{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,25]],"date-time":"2026-09-25T21:06:23Z","timestamp":1790370383864,"version":"4.1.0"},"reference-count":50,"publisher":"Oxford University Press (OUP)","issue":"8","license":[{"start":{"date-parts":[[2023,4,26]],"date-time":"2023-04-26T00:00:00Z","timestamp":1682467200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/academic.oup.com\/pages\/standard-publication-reuse-rights"}],"funder":[{"DOI":"10.13039\/100000054","name":"National Cancer Institute","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000054","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]},{"name":"FDA Center for Tobacco Products","award":["U54CA229974"],"award-info":[{"award-number":["U54CA229974"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,7,14]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Introduction<\/jats:title>\n                    <jats:p>Cigarette smoking continues to pose a threat to public health. Identifying individual risk factors for smoking initiation is essential to further mitigate this epidemic. To the best of our knowledge, no study today has used machine learning (ML) techniques to automatically uncover informative predictors of smoking onset among adults using the Population Assessment of Tobacco and Health (PATH) study.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Aims and Methods<\/jats:title>\n                    <jats:p>In this work, we employed random forest paired with Recursive Feature Elimination to identify relevant PATH variables that predict smoking initiation among adults who have never smoked at baseline between two consecutive PATH waves. We included all potentially informative baseline variables in wave 1 (wave 4) to predict past 30-day smoking status in wave 2 (wave 5). Using the first and most recent pairs of PATH waves was found sufficient to identify the key risk factors of smoking initiation and test their robustness over time. The eXtreme Gradient Boosting method was employed to test the quality of these selected variables.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>As a result, classification models suggested about 60 informative PATH variables among many candidate variables in each baseline wave. With these selected predictors, the resulting models have a high discriminatory power with the area under the specificity-sensitivity curves of around 80%. We examined the chosen variables and discovered important features. Across the considered waves, two factors, (1) BMI, and (2) dental and oral health status, robustly appeared as important predictors of smoking initiation, besides other well-established predictors.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>Our work demonstrates that ML methods are useful to predict smoking initiation with high accuracy, identifying novel smoking initiation predictors, and to enhance our understanding of tobacco use behaviors.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Implications<\/jats:title>\n                    <jats:p>Understanding individual risk factors for smoking initiation is essential to prevent smoking initiation. With this methodology, a set of the most informative predictors of smoking onset in the PATH data were identified. Besides reconfirming well-known risk factors, the findings suggested additional predictors of smoking initiation that have been overlooked in previous work. More studies that focus on the newly discovered factors (BMI and dental and oral health status,) are needed to confirm their predictive power against the onset of smoking as well as determine the underlying mechanisms.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1093\/ntr\/ntad066","type":"journal-article","created":{"date-parts":[[2023,4,26]],"date-time":"2023-04-26T16:19:03Z","timestamp":1682525943000},"page":"1481-1488","source":"Crossref","is-referenced-by-count":7,"title":["Are the Relevant Risk Factors Being Adequately Captured in Empirical Studies of Smoking Initiation? A Machine Learning Analysis Based on the Population Assessment of Tobacco and Health Study"],"prefix":"10.1093","volume":"25","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3106-4045","authenticated-orcid":false,"given":"Thuy T T","family":"Le","sequence":"first","affiliation":[{"name":"Department of