{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,15]],"date-time":"2026-09-15T12:31:12Z","timestamp":1789475472082,"version":"build-2803163510"},"reference-count":38,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,3,13]],"date-time":"2026-03-13T00:00:00Z","timestamp":1773360000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Chem."],"abstract":"<jats:p>\n                    This research investigates the predictive performance of ensemble learning models, specifically Bagging, when combined with weak models including Polynomial Regression (PR), K-Nearest Neighbors (KNN), and Gamma Regression (GR) to estimate drug solubility in supercritical carbon dioxide as the solvent. The models were trained and optimized using the Bat Algorithm (BA). The objective was to accurately predict two important properties: CO\n                    <jats:sub>2<\/jats:sub>\n                    density and the solubility of phenytoin in it. The bagging technique was applied to combine the predictions of multiple weak models, enhancing overall performance. The results demonstrated remarkable predictive capabilities of the Bagging model with Polynomial Regression (BAG + PR) for both CO\n                    <jats:sub>2<\/jats:sub>\n                    density and drug solubility. It achieved a high\n                    <jats:italic>R<\/jats:italic>\n                    <jats:sup>2<\/jats:sup>\n                    score of 0.9949 for CO\n                    <jats:sub>2<\/jats:sub>\n                    density and 0.97833 for solubility. The BAG + PR model also exhibited the lowest Root Mean Square Error (RMSE), indicating superior accuracy in predictions. Moreover, it exhibited the lowest Average Absolute Relative Deviation (AARD%) and Maximum Error, further validating its effectiveness in accurately capturing the relationships among the variables. Comparatively, the BAG + KNN and BAG + GR models also performed well but fell short of the BAG + PR model. While they showed respectable\n                    <jats:italic>R<\/jats:italic>\n                    <jats:sup>2<\/jats:sup>\n                    scores, their RMSE values were higher, suggesting larger prediction errors. The AARD% and Maximum Error metrics were also higher for these models, indicating less precise and more variable predictions.\n                  <\/jats:p>","DOI":"10.3389\/fchem.2026.1775080","type":"journal-article","created":{"date-parts":[[2026,3,13]],"date-time":"2026-03-13T06:49:02Z","timestamp":1773384542000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["Application of machine learning models in pharmaceutical engineering for prediction of pharmaceuticals solubility in supercritical solvent: study on phenytoin solubility"],"prefix":"10.3389","volume":"14","author":[{"given":"Shengnan","family":"Yu","sequence":"first","affiliation":[{"name":"School of Medicine, Huanghuai University","place":["Zhumadian, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yang","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Medicine, Huanghuai University","place":["Zhumadian, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Weidong","family":"Qiang","sequence":"additional","affiliation":[{"name":"School of Medicine, Huanghuai University","place":["Zhumadian, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,3,13]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"22876","DOI":"10.1038\/s41598-024-74616-w","article-title":"Intelligence analysis of membrane distillation via machine learning models for pharmaceutical separation","volume":"14","author":"Alkhammash","year":"2024","journal-title":"Sci. Rep."},{"key":"B2","doi-asserted-by":"publisher","first-page":"32411","DOI":"10.1038\/s41598-025-17642-6","article-title":"Raloxifene solubility in supercritical CO2 and correlation of drug solubility via hybrid machine learning and gradient based optimization","volume":"15","author":"Alotaibi","year":"2025","journal-title":"Sci. Rep."},{"key":"B3","doi-asserted-by":"publisher","first-page":"30887","DOI":"10.1038\/s41598-025-16577-2","article-title":"Predictive analysis of solubility data with pressure and temperature in assessing nanomedicine preparation via supercritical carbon dioxide","volume":"15","author":"Alsaab","year":"","journal-title":"Sci. Rep."},{"key":"B4","doi-asserted-by":"publisher","first-page":"34615","DOI":"10.1038\/s41598-025-18223-3","article-title":"Intelligence modeling of solubility of raloxifene and density of solvent for green supercritical processing of medicines for enhanced solubility","volume":"15","author":"Alsaab","year":"","journal-title":"Sci. Rep."},{"key":"B5","doi-asserted-by":"publisher","first-page":"28199","DOI":"10.1038\/s41598-025-13784-9","article-title":"Thermodynamic analysis and intelligent modeling of statin drugs solubility in supercritical carbon dioxide","volume":"15","author":"Amani","year":"2025","journal-title":"Sci. Rep."