{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"institution":[{"name":"medRxiv"}],"indexed":{"date-parts":[[2026,6,10]],"date-time":"2026-06-10T00:16:03Z","timestamp":1781050563105,"version":"3.54.1"},"posted":{"date-parts":[[2025,6,20]]},"group-title":"Public and Global Health","reference-count":38,"publisher":"openRxiv","license":[{"start":{"date-parts":[[2025,6,20]],"date-time":"2025-06-20T00:00:00Z","timestamp":1750377600000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"accepted":{"date-parts":[[2025,6,20]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                <jats:sec>\n                  <jats:title>Background<\/jats:title>\n                  <jats:p>The most effective way to reduce mortality and morbidity among current smokers is to quit smoking. Although about half of smokers attempted to quit, only one-tenth succeeded in 2022.<\/jats:p>\n                <\/jats:sec>\n                <jats:sec>\n                  <jats:title>Objective<\/jats:title>\n                  <jats:p>To identify key predictors of smoking cessation success to inform cessation interventions and increase quitting rates.<\/jats:p>\n                <\/jats:sec>\n                <jats:sec>\n                  <jats:title>Methods<\/jats:title>\n                  <jats:p>We analyzed data from waves 5 and 6 of the Population Assessment of Tobacco and Health (PATH) study (December 2018 to November 2021). Using OpenAI\u2019s GPT-4.1, we identified the top 45 variables from wave 5 that are highly predictive of 12-month smoking abstinence in wave 6, based on descriptions of survey variables. We then validated the predictive power of the GPT-4.1-selected variables by comparing the performance of eXtreme Gradient Boosting (XGBoost) trained on different sets of variables. Finally, we derived insights into the top 10 variables, ranked according to their SHapley Additive exPlanations values.<\/jats:p>\n                <\/jats:sec>\n                <jats:sec>\n                  <jats:title>Results<\/jats:title>\n                  <jats:p>The performance of XGBoost trained with all possible wave 5 variables and the 45 selected variables was almost identical (AUC:0.749 vs AUC:0.752). The top 10 variables included past 30-day smoking frequency, minutes from waking up to smoking first cigarette, important people\u2019s views on tobacco use, prevalence of tobacco use among close associates, daily electronic nicotine product use, emotional dependence, and health harm concerns.<\/jats:p>\n                <\/jats:sec>\n                <jats:sec>\n                  <jats:title>Conclusion<\/jats:title>\n                  <jats:p>This study demonstrates the ability of OpenAI\u2019s GPT-4.1 to identify the top 45 PATH wave 5 variables associated with 12-month smoking abstinence using only their descriptions. This approach could help researchers design more effective survey questionnaires and improve efficiency of data collection.<\/jats:p>\n                <\/jats:sec>\n                <jats:sec>\n                  <jats:title>What is already known on this topic<\/jats:title>\n                  <jats:p>Generative artificial intelligence models have recently been applied to assess their potential in addressing various tobacco-related issues, such as detecting tobacco products in social media videos and promoting vaping cessation. However, their application in identifying the most significant predictors of tobacco use behavior, based on survey data, remains unexplored.<\/jats:p>\n                <\/jats:sec>\n                <jats:sec>\n                  <jats:title>What this study adds<\/jats:title>\n                  <jats:p>GPT-4.1 successfully assigned high-quality importance scores to survey variables for predicting 12-month smoking abstinence over two years among current established smokers. It accomplished this using only the textual descriptions of the survey variables, without accessing the actual survey data. Based on these importance scores, GPT-4.1 can aid in identifying the most crucial variables for predicting smoking cessation success.<\/jats:p>\n                <\/jats:sec>\n                <jats:sec>\n                  <jats:title>How this study might affect research, practice or policy<\/jats:title>\n                  <jats:p>This study demonstrates the capacity of GPT-4.1 to perform feature selection, paving the way for future exploration of this innovative approach to address other tobacco-related issues.<\/jats:p>\n                <\/jats:sec>","DOI":"10.1101\/2025.06.18.25329854","type":"posted-content","created":{"date-parts":[[2025,6,20]],"date-time":"2025-06-20T18:35:19Z","timestamp":1750444519000},"source":"Crossref","is-referenced-by-count":1,"title":["Identifying Key Predictors of Smoking Cessation Success: Text-Based Feature Selection Using a Large Language Model"],"prefix":"10.64898","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3106-4045","authenticated-orcid":false,"given":"Thuy T. T.","family":"Le","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiongxuan","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zimo","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kaidi","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenjun","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yan","family":"Hu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"54368","reference":[{"key":"2025062307250764000_2025.06.18.25329854v1.1","unstructured":"U.S. Department of Health and Human Services. The Health Consequences of Smoking\u201450 Years of Progress: A Report of the Surgeon General. Atlanta: U.S. Department of Health and Human Services, Centers for Disease Control and Prevention, National Center for Chronic Disease Prevention and Health Promotion, Office on Smoking and Health, 2014."