{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,7]],"date-time":"2026-08-07T17:20:25Z","timestamp":1786123225370,"version":"build-2736575974"},"reference-count":26,"publisher":"Ovid Technologies (Wolters Kluwer Health)","issue":"5","content-domain":{"domain":["lww.com","ovid.com"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2020,11]]},"abstract":"<jats:sec>\n                    <jats:title>BACKGROUND:<\/jats:title>\n                    <jats:p>Induction of anesthesia is a phase characterized by rapid changes in both drug concentration and drug effect. Conventional mammillary compartmental models are limited in their ability to accurately describe the early drug distribution kinetics. Recirculatory models have been used to account for intravascular mixing after drug administration. However, these models themselves may be prone to misspecification. Artificial neural networks offer an advantage in that they are flexible and not limited to a specific structure and, therefore, may be superior in modeling complex nonlinear systems. They have been used successfully in the past to model steady-state or near steady-state kinetics, but never have they been used to model induction-phase kinetics using a high-resolution pharmacokinetic dataset. This study is the first to use an artificial neural network to model early- and late-phase kinetics of a drug.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>METHODS:<\/jats:title>\n                    <jats:p>Twenty morbidly obese and 10 lean subjects were each administered propofol for induction of anesthesia at a rate of 100 mg\/kg\/h based on lean body weight and total body weight for obese and lean subjects, respectively. High-resolution plasma samples were collected during the induction phase of anesthesia, with the last sample taken at 16 hours after propofol administration for a total of 47 samples per subject. Traditional mammillary compartment models, recirculatory models, and a gated recurrent unit neural network were constructed to model the propofol pharmacokinetics. Model performance was compared.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>RESULTS:<\/jats:title>\n                    <jats:p>A 4-compartment model, a recirculatory model, and a gated recurrent unit neural network were assessed. The final recirculatory model (mean prediction error: 0.348; mean square error: 23.92) and gated recurrent unit neural network that incorporated ensemble learning (mean prediction error: 0.161; mean square error: 20.83) had similar performance. Each of these models overpredicted propofol concentrations during the induction and elimination phases. Both models had superior performance compared to the 4-compartment model (mean prediction error: 0.108; mean square error: 31.61), which suffered from overprediction bias during the first 5 minutes followed by under-prediction bias after 5 minutes.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>CONCLUSIONS:<\/jats:title>\n                    <jats:p>A recirculatory model and gated recurrent unit artificial neural network that incorporated ensemble learning both had similar performance and were both superior to a compartmental model in describing our high-resolution pharmacokinetic data of propofol. The potential of neural networks in pharmacokinetic modeling is encouraging but may be limited by the amount of training data available for these models.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1213\/ane.0000000000004897","type":"journal-article","created":{"date-parts":[[2020,6,1]],"date-time":"2020-06-01T07:12:59Z","timestamp":1590995579000},"page":"1500-1509","update-policy":"https:\/\/doi.org\/10.1097\/lww.0000000000001000","source":"Crossref","is-referenced-by-count":15,"title":["The Performance of an Artificial Neural Network Model in Predicting the Early Distribution Kinetics of Propofol in Morbidly Obese and Lean Subjects"],"prefix":"10.1213","volume":"131","author":[{"given":"Jerry","family":"Ingrande","sequence":"first","affiliation":[{"name":"Department of Anesthesiology"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rodney A.","family":"Gabriel","sequence":"additional","affiliation":[{"name":"Department of Anesthesiology"},{"name":"Division of Biomedical Informatics, Department of Medicine, University of California, San Diego School of Medicine, La Jolla, California"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Julian","family":"McAuley","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, University