Health Management and Policy, School of Public Health, University of Michigan , Ann Arbor, MI , USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mona","family":"Issabakhsh","sequence":"additional","affiliation":[{"name":"Department of Oncology, School of Medicine, Georgetown University , Washington, DC , USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5851-8652","authenticated-orcid":false,"given":"Yameng","family":"Li","sequence":"additional","affiliation":[{"name":"Department of Oncology, School of Medicine, Georgetown University , Washington, DC , USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7951-3965","authenticated-orcid":false,"given":"Luz","family":"Mar\u00eda S\u00e1nchez-Romero","sequence":"additional","affiliation":[{"name":"Department of Oncology, School of Medicine, Georgetown University , Washington, DC , USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiale","family":"Tan","sequence":"additional","affiliation":[{"name":"Department of Epidemiology, School of Public Health, University of Michigan , Ann Arbor, MI , USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1076-5037","authenticated-orcid":false,"given":"Rafael","family":"Meza","sequence":"additional","affiliation":[{"name":"Integrative Oncology, BC Cancer Research Institute , Vancouver BC , USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5280-3612","authenticated-orcid":false,"given":"David","family":"Levy","sequence":"additional","affiliation":[{"name":"Department of Oncology, School of Medicine, Georgetown University , Washington, DC , USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4415-4832","authenticated-orcid":false,"given":"David","family":"Mendez","sequence":"additional","affiliation":[{"name":"Department of Health Management and Policy, School of Public Health, University of Michigan , Ann Arbor, MI , USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2023,4,26]]},"reference":[{"issue":"46","key":"2023071411350100300_CIT0001","doi-asserted-by":"crossref","first-page":"1736","DOI":"10.15585\/mmwr.mm6946a4","article-title":"Tobacco product use among adults\u2014United States, 2019","volume":"69","author":"Cornelius","year":"2020","journal-title":"MMWR Morb Mortal Wkly Rep."},{"key":"2023071411350100300_CIT0002","author":"US Department of Health and Human Service"},{"key":"2023071411350100300_CIT0003","volume-title":"E-cigarette Use Among Youth and Young Adults: A Report of the Surgeon General","author":"US Department of Health and Human Services","year":"2016"},{"key":"2023071411350100300_CIT0004","volume-title":"The Health Consequences of Smoking - 50 Years of Progress: A Report of the Surgeon General","author":"U.S. Department of Health and Human Services","year":"2014"},{"key":"2023071411350100300_CIT0005","doi-asserted-by":"crossref","first-page":"106529","DOI":"10.1016\/j.ypmed.2021.106529","article-title":"US healthcare spending attributable to cigarette smoking in 2014","volume":"150","author":"Xu","year":"2021","journal-title":"Prev Med."},{"issue":"5","key":"2023071411350100300_CIT0006","doi-asserted-by":"crossref","first-page":"710","DOI":"10.1093\/ntr\/ntab243","article-title":"Is adolescent e-cigarette use associated with subsequent smoking? a new look","volume":"24","author":"Sun","year":"2021","journal-title":"Nicotine Tob Res."},{"key":"2023071411350100300_CIT0007","doi-asserted-by":"crossref","first-page":"343","DOI":"10.1016\/j.addbeh.2017.08.023","article-title":"Exclusive e-cigarette use predicts cigarette initiation among college students","volume":"76","author":"Loukas","year":"2018","journal-title":"Addict Behav."},{"issue":"2","key":"2023071411350100300_CIT0008","doi-asserted-by":"crossref","first-page":"181","DOI":"10.1001\/jamapediatrics.2017.4173","article-title":"Association of noncigarette tobacco product use with future cigarette smoking among youth in the Population Assessment of Tobacco and Health (PATH) study, 2013-2015","volume":"172","author":"Watkins","year":"2018","journal-title":"JAMA Pediatr"},{"key":"2023071411350100300_CIT0009","doi-asserted-by":"crossref","first-page":"45","DOI":"10.1016\/j.socscimed.2014.08.016","article-title":"All gates lead to smoking: the \u201cgateway theory,\u201d e-cigarettes and the remaking of nicotine","volume":"119","author":"Bell","year":"2014","journal-title":"Soc Sci Med."