{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,13]],"date-time":"2026-10-13T16:21:03Z","timestamp":1791908463306,"version":"4.3.4"},"reference-count":133,"publisher":"Cambridge University Press (CUP)","issue":"2","license":[{"start":{"date-parts":[[2024,12,6]],"date-time":"2024-12-06T00:00:00Z","timestamp":1733443200000},"content-version":"unspecified","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["cambridge.org"],"crossmark-restriction":true},"short-container-title":["Proc. Nutr. Soc."],"published-print":{"date-parts":[[2026,5]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Machine learning is increasingly being utilised across various domains of nutrition research due to its ability to analyse complex data, especially as large datasets become more readily available. However, at times, this enthusiasm has led to the adoption of machine learning techniques prior to a proper understanding of how they should be applied, leading to non-robust study designs and results of questionable validity. To ensure that research standards do not suffer, key machine learning concepts must be understood by the research community. The aim of this review is to facilitate a better understanding of machine learning in research by outlining good practices and common pitfalls in each of the steps in the machine learning process. Key themes include the importance of generating high-quality data, employing robust validation techniques, quantifying the stability of results, accurately interpreting machine learning outputs, adequately describing methodologies, and ensuring transparency when reporting findings. Achieving this aim will facilitate the implementation of robust machine learning methodologies, which will reduce false findings and make research more reliable, as well as enable researchers to critically evaluate and better interpret the findings of others using machine learning in their work.<\/jats:p>","DOI":"10.1017\/s0029665124007638","type":"journal-article","created":{"date-parts":[[2024,12,6]],"date-time":"2024-12-06T05:32:51Z","timestamp":1733463171000},"page":"253-266","update-policy":"https:\/\/doi.org\/10.1017\/policypage","source":"Crossref","is-referenced-by-count":11,"title":["Good practices and common pitfalls of machine learning in nutrition research"],"prefix":"10.1017","volume":"85","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7738-7686","authenticated-orcid":false,"given":"Daniel","family":"Kirk","sequence":"first","affiliation":[{"name":"King\u2019s College London"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"56","published-online":{"date-parts":[[2024,12,6]]},"reference":[{"key":"S0029665124007638_ref101","doi-asserted-by":"publisher","DOI":"10.1145\/1102351.1102430"},{"key":"S0029665124007638_ref79","first-page":"101","article-title":"A selective overview of variable selection in high dimensional feature space","volume":"20","author":"Fan","year":"2010","journal-title":"Stat Sin"},{"key":"S0029665124007638_ref16","doi-asserted-by":"publisher","DOI":"10.1007\/s42979-021-00592-x"},{"key":"S0029665124007638_ref55","doi-asserted-by":"publisher","DOI":"10.1016\/j.dajour.2023.100164"},{"key":"S0029665124007638_ref100","unstructured":"100. Kull, M , De Menezes, T , Filho, S & Flach, P (2017) Beta calibration: a well-founded and easily implemented improvement on logistic calibration for binary classifiers. In Proceedings of the 20th International Conference on Artificial Intelligence and Statistics (PMLR), pp. 623\u2013631."