of California, San Diego, La Jolla, California"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Karolina","family":"Krasinska","sequence":"additional","affiliation":[{"name":"Stanford University Mass Spectrometry Laboratory, Stanford, California"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Allis","family":"Chien","sequence":"additional","affiliation":[{"name":"Stanford University Mass Spectrometry Laboratory, Stanford, California"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hendrikus J. M.","family":"Lemmens","sequence":"additional","affiliation":[{"name":"Department of Anesthesiology, Perioperative and Pain Medicine, Stanford University School of Medicine, Stanford, California."}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"276","published-online":{"date-parts":[[2020,5,29]]},"reference":[{"key":"R1-20250227","doi-asserted-by":"crossref","first-page":"901","DOI":"10.1213\/00000539-199611000-00002","article-title":"(Almost) everything you learned about pharmacokinetics was (somewhat) wrong!.","volume":"83","author":"Fisher","year":"1996","journal-title":"Anesth Analg"},{"key":"R2-20250227","doi-asserted-by":"crossref","first-page":"805","DOI":"10.1097\/ALN.0b013e3181b799c1","article-title":"Early phase pharmacokinetics but not pharmacodynamics are influenced by propofol infusion rate.","volume":"111","author":"Masui","year":"2009","journal-title":"Anesthesiology"},{"key":"R3-20250227","doi-asserted-by":"crossref","first-page":"615","DOI":"10.1023\/A:1025769431364","article-title":"A semiparametric method for describing noisy population pharmacokinetic data.","volume":"25","author":"Park","year":"1997","journal-title":"J Pharmacokinet Biopharm"},{"key":"R4-20250227","doi-asserted-by":"crossref","first-page":"223","DOI":"10.1213\/ANE.0b013e318240139b","article-title":"Recirculatory pharmacokinetic modeling: what goes around, comes around.","volume":"115","author":"Krejcie","year":"2012","journal-title":"Anesth Analg"},{"key":"R5-20250227","doi-asserted-by":"crossref","first-page":"368","DOI":"10.1213\/ANE.0b013e3181bdcf5b","article-title":"The performance of compartmental and physiologically based recirculatory pharmacokinetic models for propofol: a comparison using bolus, continuous, and target-controlled infusion data.","volume":"111","author":"Masui","year":"2010","journal-title":"Anesth Analg"},{"key":"R6-20250227","doi-asserted-by":"crossref","first-page":"48","DOI":"10.1111\/bcp.12234","article-title":"Combining the \u2018bottom up\u2019 and \u2018top down\u2019 approaches in pharmacokinetic modelling: fitting PBPK models to observed clinical data.","volume":"79","author":"Tsamandouras","year":"2015","journal-title":"Br J Clin Pharmacol"},{"key":"R7-20250227","doi-asserted-by":"crossref","first-page":"e1005153","DOI":"10.1371\/journal.pcbi.1005153","article-title":"Structural identifiability of dynamic systems biology models.","volume":"12","author":"Villaverde","year":"2016","journal-title":"PLoS Comput Biol"},{"key":"R8-20250227","doi-asserted-by":"crossref","first-page":"431","DOI":"10.1097\/ALN.0000000000001984","article-title":"Artificial intelligence for everyone.","volume":"128","author":"Gambus","year":"2018","journal-title":"Anesthesiology"},{"key":"R9-20250227","doi-asserted-by":"crossref","first-page":"1044","DOI":"10.1592\/phco.23.8.1044.32872","article-title":"Comparison of neural network, Bayesian, and multiple stepwise regression-based limited sampling models to estimate area under the curve.","volume":"23","author":"Ng","year":"2003","journal-title":"Pharmacotherapy"},{"key":"R10-20250227","doi-asserted-by":"crossref","first-page":"840","DOI":"10.1021\/js9604016","article-title":"Application of neural networks to population pharmacokinetic data analysis.","volume":"86","author":"Chow","year":"1997","journal-title":"J Pharm Sci"},{"key":"R11-20250227","first-page":"510","article-title":"Application of artificial neural networks to clinical pharmacology.","volume":"34","author":"Brier","year":"1996","journal-title":"Int J Clin Pharmacol Ther"},{"key":"R12-20250227","doi-asserted-by":"crossref","first-page":"57","DOI":"10.1213\/ANE.0b013e3181f6d9c0","article-title":"Lean body weight scalar for the anesthetic induction dose of propofol in morbidly obese subjects.","volume":"113","author":"Ingrande","year":"2011","journal-title":"Anesth Analg"},{"key":"R14-20250227","doi-asserted-by":"crossref","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","article-title":"Long