{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,21]],"date-time":"2026-09-21T18:27:37Z","timestamp":1790015257309,"version":"4.0.1"},"reference-count":48,"publisher":"BMJ","issue":"1","license":[{"start":{"date-parts":[[2025,1,21]],"date-time":"2025-01-21T00:00:00Z","timestamp":1737417600000},"content-version":"unspecified","delay-in-days":20,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"funder":[{"name":"National Heart, Lung, and Blood Institute (NHLBI) of the National Institute of Health","award":["K23HL151671"],"award-info":[{"award-number":["K23HL151671"]}]},{"name":"Mayo Clinic Critical Care Research Committee"}],"content-domain":{"domain":["bmj.com"],"crossmark-restriction":true},"short-container-title":["BMJ Open"],"accepted":{"date-parts":[[2025,1,7]]},"published-print":{"date-parts":[[2025,1]]},"abstract":"<jats:sec>\n                    <jats:title>Introduction<\/jats:title>\n                    <jats:p>Propofol is a widely used sedative-hypnotic agent for critically ill patients requiring invasive mechanical ventilation (IMV). Despite its clinical benefits, propofol is associated with increased risks of hypertriglyceridemia. Early identification of patients at risk for propofol-associated hypertriglyceridemia is crucial for optimising sedation strategies and preventing adverse outcomes. Machine-learning (ML) models offer a promising approach for predicting individualised patient risks of propofol-associated hypertriglyceridemia.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods and analysis<\/jats:title>\n                    <jats:p>We propose the development of an ML model aimed at predicting the risk of propofol-associated hypertriglyceridemia in ICU patients receiving IMV. The study will use retrospective data from four Mayo Clinic sites. Nested cross validation (CV) will be employed, with a tenfold inner CV loop for model tuning and selection as well as an outer loop using leave-one-site-out CV for external validation. Feature selection will be conducted using Boruta and least absolute shrinkage and selection operator-penalised logistic regression. Data preprocessing steps include missing data imputation, feature scaling and dimensionality reduction techniques. Six ML algorithms will be tuned and evaluated. Bayesian optimisation will be used for hyperparameter selection. Global model explainability will be assessed using permutation importance, and local model explainability will be assessed using SHapley Additive exPlanations.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Ethics and dissemination<\/jats:title>\n                    <jats:p>The proposed ML model aims to provide a reliable and interpretable tool for clinicians to predict the risk of propofol-associated hypertriglyceridemia in ICU patients. The final model will be deployed in a web-based clinical risk calculator. The model development process and performance measures obtained during nested CV will be described in a study publication to be disseminated in a peer-reviewed journal. The proposed study has received ethics approval from the Mayo Clinic Institutional Review Board (IRB #23\u20130\u200907\u2009416).<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1136\/bmjopen-2024-092594","type":"journal-article","created":{"date-parts":[[2025,1,22]],"date-time":"2025-01-22T01:21:27Z","timestamp":1737508887000},"page":"e092594","update-policy":"https:\/\/doi.org\/10.1136\/crossmarkpolicy","source":"Crossref","is-referenced-by-count":11,"title":["Development and validation of machine-learning models for predicting the risk of hypertriglyceridemia in critically ill patients receiving propofol sedation using retrospective data: a protocol"],"prefix":"10.1136","volume":"15","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8274-6468","authenticated-orcid":false,"given":"Jiawen","family":"Deng","sequence":"first","affiliation":[{"name":"Temerty