},{"key":"S0029665124007638_ref5","doi-asserted-by":"publisher","DOI":"10.1080\/10408398.2021.1956425"},{"key":"S0029665124007638_ref95","first-page":"2079","article-title":"On over-fitting in model selection and subsequent selection bias in performance evaluation","volume":"11","author":"Cawley","year":"2010","journal-title":"J Mach Learn Res"},{"key":"S0029665124007638_ref114","doi-asserted-by":"publisher","DOI":"10.1145\/2939672.2939778\/SUPPL_FILE\/KDD2016_RIBEIRO_ANY_CLASSIFIER_01-ACM.MP4"},{"key":"S0029665124007638_ref76","doi-asserted-by":"publisher","DOI":"10.1016\/j.compeleceng.2013.11.024"},{"key":"S0029665124007638_ref116","doi-asserted-by":"publisher","DOI":"10.1186\/1471-2105-8-25"},{"key":"S0029665124007638_ref23","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2015.07.013"},{"key":"S0029665124007638_ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICAIS53314.2022.9742919"},{"key":"S0029665124007638_ref125","doi-asserted-by":"publisher","DOI":"10.1007\/s44230-023-00038-y"},{"key":"S0029665124007638_ref98","unstructured":"98. Doshi-Velez, F & Kim, B (2017) Towards A Rigorous Science of Interpretable Machine Learning."},{"key":"S0029665124007638_ref67","doi-asserted-by":"publisher","DOI":"10.1080\/08839514.2022.2042924"},{"key":"S0029665124007638_ref122","doi-asserted-by":"publisher","DOI":"10.1007\/s10115-006-0040-8"},{"key":"S0029665124007638_ref50","first-page":"9","article-title":"Missing data imputation: focusing on single imputation","volume":"4","author":"Zhang","year":"2016","journal-title":"Ann Transl Med"},{"key":"S0029665124007638_ref111","doi-asserted-by":"publisher","DOI":"10.3390\/e23010018"},{"key":"S0029665124007638_ref27","doi-asserted-by":"publisher","DOI":"10.1002\/ehf2.13073"},{"key":"S0029665124007638_ref123","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-019-0048-x"},{"key":"S0029665124007638_ref12","doi-asserted-by":"publisher","DOI":"10.1038\/nmeth.4642"},{"key":"S0029665124007638_ref107","doi-asserted-by":"publisher","DOI":"10.1016\/j.jclinepi.2014.09.007"},{"key":"S0029665124007638_ref7","doi-asserted-by":"publisher","DOI":"10.1186\/s12966-021-01224-6"},{"key":"S0029665124007638_ref94","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2021.115222"},{"key":"S0029665124007638_ref81","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btm344"},{"key":"S0029665124007638_ref37","doi-asserted-by":"publisher","DOI":"10.4103\/0019-5154.174011"},{"key":"S0029665124007638_ref127","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pmed.1001747"},{"key":"S0029665124007638_ref128","doi-asserted-by":"publisher","DOI":"10.1038\/533452a"},{"key":"S0029665124007638_ref102","first-page":"61","article-title":"Probabilistic outputs for support vector machines and comparisons to regularized likelihood methods","volume":"10","author":"Platt","year":"1999","journal-title":"Adv Large Margin Classif"},{"key":"S0029665124007638_ref24","doi-asserted-by":"publisher","DOI":"10.1155\/2023\/5548684"},{"key":"S0029665124007638_ref131","doi-asserted-by":"publisher","DOI":"10.1001\/jama.2019.20866"},{"key":"S0029665124007638_ref129","doi-asserted-by":"publisher","DOI":"10.1161\/CIRCRESAHA.114.303819"},{"key":"S0029665124007638_ref117","doi-asserted-by":"publisher","DOI":"10.1186\/1471-2105-9-307"},{"key":"S0029665124007638_ref48","doi-asserted-by":"publisher","DOI":"10.1111\/j.1467-842X.2001.tb00294.x"},{"key":"S0029665124007638_ref49","doi-asserted-by":"publisher","DOI":"10.1136\/bmj.b2393"},{"key":"S0029665124007638_ref75","doi-asserted-by":"publisher","DOI":"10.1002\/widm.1484"},{"key":"S0029665124007638_ref34","doi-asserted-by":"publisher","DOI":"10.1214\/ss\/1009213726"},{"key":"S0029665124007638_ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.advnut.2024.100264"},{"key":"S0029665124007638_ref120","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1900654116"},{"key":"S0029665124007638_ref72","doi-asserted-by":"publisher","DOI":"10.1145\/2939672.2939785"},{"key":"S0029665124007638_ref92","volume-title":"Python Machine Learning: Machine Learning and Deep Learning with Python, Scikit-learn, and Tensorflow 