short-term memory.","volume":"9","author":"Hochreiter","year":"1997","journal-title":"Neural Comput"},{"key":"R15-20250227","doi-asserted-by":"crossref","first-page":"2451","DOI":"10.1162\/089976600300015015","article-title":"Learning to forget: continual prediction with LSTM.","volume":"12","author":"Gers","year":"2000","journal-title":"Neural Comput"},{"key":"R20-20250227","first-page":"97","article-title":"Machine-learning research: four current directions.","volume":"18","author":"Dietterich","year":"1997","journal-title":"AI Magazine"},{"key":"R21-20250227","doi-asserted-by":"crossref","first-page":"S78","DOI":"10.1016\/j.ejps.2017.05.021","article-title":"Combined proportional and additive residual error models in population pharmacokinetic modelling.","volume":"109S","author":"Proost","year":"2017","journal-title":"Eur J Pharm Sci"},{"key":"R22-20250227","first-page":"541","article-title":"What determines anesthetic induction dose? It\u2019s the front-end kinetics, doctor!.","volume":"89","author":"Krejcie","year":"1999","journal-title":"Anesth Analg"},{"key":"R23-20250227","doi-asserted-by":"crossref","first-page":"121","DOI":"10.1007\/BF00613938","article-title":"Modelling of initial distribution of drugs following intravenous bolus injection.","volume":"24","author":"Weiss","year":"1983","journal-title":"Eur J Clin Pharmacol"},{"key":"R24-20250227","doi-asserted-by":"crossref","first-page":"919","DOI":"10.1002\/jps.2600750922","article-title":"The initial rate of change in distribution volume is the sum of intercompartmental clearances.","volume":"75","author":"Avram","year":"1986","journal-title":"J Pharm Sci"},{"key":"R25-20250227","doi-asserted-by":"crossref","first-page":"823","DOI":"10.1213\/ANE.0b013e31825d6254","article-title":"The effective effect-site propofol concentration for induction and intubation with two pharmacokinetic models in morbidly obese patients using total body weight.","volume":"115","author":"Echevarr\u00eda","year":"2012","journal-title":"Anesth Analg"},{"key":"R26-20250227","doi-asserted-by":"crossref","first-page":"1078","DOI":"10.1097\/00000542-200311000-00013","article-title":"Using front-end kinetics to optimize target-controlled drug infusions.","volume":"99","author":"Avram","year":"2003","journal-title":"Anesthesiology"},{"key":"R27-20250227","doi-asserted-by":"crossref","first-page":"344","DOI":"10.1097\/00000542-200508000-00018","article-title":"A physiologically based, recirculatory model of the kinetics and dynamics of propofol in man.","volume":"103","author":"Upton","year":"2005","journal-title":"Anesthesiology"},{"key":"R28-20250227","doi-asserted-by":"crossref","first-page":"157","DOI":"10.1109\/72.279181","article-title":"Learning long-term dependencies with gradient descent is difficult.","volume":"5","author":"Bengio","year":"1994","journal-title":"IEEE Trans Neural Netw"},{"key":"R29-20250227","doi-asserted-by":"crossref","first-page":"492","DOI":"10.1097\/ALN.0000000000001892","article-title":"Prediction of bispectral index during target-controlled infusion of propofol and remifentanil: a deep learning approach.","volume":"128","author":"Lee","year":"2018","journal-title":"Anesthesiology"},{"key":"R30-20250227","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1162\/neco.1992.4.1.1","article-title":"Neural networks and the bias\/variance dilemma.","volume":"4","author":"Geman","year":"1992","journal-title":"Neural Comput"},{"key":"R31-20250227","doi-asserted-by":"crossref","first-page":"1170","DOI":"10.1097\/00000542-199805000-00006","article-title":"The influence of method of administration and covariates on the pharmacokinetics of propofol in adult volunteers.","volume":"88","author":"Schnider","year":"1998","journal-title":"Anesthesiology"}],"container-title":["Anesthesia &amp; Analgesia"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.ovid.com\/10.1213\/ANE.0000000000004897","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,7]],"date-time":"2026-08-07T14:26:02Z","timestamp":1786112762000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.ovid.com\/10.1213\/ANE.0000000000004897"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,5,29]]},"references-count":26,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2020]]}},"URL":"https:\/\/doi.org\/10.1213\/ane.0000000000004897","relation":{},"ISSN":["0003-2999"],"issn-type":[{"value":"0003-2999","type":"print"}],"subject":[],"published":{"date-parts":[[2020,5,29]]}}}