},{"key":"2023071411350100300_CIT0010"},{"issue":"1","key":"2023071411350100300_CIT0011","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/s12859-018-2264-5","article-title":"Random forest versus logistic regression: a large-scale benchmark experiment","volume":"19","author":"Couronn\u00e9","year":"2018","journal-title":"BMC Bioinform"},{"issue":"1","key":"2023071411350100300_CIT0012","doi-asserted-by":"crossref","first-page":"87","DOI":"10.1093\/pan\/mpv024","article-title":"Comparing random forest with logistic regression for predicting class-imbalanced civil war onset data","volume":"24","author":"Muchlinski","year":"2016","journal-title":"Political Anal"},{"issue":"1","key":"2023071411350100300_CIT0013","doi-asserted-by":"crossref","first-page":"99","DOI":"10.1136\/tobaccocontrol-2020-056438","article-title":"Machine learning applications in tobacco research: a scoping review","volume":"32","author":"Fu","year":"2021","journal-title":"Tob Control."},{"key":"2023071411350100300_CIT0014","doi-asserted-by":"crossref","first-page":"106418","DOI":"10.1016\/j.ypmed.2021.106418","article-title":"Identifying emerging predictors for adolescent electronic nicotine delivery systems use: a machine learning analysis of the Population Assessment of Tobacco and Health Study","volume":"145","author":"Han","year":"2021","journal-title":"Prev Med."},{"issue":"1","key":"2023071411350100300_CIT0015","first-page":"21","article-title":"A machine learning approach to predict e-cigarette use and dependence among Ontario youth.","volume":"42","author":"Shi","year":"2022","journal-title":"The HPCDP Journal"},{"issue":"3","key":"2023071411350100300_CIT0016","doi-asserted-by":"crossref","first-page":"415","DOI":"10.1093\/ntr\/nty259","article-title":"A machine-learning approach to predicting smoking cessation treatment outcomes","volume":"22","author":"Coughlin","year":"2020","journal-title":"Nicotine Tob Res."},{"issue":"12","key":"2023071411350100300_CIT0017","doi-asserted-by":"crossref","first-page":"e0000060","DOI":"10.1371\/journal.pgph.0000060","article-title":"Machine learning models of tobacco susceptibility and current use among adolescents from 97 countries in the global youth tobacco survey, 2013-2017","volume":"1","author":"Kim","year":"2021","journal-title":"PLOS Glob Public Health."},{"issue":"7","key":"2023071411350100300_CIT0018","doi-asserted-by":"crossref","first-page":"1028","DOI":"10.1093\/ntr\/ntab257","article-title":"A machine learning approach to identify predictors of frequent vaping and vulnerable californian youth subgroups","volume":"24","author":"Fu","year":"2022","journal-title":"Nicotine Tob Res."},{"key":"2023071411350100300_CIT0019","volume-title":"Package \u201crandomforest.\u201d","author":"RColorBrewer","year":"2018"},{"issue":"19","key":"2023071411350100300_CIT0020","doi-asserted-by":"crossref","first-page":"2507","DOI":"10.1093\/bioinformatics\/btm344","article-title":"A review of feature selection techniques in bioinformatics","volume":"23","author":"Saeys","year":"2007","journal-title":"Bioinformatics."},{"issue":"1","key":"2023071411350100300_CIT0021","doi-asserted-by":"crossref","first-page":"389","DOI":"10.1023\/A:1012487302797","article-title":"Gene selection for cancer classification using support vector machines","volume":"46","author":"Guyon","year":"2002","journal-title":"Mach Learn."},{"key":"2023071411350100300_CIT0022","first-page":"1","author":"Kuhn","year":"2012"},{"key":"2023071411350100300_CIT0023","doi-asserted-by":"crossref","first-page":"92","DOI":"10.1007\/s10618-012-0295-5","article-title":"Training and assessing classification rules with imbalanced data","volume":"28","author":"Menardi","year":"2014","journal-title":"Data Min Knowl Discov."},{"issue":"2","key":"2023071411350100300_CIT0024","doi-asserted-by":"crossref","first-page":"197","DOI":"10.1007\/s11749-016-0481-7","article-title":"A random forest guided tour.","volume":"25","author":"Biau","year":"2016","journal-title":"Test"},{"key":"2023071411350100300_CIT0025","first-page":"157","volume-title":"Random forests","author":"Cutler","year":"2012"},{"key":"2023071411350100300_CIT0026","first-page":"785","article-title":"Xgboost: A scalable tree boosting system","author":"Chen","year":"2016"},{"key":"2023071411350100300_CIT0027","first-page":"519","article-title":"AUC: a statistically consistent and more discriminating measure than accuracy","volume":"3","author":"Ling","year":"2003","journal-title":"IJCAI."