2","author":"Raschka","year":"2019"},{"key":"S0029665124007638_ref26","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-022-27264-x"},{"key":"S0029665124007638_ref9","doi-asserted-by":"publisher","DOI":"10.1002\/cpt.1796"},{"key":"S0029665124007638_ref132","doi-asserted-by":"publisher","DOI":"10.1038\/s41592-021-01256-7"},{"key":"S0029665124007638_ref56","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4614-6849-3"},{"key":"S0029665124007638_ref63","doi-asserted-by":"publisher","DOI":"10.1186\/1471-2288-12-21"},{"key":"S0029665124007638_ref13","doi-asserted-by":"publisher","DOI":"10.1038\/nrg3920"},{"key":"S0029665124007638_ref87","doi-asserted-by":"publisher","DOI":"10.1186\/s12920-020-00826-6"},{"key":"S0029665124007638_ref90","doi-asserted-by":"publisher","DOI":"10.7717\/peerj-cs.623"},{"key":"S0029665124007638_ref39","doi-asserted-by":"publisher","DOI":"10.1097\/PRS.0b013e3181f44abc"},{"key":"S0029665124007638_ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2021.104365"},{"key":"S0029665124007638_ref47","doi-asserted-by":"publisher","DOI":"10.1111\/rssb.12537"},{"key":"S0029665124007638_ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3317287.3328534"},{"key":"S0029665124007638_ref112","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-04083-2_4"},{"key":"S0029665124007638_ref126","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pmed.0020124"},{"key":"S0029665124007638_ref42","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pcbi.1006907"},{"key":"S0029665124007638_ref89","doi-asserted-by":"publisher","DOI":"10.1007\/s44150-021-00015-8"},{"key":"S0029665124007638_ref108","doi-asserted-by":"publisher","DOI":"10.1186\/s40168-020-00811-2"},{"key":"S0029665124007638_ref86","first-page":"126","article-title":"Comparison of regularized regression methods for \u223comics data","volume":"3","author":"Acharjee","year":"2013","journal-title":"Metabolomics"},{"key":"S0029665124007638_ref104","doi-asserted-by":"publisher","DOI":"10.1038\/s41746-021-00549-7"},{"key":"S0029665124007638_ref38","doi-asserted-by":"publisher","DOI":"10.1016\/j.chest.2020.03.014"},{"key":"S0029665124007638_ref99","doi-asserted-by":"publisher","DOI":"10.1111\/geb.13070"},{"key":"S0029665124007638_ref53","doi-asserted-by":"publisher","DOI":"10.1186\/s40537-021-00516-9"},{"key":"S0029665124007638_ref66","doi-asserted-by":"publisher","DOI":"10.1186\/1471-2288-10-59"},{"key":"S0029665124007638_ref40","article-title":"The effects of data quality on machine learning performance","author":"Budach","year":"2022","journal-title":"ArXiv"},{"key":"S0029665124007638_ref109","doi-asserted-by":"publisher","DOI":"10.1186\/s12916-023-02779-w"},{"key":"S0029665124007638_ref93","unstructured":"93. Smith, JW , Everhart, JE , Dickson, WC , Knowler, WC & Johannes, RS (1988) Using the ADAP learning algorithm to forecast the onset of diabetes mellitus. Proceedings of the Annual Symposium on Computer Application in Medical Care, 261."},{"key":"S0029665124007638_ref97","doi-asserted-by":"publisher","DOI":"10.1186\/s12916-019-1466-7"},{"key":"S0029665124007638_ref4","doi-asserted-by":"publisher","DOI":"10.1111\/obr.12667"},{"key":"S0029665124007638_ref51","doi-asserted-by":"publisher","DOI":"10.1016\/j.jclinepi.2006.01.014"},{"key":"S0029665124007638_ref41","doi-asserted-by":"publisher","DOI":"10.1007\/s40520-023-02552-2"},{"key":"S0029665124007638_ref80","article-title":"Feature selection","volume":"50","author":"Li","year":"2017","journal-title":"ACM Comput Surveys (CSUR)"},{"key":"S0029665124007638_ref17","doi-asserted-by":"publisher","DOI":"10.3390\/nu16071073"},{"key":"S0029665124007638_ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-19425-7"},{"key":"S0029665124007638_ref78","doi-asserted-by":"publisher","DOI":"10.3389\/fbinf.2022.927312"},{"key":"S0029665124007638_ref130","doi-asserted-by":"publisher","DOI":"10.1126\/scitranslmed.abb1655"},{"key":"S0029665124007638_ref133","doi-asserted-by":"publisher","DOI":"10.1098\/rsos.220346"},{"key":"S0029665124007638_ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-0-387-84858-7"},{"key":"S0029665124007638_ref113","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1705.07874"},{"key":"S0029665124007638_ref54","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2018.06.012"},{"key":"S0029665124007638_ref74","first-page":"281","article-title":"Random