},{"key":"B6","article-title":"Pattern recognition","volume":"128","author":"Bishop","year":"2006","journal-title":"Mach. Learning"},{"key":"B7","doi-asserted-by":"publisher","first-page":"123","DOI":"10.1007\/bf00058655","article-title":"Bagging predictors","volume":"24","author":"Breiman","year":"1996","journal-title":"Mach. Learning"},{"key":"B8","doi-asserted-by":"publisher","first-page":"861","DOI":"10.1016\/j.asoc.2016.09.010","article-title":"Bagging ensemble models for bank profitability: an emprical research on Turkish development and investment banks","volume":"49","author":"Erdal","year":"2016","journal-title":"Appl. Soft Comput."},{"key":"B9","doi-asserted-by":"crossref","DOI":"10.1109\/CINTI.2014.7028669","article-title":"Bat algorithm: recent advances","volume-title":"2014 IEEE 15th international symposium on computational intelligence and informatics (CINTI)","author":"Fister","year":"2014"},{"key":"B10","doi-asserted-by":"publisher","first-page":"105","DOI":"10.1016\/j.supflu.2017.03.005","article-title":"Amorphization of drugs by adsorptive precipitation from supercritical solutions: a review","volume":"132","author":"Gurikov","year":"2018","journal-title":"J. Supercrit. Fluids"},{"key":"B11","doi-asserted-by":"publisher","first-page":"122511","DOI":"10.1016\/j.molliq.2023.122511","article-title":"Machine learning aided drug development: assessing improvement of drug efficiency by correlation of solubility in supercritical solvent for nanomedicine preparation","volume":"387","author":"Ghazwani","year":"2023","journal-title":"J. Mol. Liq."},{"key":"B12","doi-asserted-by":"publisher","first-page":"122446","DOI":"10.1016\/j.molliq.2023.122446","article-title":"Development of advanced model for understanding the behavior of drug solubility in green solvents: machine learning modeling for small-molecule API solubility prediction","volume":"386","author":"Ghazwani","year":"2023","journal-title":"J. Mol. Liq."},{"key":"B13","doi-asserted-by":"crossref","DOI":"10.1201\/b18401","volume-title":"Statistical learning with sparsity: the lasso and generalizations","author":"Hastie","year":"2015"},{"key":"B14","doi-asserted-by":"publisher","first-page":"3221","DOI":"10.1016\/j.xphs.2021.05.010","article-title":"Microwave-induced in situ drug amorphization using a mixture of polyethylene glycol and polyvinylpyrrolidone","volume":"110","author":"Hempel","year":"2021","journal-title":"J. Pharm. Sci."},{"key":"B15","doi-asserted-by":"crossref","DOI":"10.1007\/978-1-4614-7138-7","volume-title":"An introduction to statistical learning","author":"James","year":"2013"},{"key":"B16","doi-asserted-by":"publisher","first-page":"120650","DOI":"10.1016\/j.molliq.2022.120650","article-title":"Effect of choline chloride based deep eutectic solvents on the aqueous solubility of 4-hydroxycoumarin drug: measurement and correlation","volume":"368","author":"Khorsandi","year":"2022","journal-title":"J. Mol. Liq."},{"key":"B17","doi-asserted-by":"publisher","first-page":"104346","DOI":"10.1016\/j.arabjc.2022.104346","article-title":"Development of machine learning model and analysis study of drug solubility in supercritical solvent for green technology development","volume":"15","author":"Kostyrin","year":"2022","journal-title":"Arabian J. Chem."},{"key":"B18","doi-asserted-by":"crossref","first-page":"13","DOI":"10.1007\/978-3-642-38652-7_2","volume-title":"Dimensionality reduction with unsupervised nearest neighbors","author":"Kramer","year":"2013"},{"key":"B19","doi-asserted-by":"publisher","first-page":"120984","DOI":"10.1016\/j.molliq.2022.120984","article-title":"Theoretical modeling study on preparation of nanosized drugs using supercritical-based processing: determination of solubility of Chlorothiazide in supercritical carbon dioxide","volume":"370","author":"Li","year":"2023","journal-title":"J. Mol. Liq."},{"key":"B20","doi-asserted-by":"publisher","first-page":"104326","DOI":"10.1016\/j.csite.2024.104326","article-title":"Employment of artificial intelligence approach for optimizing the solubility of drug in the supercritical CO2 system","volume":"57","author":"Li","year":"2024","journal-title":"Case Stud. Therm. Eng."},{"key":"B21","doi-asserted-by":"publisher","first-page":"103973","DOI":"10.1016\/j.jddst.2022.103973","article-title":"The effect of mucin on supersaturation of poorly water-soluble drugs with different crystallization behavior and in vitro-in vivo correlation","volume":"78","author":"Liu","year":"","journal-title":"J. Drug Deliv. Sci. Technol."