conference, Kyoto, pp 1183\u20141190, https:\/\/doi.org\/10.1145\/3205455.3205539","DOI":"10.1145\/3205455.3205539"},{"key":"9887_CR20","doi-asserted-by":"publisher","unstructured":"Sahoo SS, Lampert CH, Martius G (2018) Learning equations for extrapolation and control. In: Proceedings of the 35th International Conference on Machine Learning, ICML 2018, Stockholm, Sweden, Proceedings of Machine Learning Research, vol\u00a080. PMLR, pp 4439\u20134447, https:\/\/doi.org\/10.48550\/arXiv.1806.07259","DOI":"10.48550\/arXiv.1806.07259"},{"issue":"9","key":"9887_CR21","doi-asserted-by":"publisher","first-page":"4166","DOI":"10.1109\/TNNLS.2020.3017010","volume":"32","author":"S Kim","year":"2021","unstructured":"Kim S, Lu PY, Mukherjee S et al (2021) Integration of neural network-based symbolic regression in deep learning for scientific discovery. IEEE Trans Neural Networks Learn Syst 32(9):4166\u20134177. https:\/\/doi.org\/10.1109\/TNNLS.2020.3017010","journal-title":"IEEE Trans Neural Networks Learn Syst"},{"key":"9887_CR22","doi-asserted-by":"publisher","unstructured":"Udrescu SM, Tan A, Feng J, et\u00a0al (2020) AI feynman 2.0: Pareto-optimal symbolic regression exploiting graph modularity. In: Proceedings of the 34th International Conference on Neural Information Processing Systems, NIPS\u201920, pp 4860\u20134871, https:\/\/doi.org\/10.48550\/arXiv.2006.10782","DOI":"10.48550\/arXiv.2006.10782"},{"key":"9887_CR23","doi-asserted-by":"publisher","DOI":"10.1007\/BF00175355","volume-title":"Genetic programming: on the programming of computers by means of natural selection","author":"JR Koza","year":"1992","unstructured":"Koza JR (1992) Genetic programming: on the programming of computers by means of natural selection. MIT Press, Cambridge. https:\/\/doi.org\/10.1007\/BF00175355"},{"key":"9887_CR24","doi-asserted-by":"publisher","unstructured":"Kingma DP, Ba J (2017) Adam: A method for stochastic optimization. In: Proceedings of the 3rd International Conference on Learning Representations (ICLR), https:\/\/doi.org\/10.48550\/arXiv.1412.6980","DOI":"10.48550\/arXiv.1412.6980"},{"key":"9887_CR25","doi-asserted-by":"publisher","DOI":"10.21105\/joss.00602","author":"M Innes","year":"2018","unstructured":"Innes M (2018) Flux: elegant machine learning with Julia. J Open Source Softw. https:\/\/doi.org\/10.21105\/joss.00602","journal-title":"J Open Source Softw"},{"issue":"1","key":"9887_CR26","doi-asserted-by":"publisher","first-page":"65","DOI":"10.1137\/141000671","volume":"59","author":"J Bezanson","year":"2017","unstructured":"Bezanson J, Edelman A, Karpinski S et al (2017) Julia: a fresh approach to numerical computing. SIAM Rev 59(1):65\u201398. https:\/\/doi.org\/10.1137\/141000671","journal-title":"SIAM Rev"},{"key":"9887_CR27","unstructured":"Wahlquist Y (2023) Learning pharmacometric structures. https:\/\/github.com\/wahlquisty\/learning-pharmacometric-covariate-structures, commit: dfafb1f"},{"key":"9887_CR28","unstructured":"LeCun Y, Denker J, Solla S (1989) Optimal brain damage. In: Advances in neural information processing systems, vol\u00a02. Morgan-Kaufmann"},{"key":"9887_CR29","unstructured":"Innes M (2018) Don\u2019t unroll adjoint: Differentiating SSA-form programs. CoRR arXiv1810.07951"},{"key":"9887_CR30","doi-asserted-by":"publisher","unstructured":"Wahlquist Y, Morin M, Soltesz K (2022) Pharmacometric covariate modeling using symbolic regression networks. In: 2022 IEEE Conference on Control Technology and Applications (CCTA), pp 1\u201324, https:\/\/doi.org\/10.1109\/CCTA41146.2020.9206396","DOI":"10.1109\/CCTA41146.2020.9206396"},{"issue":"24","key":"9887_CR31","doi-asserted-by":"publisher","first-page":"615","DOI":"10.21105\/joss.00615","volume":"3","author":"PK Mogensen","year":"2018","unstructured":"Mogensen PK, Riseth AN (2018) Optim: a mathematical optimization package for Julia. J Open Source Softw 3(24):615. https:\/\/doi.org\/10.21105\/joss.00615","journal-title":"J Open Source Softw"},{"issue":"5309","key":"9887_CR32","doi-asserted-by":"publisher","first-page":"122","DOI":"10.1126\/science.276.5309.122","volume":"276","author":"GB West","year":"1997","unstructured":"West GB, Brown JH, Enquist BJ (1997) A general model for the origin of allometric scaling laws in biology. Science 276(5309):122\u2013126. https:\/\/doi.org\/10.1126\/science.276.5309.122","journal-title":"Science"},{"key":"9887_CR33","doi-asserted-by":"publisher","first-page":"303","DOI":"10.1146\/annurev.pharmtox.48.113006.094708","volume":"48","author":"BJ Anderson","year":"2008","unstructured":"Anderson BJ, Holford NHG (2008) Mechanism-based concepts of size and maturity in pharmacokinetics. Ann Rev Pharmacol Toxicol 48:303\u2013332. https:\/\/doi.org\/10.1146\/annurev.pharmtox.48.113006.094708","journal-title":"Ann Rev Pharmacol Toxicol"}],"container-title":["Journal of Pharmacokinetics and Pharmacodynamics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10928-023-09887-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10928-023-09887-3\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10928-023-09887-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,21]],"date-time":"2024-09-21T13:02:23Z","timestamp":1726923743000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10928-023-09887-3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,21]]},"references-count":33,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2024,4]]}},"alternative-id":["9887"],"URL":"https:\/\/doi.org\/10.1007\/s10928-023-09887-3","relation":{"has-preprint":[{"id-type":"doi","id":"10.21203\/rs.3.rs-3062691\/v1","asserted-by":"object"}]},"ISSN":["1567-567X","1573-8744"],"issn-type":[{"value":"1567-567X","type":"print"},{"value":"1573-8744","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,10,21]]},"assertion":[{"value":"14 June 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"18 September 2023","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"21 October 2023","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}