search for hyper-parameter optimization Yoshua Bengio","volume":"13","author":"Bergstra","year":"2012","journal-title":"J Mach Learn Res"},{"key":"S0029665124007638_ref110","doi-asserted-by":"publisher","DOI":"10.1016\/j.jclinepi.2024.111387"},{"key":"S0029665124007638_ref30","article-title":"Comparisons of the prediction models for undiagnosed diabetes between machine learning versus traditional statistical methods","volume":"13","author":"Choi","year":"2023","journal-title":"Sci Rep"},{"key":"S0029665124007638_ref77","doi-asserted-by":"publisher","DOI":"10.1007\/s10115-023-02010-5"},{"key":"S0029665124007638_ref33","doi-asserted-by":"publisher","DOI":"10.3389\/fnins.2017.00543"},{"key":"S0029665124007638_ref31","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijmedinf.2023.105228"},{"key":"S0029665124007638_ref64","doi-asserted-by":"publisher","DOI":"10.1002\/sim.2331"},{"key":"S0029665124007638_ref121","doi-asserted-by":"publisher","DOI":"10.1186\/s12859-016-0900-5"},{"key":"S0029665124007638_ref11","article-title":"Machine learning and artificial intelligence research for patient benefit: 20 critical questions on transparency, replicability, ethics, and effectiveness","volume":"368","author":"Vollmer","year":"2020","journal-title":"BMJ"},{"key":"S0029665124007638_ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-39601-9_4"},{"key":"S0029665124007638_ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2023.3259425"},{"key":"S0029665124007638_ref115","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btq134"},{"key":"S0029665124007638_ref28","doi-asserted-by":"publisher","DOI":"10.1016\/j.imu.2022.101103"},{"key":"S0029665124007638_ref44","article-title":"A survey of dimensionality reduction techniques","author":"Sorzano","year":"2014","journal-title":"ArXiv"},{"key":"S0029665124007638_ref73","doi-asserted-by":"publisher","DOI":"10.1007\/s11704-019-8208-z"},{"key":"S0029665124007638_ref35","doi-asserted-by":"publisher","DOI":"10.1111\/j.2517-6161.1996.tb02080.x"},{"key":"S0029665124007638_ref29","doi-asserted-by":"publisher","DOI":"10.1017\/S0007114518001150"},{"key":"S0029665124007638_ref83","doi-asserted-by":"publisher","DOI":"10.1201\/9780367816377"},{"key":"S0029665124007638_ref71","doi-asserted-by":"publisher","DOI":"10.1023\/A:1010933404324"},{"key":"S0029665124007638_ref85","doi-asserted-by":"crossref","unstructured":"85. Lones, MA (2024) How to avoid machine learning pitfalls: a guide for academic researchers.10.1016\/j.patter.2024.101046","DOI":"10.1016\/j.patter.2024.101046"},{"key":"S0029665124007638_ref58","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2019.105524"},{"key":"S0029665124007638_ref70","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3207287"},{"key":"S0029665124007638_ref62","doi-asserted-by":"publisher","DOI":"10.1002\/9781118445112.stat04857"},{"key":"S0029665124007638_ref105","doi-asserted-by":"publisher","DOI":"10.1016\/j.cmpb.2021.106288"},{"key":"S0029665124007638_ref124","doi-asserted-by":"publisher","DOI":"10.1016\/j.giq.2021.101666"},{"key":"S0029665124007638_ref106","doi-asserted-by":"publisher","DOI":"10.1093\/ckj\/sfaa188"},{"key":"S0029665124007638_ref96","doi-asserted-by":"publisher","DOI":"10.1016\/j.jclinepi.2015.04.005"},{"key":"S0029665124007638_ref20","doi-asserted-by":"publisher","DOI":"10.1126\/science.aaa8415"},{"key":"S0029665124007638_ref15","volume-title":"Introducing To Linear Regression Analysis","author":"Montgomery","year":"2021"},{"key":"S0029665124007638_ref119","doi-asserted-by":"publisher","DOI":"10.1007\/s42452-021-04148-9"},{"key":"S0029665124007638_ref45","doi-asserted-by":"publisher","DOI":"10.38094\/jastt1224"},{"key":"S0029665124007638_ref84","doi-asserted-by":"publisher","DOI":"10.1038\/s41576-021-00434-9"},{"key":"S0029665124007638_ref65","unstructured":"65. Sauerbrei, W & Royston, P (2010) Continuous variables: to categorize or to model? In Proceedings of the Eighth International Conference on Teaching Statistics."