},{"key":"B22","doi-asserted-by":"publisher","first-page":"119208","DOI":"10.1016\/j.molliq.2022.119208","article-title":"Development and validation of machine learning models for prediction of nanomedicine solubility in supercritical solvent for advanced pharmaceutical manufacturing","volume":"358","author":"Liu","year":"","journal-title":"J. Mol. Liq."},{"key":"B23","first-page":"971","volume-title":"Generalized linear models, Vol. 37 of Monographs on Statistics and applied probability London","author":"McCullagh","year":"1989"},{"key":"B24","volume-title":"The discipline of machine learning","author":"Mitchell","year":"2006"},{"key":"B25","doi-asserted-by":"publisher","first-page":"1155","DOI":"10.48550\/arXiv.0711.2349","article-title":"Robust model selection in generalized linear models","author":"M\u00fcller","year":"2009","journal-title":"Stat. Sin."},{"key":"B26","doi-asserted-by":"publisher","first-page":"121246","DOI":"10.1016\/j.molliq.2023.121246","article-title":"Increasing solubility of phenytoin and raloxifene drugs: application of supercritical CO2 technology","volume":"373","author":"Notej","year":"2023","journal-title":"J. Mol. Liq."},{"key":"B27","doi-asserted-by":"publisher","first-page":"114061","DOI":"10.1016\/j.fluid.2024.114061","article-title":"Empirical correlations of drug-and plant-based bioactive compound solubility in supercritical CO2: a comparative evaluation study","volume":"580","author":"Obek","year":"2024","journal-title":"Fluid Phase Equilibria"},{"key":"B28","doi-asserted-by":"publisher","first-page":"500","DOI":"10.1016\/j.proeng.2012.09.545","article-title":"Modelling using polynomial regression","volume":"48","author":"Ostertagov\u00e1","year":"2012","journal-title":"Procedia Eng."},{"key":"B29","doi-asserted-by":"publisher","first-page":"123791","DOI":"10.1016\/j.ijpharm.2024.123791","article-title":"Use of solid thermolytic salts to facilitate microwave-induced in situ amorphization","volume":"651","author":"Qiang","year":"2024","journal-title":"Int. J. Pharm."},{"key":"B30","volume-title":"Newton-raphson versus fisher scoring algorithms in calculating maximum likelihood estimates","author":"Schworer","year":"2004"},{"key":"B31","first-page":"1","article-title":"Bat algorithm for rough set attribute reduction","volume":"51","author":"Taha","year":"2013","journal-title":"J. Theoretical Applied Information Technology"},{"key":"B32","doi-asserted-by":"crossref","DOI":"10.1109\/ICCS45141.2019.9065747","article-title":"A brief review of nearest neighbor algorithm for learning and classification","volume-title":"2019 international conference on intelligent computing and control systems (ICCS)","author":"Taunk","year":"2019"},{"key":"B33","doi-asserted-by":"publisher","first-page":"41761","DOI":"10.1038\/s41598-025-22903-5","article-title":"Machine learning estimating paracetamol solubility in supercritical CO2 by utilization of K-nearest neighbor regression and metaheuristic algorithms","volume":"15","author":"Thajudeen","year":"2025","journal-title":"Sci. Rep."},{"key":"B34","volume-title":"The elements of statistical learning: data mining, inference, and prediction","author":"Trevor","year":"2009"},{"key":"B35","doi-asserted-by":"publisher","first-page":"23193","DOI":"10.1038\/s41598-025-05428-9","article-title":"Intelligence modeling of nanomedicine manufacture by supercritical processing in estimation of solubility of drug in supercritical CO2","volume":"15","author":"Wu","year":"2025","journal-title":"Sci. Rep."},{"key":"B36","doi-asserted-by":"publisher","DOI":"10.1504\/IJBIC.2013.055093","article-title":"Bat algorithm: literature review and applications","volume":"5","author":"Yang","year":"2013","journal-title":"Int. J. Bio-Inspired Computation"},{"key":"B37","doi-asserted-by":"publisher","first-page":"464","DOI":"10.1108\/02644401211235834","article-title":"Bat algorithm: a novel approach for global engineering optimization","volume":"29","author":"Yang","year":"2012","journal-title":"Eng. Computations"},{"key":"B38","doi-asserted-by":"crossref","DOI":"10.1007\/978-1-4939-2818-7","volume-title":"Vector generalized linear and additive models: with an implementation in R","author":"Yee","year":"2015"}],"container-title":["Frontiers in Chemistry"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fchem.2026.1775080\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,13]],"date-time":"2026-03-13T06:49:05Z","timestamp":1773384545000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fchem.2026.1775080\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,13]]},"references-count":38,"alternative-id":["10.3389\/fchem.2026.1775080"],"URL":"https:\/\/doi.org\/10.3389\/fchem.2026.1775080","relation":{},"ISSN":["2296-2646"],"issn-type":[{"value":"2296-2646","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3,13]]},"article-number":"1775080"}}