Faculty of Medicine, University of Toronto, Toronto, Ontario, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kiyan","family":"Heybati","sequence":"additional","affiliation":[{"name":"Alix School of Medicine, Mayo Clinic, Rochester, Minnesota, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1889-2524","authenticated-orcid":false,"given":"Hemang","family":"Yadav","sequence":"additional","affiliation":[{"name":"Division of Pulmonary and Critical Care, Mayo Clinic, Rochester, Minnesota, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"239","published-online":{"date-parts":[[2025,1,21]]},"reference":[{"key":"2025121600020225000_15.1.e092594.1","doi-asserted-by":"publisher","DOI":"10.1007\/s40262-018-0672-3"},{"key":"2025121600020225000_15.1.e092594.2","doi-asserted-by":"publisher","DOI":"10.1097\/CCM.0000000000003299"},{"key":"2025121600020225000_15.1.e092594.3","doi-asserted-by":"publisher","DOI":"10.1111\/j.1527-3458.2008.00043.x"},{"key":"2025121600020225000_15.1.e092594.4","doi-asserted-by":"publisher","DOI":"10.1592\/phco.2005.25.10.1348"},{"key":"2025121600020225000_15.1.e092594.5","doi-asserted-by":"publisher","DOI":"10.1513\/AnnalsATS.202205-403OC"},{"key":"2025121600020225000_15.1.e092594.6","doi-asserted-by":"publisher","DOI":"10.1007\/s00134-012-2688-8"},{"key":"2025121600020225000_15.1.e092594.7","doi-asserted-by":"publisher","DOI":"10.1097\/MJT.0000000000000461"},{"key":"2025121600020225000_15.1.e092594.8","doi-asserted-by":"publisher","DOI":"10.1001\/jama.2023.25057"},{"key":"2025121600020225000_15.1.e092594.9","doi-asserted-by":"publisher","DOI":"10.3949\/ccjm.91a.23070"},{"key":"2025121600020225000_15.1.e092594.10","doi-asserted-by":"crossref","DOI":"10.1098\/rsif.2017.0387","article-title":"Opportunities and obstacles for deep learning in biology and medicine","volume":"15","author":"Ching","year":"2018","journal-title":"J R Soc Interface"},{"key":"2025121600020225000_15.1.e092594.11","doi-asserted-by":"crossref","DOI":"10.1136\/bmj-2023-078378","article-title":"TRIPOD+AI statement: updated guidance for reporting clinical prediction models that use regression or machine learning methods","volume":"385","author":"Collins","year":"2024","journal-title":"BMJ"},{"key":"2025121600020225000_15.1.e092594.12","doi-asserted-by":"crossref","DOI":"10.2196\/49023","article-title":"Practical Considerations and Applied Examples of Cross-Validation for Model Development and Evaluation in Health Care: Tutorial","volume":"2","author":"Wilimitis","year":"2023","journal-title":"JMIR AI"},{"key":"2025121600020225000_15.1.e092594.13","doi-asserted-by":"crossref","first-page":"115222","DOI":"10.1016\/j.eswa.2021.115222","article-title":"Nested cross-validation when selecting classifiers is overzealous for most practical applications","volume":"182","author":"Wainer","year":"2021","journal-title":"Expert Syst Appl"},{"key":"2025121600020225000_15.1.e092594.14","doi-asserted-by":"crossref","DOI":"10.1148\/ryai.220232","article-title":"A Guide to Cross-Validation for Artificial Intelligence in Medical Imaging","volume":"5","author":"Bradshaw","year":"2023","journal-title":"Radiol Artif Intell"},{"key":"2025121600020225000_15.1.e092594.15","doi-asserted-by":"crossref","unstructured":"Kursa MB , Rudnicki WR . Feature Selection with theBorutaPackage. J Stat Softw 2010. doi:10.18637\/jss.v036.i11","DOI":"10.18637\/jss.v036.i11"},{"key":"2025121600020225000_15.1.e092594.16","doi-asserted-by":"crossref","unstructured":"Muthukrishnan R , Rohini R . LASSO: a feature selection technique in predictive modeling for machine learning. 