},{"issue":"3","key":"2023071411350100300_CIT0028","doi-asserted-by":"crossref","first-page":"276","DOI":"10.11613\/BM.2012.031","article-title":"Interrater reliability: the kappa statistic","volume":"22","author":"McHugh","year":"2012","journal-title":"Biochem Med."},{"key":"2023071411350100300_CIT0029","author":"Robin","year":"2021"},{"issue":"11","key":"2023071411350100300_CIT0030","doi-asserted-by":"crossref","first-page":"397","DOI":"10.15585\/mmwr.mm7111a1","article-title":"Tobacco product use among adults\u2014United States, 2020","volume":"71","author":"Cornelius","year":"2022","journal-title":"MMWR Morb Mortal Wkly Rep."},{"key":"2023071411350100300_CIT0031","article-title":"Smoking initiation among young adults in the United States and Canada, 1998-2010: a systematic review","volume":"9:110037","author":"Freedman","year":"2012","journal-title":"Prev Chronic Dis."},{"key":"2023071411350100300_CIT0032","doi-asserted-by":"crossref","first-page":"s191","DOI":"10.1136\/tobaccocontrol-2020-055671","article-title":"Correlates of tobacco product initiation among youth and adults in the USA: findings from the PATH Study Waves 1\u20133 (2013\u20132016)","volume":"29","author":"Kasza","year":"2020","journal-title":"Tob Control."},{"issue":"324","key":"2023071411350100300_CIT0033","doi-asserted-by":"crossref","first-page":"626","DOI":"10.1111\/ecca.12095","article-title":"Does job loss make you smoke and gain weight?","volume":"81","author":"Marcus","year":"2014","journal-title":"Economica."},{"issue":"5","key":"2023071411350100300_CIT0034","doi-asserted-by":"crossref","first-page":"e021080","DOI":"10.1136\/bmjopen-2017-021080","article-title":"Risky business: a longitudinal study examining cigarette smoking initiation among susceptible and non-susceptible e-cigarette users in Canada","volume":"8","author":"Aleyan","year":"2018","journal-title":"BMJ Open."},{"issue":"7","key":"2023071411350100300_CIT0035","doi-asserted-by":"crossref","first-page":"700","DOI":"10.1001\/jama.2015.8950","article-title":"Association of electronic cigarette use with initiation of combustible tobacco product smoking in early adolescence","volume":"314","author":"Leventhal","year":"2015","journal-title":"JAMA."},{"issue":"8","key":"2023071411350100300_CIT0036","doi-asserted-by":"crossref","first-page":"788","DOI":"10.1001\/jamapediatrics.2017.1488","article-title":"Association between initial use of e-cigarettes and subsequent cigarette smoking among adolescents and young adults: a systematic review and meta-analysis","volume":"171","author":"Soneji","year":"2017","journal-title":"JAMA Pediatr"},{"issue":"3","key":"2023071411350100300_CIT0037","doi-asserted-by":"crossref","first-page":"e045603","DOI":"10.1136\/bmjopen-2020-045603","article-title":"E-cigarette use and combustible tobacco cigarette smoking uptake among non-smokers, including relapse in former smokers: umbrella review, systematic review and meta-analysis","volume":"11","author":"Baenziger","year":"2021","journal-title":"BMJ Open."},{"issue":"6","key":"2023071411350100300_CIT0038","doi-asserted-by":"crossref","DOI":"10.1542\/peds.2020-017921","article-title":"Smoking susceptibility and tobacco media engagement among youth never smokers","volume":"147","author":"Coreas","year":"2021","journal-title":"Pediatrics."},{"issue":"5","key":"2023071411350100300_CIT0039","doi-asserted-by":"crossref","first-page":"688","DOI":"10.1177\/0093650216641183","article-title":"A fatal attraction: The effect of TV viewing on smoking initiation among young women.","volume":"46","author":"Johnson","year":"2019","journal-title":"Commun Res."},{"issue":"4","key":"2023071411350100300_CIT0040","doi-asserted-by":"crossref","first-page":"972","DOI":"10.1093\/ajae\/aaq036","article-title":"Low income and poor health choices: the example of smoking","volume":"92","author":"Binkley","year":"2010","journal-title":"Am J Agric Econ."},{"issue":"1","key":"2023071411350100300_CIT0041","doi-asserted-by":"crossref","first-page":"85","DOI":"10.1080\/1462220031000070507","article-title":"Psychiatric disorders, familial factors and cigarette smoking: I. Associations with smoking initiation","volume":"5","author":"Rohde","year":"2003","journal-title":"Nicotine Tob Res."