},{"key":"S0029665124007638_ref25","doi-asserted-by":"publisher","DOI":"10.1093\/advances\/nmz121"},{"key":"S0029665124007638_ref1","doi-asserted-by":"publisher","DOI":"10.1093\/advances\/nmac103"},{"key":"S0029665124007638_ref59","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-42536-3_33"},{"key":"S0029665124007638_ref61","doi-asserted-by":"publisher","DOI":"10.3174\/ajnr.A2425"},{"key":"S0029665124007638_ref32","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0221911"},{"key":"S0029665124007638_ref69","first-page":"1","article-title":"Evaluation metrics and statistical tests for machine learning","volume":"14","author":"Rainio","year":"2024","journal-title":"Sci Rep"},{"key":"S0029665124007638_ref88","first-page":"743138","article-title":"Beyond accuracy: Measures for assessing machine learning models, pitfalls and guidelines","author":"Dinga","year":"2019","journal-title":"bioRxiv"},{"key":"S0029665124007638_ref82","doi-asserted-by":"publisher","DOI":"10.1016\/j.jksuci.2019.06.012"},{"key":"S0029665124007638_ref68","doi-asserted-by":"publisher","DOI":"10.1002\/widm.1301"},{"key":"S0029665124007638_ref118","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btr300"},{"key":"S0029665124007638_ref36","doi-asserted-by":"publisher","DOI":"10.1007\/s00500-020-05297-6"},{"key":"S0029665124007638_ref18","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2024.124313"},{"key":"S0029665124007638_ref21","doi-asserted-by":"publisher","DOI":"10.3390\/nu14224847"},{"key":"S0029665124007638_ref52","doi-asserted-by":"publisher","DOI":"10.1016\/j.artmed.2010.05.002"},{"key":"S0029665124007638_ref60","doi-asserted-by":"publisher","DOI":"10.1186\/1471-2164-7-142"},{"key":"S0029665124007638_ref91","unstructured":"91. Palacio-Ni\u00f1o, J-O & Berzal, F (2019) Evaluation metrics for unsupervised learning algorithms."},{"key":"S0029665124007638_ref8","doi-asserted-by":"publisher","DOI":"10.1038\/s41591-021-01614-0"},{"key":"S0029665124007638_ref46","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2014.12.003"},{"key":"S0029665124007638_ref103","doi-asserted-by":"publisher","DOI":"10.1016\/j.patter.2020.100129"},{"key":"S0029665124007638_ref57","doi-asserted-by":"publisher","DOI":"10.4249\/scholarpedia.1883"}],"container-title":["Proceedings of the Nutrition Society"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.cambridge.org\/core\/services\/aop-cambridge-core\/content\/view\/S0029665124007638","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,13]],"date-time":"2026-04-13T02:56:13Z","timestamp":1776048973000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.cambridge.org\/core\/product\/identifier\/S0029665124007638\/type\/journal_article"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,6]]},"references-count":133,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2026,5]]}},"alternative-id":["S0029665124007638"],"URL":"https:\/\/doi.org\/10.1017\/s0029665124007638","relation":{},"ISSN":["0029-6651","1475-2719"],"issn-type":[{"value":"0029-6651","type":"print"},{"value":"1475-2719","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,12,6]]},"assertion":[{"value":"\u00a9 The Author(s), 2024. Published by Cambridge University Press on behalf of The Nutrition Society","name":"copyright","label":"Copyright","group":{"name":"copyright_and_licensing","label":"Copyright and Licensing"}},{"value":"This is an Open Access article, distributed under the terms of the Creative Commons Attribution licence (https:\/\/creativecommons.org\/licenses\/by\/4.0\/), which permits unrestricted re-use, distribution and reproduction, provided the original article is properly cited.","name":"license","label":"License","group":{"name":"copyright_and_licensing","label":"Copyright and Licensing"}},{"value":"This content has been made available to all.","name":"free","label":"Free to read"}]}}