2016 IEEE International Conference on Advances in Computer Applications (ICACA); Coimbatore, India, 2016 doi:10.1109\/ICACA.2016.7887916","DOI":"10.1109\/ICACA.2016.7887916"},{"key":"2025121600020225000_15.1.e092594.17","doi-asserted-by":"publisher","DOI":"10.1002\/sim.4780030207"},{"key":"2025121600020225000_15.1.e092594.18","doi-asserted-by":"publisher","DOI":"10.1002\/(SICI)1097-0258(19960229)15:4<361::AID-SIM168>3.0.CO;2-4"},{"key":"2025121600020225000_15.1.e092594.19","doi-asserted-by":"crossref","unstructured":"Heybati K , Deng J , Xie G , et al . Propofol, Triglycerides, and Acute Pancreatitis: A Multi-Center Epidemiologic Analysis. Ann Am Thorac Soc 2024. doi:10.1513\/AnnalsATS.202407-781OC","DOI":"10.1513\/AnnalsATS.202407-781OC"},{"key":"2025121600020225000_15.1.e092594.20","doi-asserted-by":"crossref","unstructured":"Ashenden SK , Bartosik A , Agapow P-M , et al . Chapter 2 - introduction to artificial intelligence and machine learning. In: Ashenden SK , ed. The Era of Artificial Intelligence, Machine Learning, and Data Science in the Pharmaceutical Industry. Cambridge, MA, USA: Academic Press, 2021: 15\u201326.","DOI":"10.1016\/B978-0-12-820045-2.00003-9"},{"key":"2025121600020225000_15.1.e092594.21","doi-asserted-by":"crossref","unstructured":"Buuren S mice G-OK . Multivariate Imputation by Chained Equations inR. J Stat Softw 2011. doi:10.18637\/jss.v045.i03","DOI":"10.18637\/jss.v045.i03"},{"key":"2025121600020225000_15.1.e092594.22","doi-asserted-by":"crossref","first-page":"651","DOI":"10.1080\/10705510802339072","article-title":"What Improves with Increased Missing Data Imputations?","volume":"15","author":"Bodner","year":"2008","journal-title":"Structural Equation Modeling: A Multidisciplinary Journal"},{"key":"2025121600020225000_15.1.e092594.23","doi-asserted-by":"publisher","DOI":"10.1002\/sim.4067"},{"key":"2025121600020225000_15.1.e092594.24","doi-asserted-by":"crossref","unstructured":"Apicella A , Isgr\u00f2 F , Prevete R . Don\u2019t push the button! exploring data leakage risks in machine learning and transfer learning. SSRN [Preprint] 2024. doi:10.2139\/ssrn.4733889","DOI":"10.2139\/ssrn.4733889"},{"key":"2025121600020225000_15.1.e092594.25","doi-asserted-by":"publisher","DOI":"10.1093\/biomet\/52.3-4.591"},{"key":"2025121600020225000_15.1.e092594.26","doi-asserted-by":"publisher","DOI":"10.5812\/ijem.3505"},{"key":"2025121600020225000_15.1.e092594.27","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2022.109924"},{"key":"2025121600020225000_15.1.e092594.28","doi-asserted-by":"crossref","unstructured":"Cabello-Solorzano K , Araujo I , Pe\u00f1a M , et al . The impact of data normalization on the accuracy of machine learning algorithms: a comparative analysis. In: Lecture Notes in Networks and Systems. Cham: Springer Nature Switzerland, 2023: 344\u201353.","DOI":"10.1007\/978-3-031-42536-3_33"},{"key":"2025121600020225000_15.1.e092594.29","doi-asserted-by":"crossref","unstructured":"James G , Witten D , Hastie T , et al . An Introduction to Statistical Learning: With Applications in R. New York, NY: Springer Science & Business Media, 2013.","DOI":"10.1007\/978-1-4614-7138-7"},{"key":"2025121600020225000_15.1.e092594.30","article-title":"Principal component analysis: a review and recent developments","volume":"374","author":"Jolliffe","year":"2016","journal-title":"Philos Trans A Math Phys Eng Sci"},{"key":"2025121600020225000_15.1.e092594.31","unstructured":"Ke G , Meng Q , Finley T , et al . LightGBM: a highly efficient gradient boosting decision tree. In: Luxburg U , Guyon I , Bengio S , eds. NIPS\u201917: Proceedings of the 31st International Conference on Neural Information Processing Systems; Red Hook, NY, USA: Curran Associates Inc, 3149\u201357."},{"key":"2025121600020225000_15.1.e092594.32","doi-asserted-by":"publisher","DOI":"10.1214\/aos\/1013203450"},{"key":"2025121600020225000_15.1.e092594.33","unstructured":"Rashmi KV , Gilad-Bachrach R . DART: dropouts meet multiple additive regression trees. arXiv 2015. doi:10.48550\/arXiv.1505.01866"},{"key":"2025121600020225000_15.1.e092594.34","doi-asserted-by":"crossref","unstructured":"Chen T , Guestrin C . XGBoost: a scalable tree boosting system. Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining; 2016 doi:10.1145\/2939672.2939785","DOI":"10.1145\/2939672.2939785"},{"key":"2025121600020225000_15.1.e092594.35","doi-asserted-by":"crossref","unstructured":"He K , Zhang X , Ren S , et al . Delving deep into rectifiers: surpassing human-level performance on imagenet classification. 2015 IEEE International Conference on Computer Vision (ICCV); Santiago, Chile. doi:10.1109\/ICCV.2015.123","DOI":"10.1109\/ICCV.2015.123"},{"key":"2025121600020225000_15.1.e092594.36","doi-asserted-by":"publisher","DOI":"10.1214\/12-AOS1000. 1102.4807"},{"key":"2025121600020225000_15.1.e092594.37","unstructured":"Ioffe S , Szegedy C . Batch Normalization: Accelerating deep network training by reducing internal covariate shift. Arxiv 2015. doi:10.48550\/ARXIV.1502.03167"},{"key":"2025121600020225000_15.1.e092594.38","unstructured":"Loshchilov I , Hutter F . Decoupled weight decay regularization. arXiv 2017. doi:10.48550\/arXiv.1711.05101"},{"key":"2025121600020225000_15.1.e092594.39","doi-asserted-by":"publisher","DOI":"10.1023\/A:1008306431147"},{"key":"2025121600020225000_15.1.e092594.40","unstructured":"Snoek J , Larochelle H , Adams RP . Practical Bayesian optimization of machine learning algorithms. Arxiv 2012. doi:10.48550\/ARXIV.1206.2944"},{"key":"2025121600020225000_15.1.e092594.41","unstructured":"Turner R , Eriksson D , McCourt M , et al . Bayesian optimization is superior to random search for machine learning hyperparameter tuning: analysis of the black-box optimization challenge 2020. arXiv 2021. doi:10.48550\/arXiv.2104.10201"},{"key":"2025121600020225000_15.1.e092594.42","doi-asserted-by":"crossref","unstructured":"Niculescu-Mizil A , Caruana R . Predicting good probabilities with supervised learning. 22nd international conference; Bonn, Germany, 2005 doi:10.1145\/1102351.1102430 Available: http:\/\/portal.acm.org\/citation.cfm?doid=1102351","DOI":"10.1145\/1102351.1102430"},{"key":"2025121600020225000_15.1.e092594.43","first-page":"61","volume-title":"Advances in large margin classifiers","volume":"10","author":"Platt","year":"1999"},{"key":"2025121600020225000_15.1.e092594.44","doi-asserted-by":"publisher","DOI":"10.1002\/1097-0142(1950)3:1<32::AID-CNCR2820030106>3.0.CO;2-3"},{"key":"2025121600020225000_15.1.e092594.45","doi-asserted-by":"publisher","DOI":"10.1097\/EDE.0b013e3181c30fb2"},{"key":"2025121600020225000_15.1.e092594.46","doi-asserted-by":"publisher","DOI":"10.1023\/A:1010933404324"},{"key":"2025121600020225000_15.1.e092594.47","unstructured":"Lundberg S , Lee S-I . A unified approach to interpreting model predictions. arXiv 2017. doi:10.48550\/arXiv.1705.07874"},{"key":"2025121600020225000_15.1.e092594.48","doi-asserted-by":"crossref","unstructured":"Fang ML , Dhami DS , Kersting K . DP-ctgan: differentially private medical data generation using ctgans. In: Artificial Intelligence in Medicine. Cham: Springer International Publishing 2022:178\u201388,","DOI":"10.1007\/978-3-031-09342-5_17"}],"container-title":["BMJ Open"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/syndication.highwire.org\/content\/doi\/10.1136\/bmjopen-2024-092594","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,16]],"date-time":"2025-12-16T08:02:09Z","timestamp":1765872129000},"score":1,"resource":{"primary":{"URL":"https:\/\/bmjopen.bmj.com\/lookup\/doi\/10.1136\/bmjopen-2024-092594"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,1]]},"references-count":48,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2025,1,21]]},"published-print":{"date-parts":[[2025,1]]}},"alternative-id":["10.1136\/bmjopen-2024-092594"],"URL":"https:\/\/doi.org\/10.1136\/bmjopen-2024-092594","relation":{"has-preprint":[{"id-type":"doi","id":"10.1101\/2024.08.17.24312159","asserted-by":"object"}]},"ISSN":["2044-6055","2044-6055"],"issn-type":[{"value":"2044-6055","type":"print"},{"value":"2044-6055","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,1]]}}}