},{"issue":"3","key":"2023071411350100300_CIT0042","doi-asserted-by":"crossref","first-page":"312","DOI":"10.1093\/ntr\/ntx010","article-title":"Time trends in smoking onset by sex and race\/ethnicity among adolescents and young adults: findings from the 2006\u20132013 National Survey on Drug Use and Health","volume":"20","author":"Thompson","year":"2018","journal-title":"Nicotine Tob Res."},{"issue":"5","key":"2023071411350100300_CIT0043","first-page":"LC08","article-title":"Exploring factors that influence smoking initiation and cessation among current smokers.","volume":"9","author":"Chezhian","year":"2015","journal-title":"J Clin Diagnostic Res."},{"key":"2023071411350100300_CIT0044","doi-asserted-by":"crossref","first-page":"106853","DOI":"10.1016\/j.addbeh.2021.106853","article-title":"Examining proximity exposure in a social network as a mechanism driving peer influence of adolescent smoking","volume":"117","author":"Khalil","year":"2021","journal-title":"Addict Behav."},{"issue":"5","key":"2023071411350100300_CIT0045","doi-asserted-by":"crossref","first-page":"497","DOI":"10.1016\/j.jadohealth.2012.02.017","article-title":"Smoking initiation during young adulthood: a longitudinal study of a population-based cohort","volume":"51","author":"Bernat","year":"2012","journal-title":"J Adolesc Health."},{"issue":"8","key":"2023071411350100300_CIT0046","doi-asserted-by":"crossref","first-page":"1322","DOI":"10.1093\/hmg\/ddy434","article-title":"The effect of body mass index on smoking behaviour and nicotine metabolism: a Mendelian randomization study","volume":"28","author":"Taylor","year":"2019","journal-title":"Hum Mol Genet."},{"issue":"2","key":"2023071411350100300_CIT0047","doi-asserted-by":"crossref","first-page":"197","DOI":"10.1093\/jpepsy\/jsy070","article-title":"Low self-esteem for physical appearance mediates the effect of body mass index on smoking initiation among adolescents","volume":"44","author":"Murphy","year":"2019","journal-title":"J Pediatr Psychol."},{"issue":"2","key":"2023071411350100300_CIT0048","doi-asserted-by":"crossref","first-page":"95","DOI":"10.1136\/tc.6.2.95","article-title":"Predictors of tobacco use initiation in adolescents: a two-year prospective study and theoretical discussion","volume":"6","author":"Wahlgren","year":"1997","journal-title":"Tob Control."},{"issue":"3","key":"2023071411350100300_CIT0049","doi-asserted-by":"crossref","first-page":"340","DOI":"10.1136\/jech.50.3.340","article-title":"Tobacco use prevalence and correlates among adolescents in a clinician initiated tobacco prevention trial in California, USA","volume":"50","author":"Hovell","year":"1996","journal-title":"J Epidemiol Community Health."},{"issue":"10","key":"2023071411350100300_CIT0050","doi-asserted-by":"crossref","first-page":"e2019022","DOI":"10.1001\/jamanetworkopen.2020.19022","article-title":"Trends in the age of cigarette smoking initiation among young adults in the US from 2002 to 2018","volume":"3","author":"Barrington-Trimis","year":"2020","journal-title":"JAMA Netw Open."}],"container-title":["Nicotine and Tobacco Research"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/ntr\/advance-article-pdf\/doi\/10.1093\/ntr\/ntad066\/50248950\/ntad066.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/ntr\/article-pdf\/25\/8\/1481\/50882369\/ntad066.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/ntr\/article-pdf\/25\/8\/1481\/50882369\/ntad066.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,7,14]],"date-time":"2023-07-14T07:36:00Z","timestamp":1689320160000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/ntr\/article\/25\/8\/1481\/7143558"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,4,26]]},"references-count":50,"journal-issue":{"issue":"8","published-online":{"date-parts":[[2023,4,26]]},"published-print":{"date-parts":[[2023,7,14]]}},"URL":"https:\/\/doi.org\/10.1093\/ntr\/ntad066","relation":{"has-preprint":[{"id-type":"doi","id":"10.1101\/2022.09.18.22280076","asserted-by":"object"}]},"ISSN":["1469-994X"],"issn-type":[{"value":"1469-994X","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2023,8,1]]},"published":{"date-parts":[[2023,4,26]]}}}