},{"key":"2025062307250764000_2025.06.18.25329854v1.2","unstructured":"U.S. Department of Health and Human Services. How Tobacco Smoke Causes Disease: The Biology and Behavioral Basis for Smoking-Attributable Disease: A Report of the Surgeon General. Atlanta, GA: U.S. Department of Health and Human Services, Centers for Disease Control and Prevention, National Center for Chronic Disease Prevention and Health Promotion, Office on Smoking and Health, 2010."},{"key":"2025062307250764000_2025.06.18.25329854v1.3","doi-asserted-by":"crossref","unstructured":"VanFrank B. Adult Smoking Cessation\u2014United States, 2022. MMWR Morbidity and Mortality Weekly Report 2024;73.","DOI":"10.15585\/mmwr.mm7329a1"},{"key":"2025062307250764000_2025.06.18.25329854v1.4","doi-asserted-by":"crossref","unstructured":"Coley K , Wang Q , Packer R , et al. Genome-wide association study of varenicline-aided smoking cessation. Nicotine and Tobacco Research 2025:taf009.","DOI":"10.1093\/ntr\/ntaf009"},{"issue":"10","key":"2025062307250764000_2025.06.18.25329854v1.5","doi-asserted-by":"crossref","first-page":"861","DOI":"10.2217\/pgs-2018-0023","article-title":"From genes to treatments: a systematic review of the pharmacogenetics in smoking cessation","volume":"19","year":"2018","journal-title":"Pharmacogenomics"},{"issue":"10","key":"2025062307250764000_2025.06.18.25329854v1.6","doi-asserted-by":"crossref","first-page":"e0184800","DOI":"10.1371\/journal.pone.0184800","article-title":"Success rates in smoking cessation: Psychological preparation plays a critical role and interacts with other factors such as psychoactive substances","volume":"12","year":"2017","journal-title":"PLoS One"},{"key":"2025062307250764000_2025.06.18.25329854v1.7","doi-asserted-by":"publisher","DOI":"10.1186\/1471-2458-11-1"},{"key":"2025062307250764000_2025.06.18.25329854v1.8","doi-asserted-by":"publisher","DOI":"10.1093\/ntr\/ntae225"},{"key":"2025062307250764000_2025.06.18.25329854v1.9","unstructured":"Aschbrenner KA , Naslund JA , Gill L , et al. Qualitative analysis of social network influences on quitting smoking among individuals with serious mental illness. Journal of Mental Health 2019."},{"key":"2025062307250764000_2025.06.18.25329854v1.10","doi-asserted-by":"publisher","DOI":"10.2105\/AJPH.2005.083527"},{"issue":"12","key":"2025062307250764000_2025.06.18.25329854v1.11","doi-asserted-by":"crossref","first-page":"2367","DOI":"10.1038\/s41562-024-02002-7","article-title":"A systematic review and network meta-analysis of population-level interventions to tackle smoking behaviour","volume":"8","year":"2024","journal-title":"Nature human behaviour"},{"key":"2025062307250764000_2025.06.18.25329854v1.12","doi-asserted-by":"publisher","DOI":"10.1136\/tobaccocontrol-2017-054108"},{"key":"2025062307250764000_2025.06.18.25329854v1.13","doi-asserted-by":"crossref","unstructured":"Le TTT , Issabakhsh M , Li Y , et al. 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. Nicotine & Tobacco Research 2023.","DOI":"10.1101\/2022.09.18.22280076"},{"issue":"10","key":"2025062307250764000_2025.06.18.25329854v1.14","doi-asserted-by":"crossref","first-page":"e2337101","DOI":"10.1001\/jamanetworkopen.2023.37101","article-title":"Key risk factors associated with electronic nicotine delivery systems use among adolescents","volume":"6","year":"2023","journal-title":"JAMA Network Open"},{"key":"2025062307250764000_2025.06.18.25329854v1.15","unstructured":"Jeong DP , Lipton ZC , Ravikumar P. Llm-select: Feature selection with large language models. arXiv preprint arXiv:240702694 2024."},{"issue":"2","key":"2025062307250764000_2025.06.18.25329854v1.16","doi-asserted-by":"crossref","first-page":"44","DOI":"10.1145\/3715073.3715077","article-title":"Exploring large language models for feature selection: A data-centric perspective","volume":"26","year":"2025","journal-title":"ACM SIGKDD Explorations Newsletter"},{"key":"2025062307250764000_2025.06.18.25329854v1.17","doi-asserted-by":"crossref","first-page":"26839","DOI":"10.1109\/ACCESS.2024.3365742","article-title":"A review on large language models: Architectures, applications, taxonomies, open issues and challenges","volume":"12","year":"2024","journal-title":"IEEE access"},{"issue":"1","key":"2025062307250764000_2025.06.18.25329854v1.18","doi-asserted-by":"crossref","first-page":"26","DOI":"10.1038\/s43856-024-00717-2","article-title":"Current applications and challenges in large language models for patient care: a systematic review","volume":"5","year":"2025","journal-title":"Communications Medicine"},{"key":"2025062307250764000_2025.06.18.25329854v1.19","unstructured":"FDA and NIH Study: Population Assessment of Tobacco and Health. https:\/\/www.fda.gov\/tobacco-products\/research\/fda-and-nih-study-population-assessment-tobacco-and-health."},{"key":"2025062307250764000_2025.06.18.25329854v1.20","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 2016:785\u2013794.","DOI":"10.1145\/2939672.2939785"},{"key":"2025062307250764000_2025.06.18.25329854v1.21","doi-asserted-by":"publisher","DOI":"10.1136\/tobaccocontrol-2016-052934"},{"key":"2025062307250764000_2025.06.18.25329854v1.22","unstructured":"OpenAI. Introducing GPT-4.1 in the API. https:\/\/openai.com\/index\/gpt-4-1\/."},{"key":"2025062307250764000_2025.06.18.25329854v1.23","unstructured":"XGBoost Parameters. https:\/\/xgboost.readthedocs.io\/en\/stable\/parameter.html."},{"key":"2025062307250764000_2025.06.18.25329854v1.24","unstructured":"Snoek J , Larochelle H , Adams RP . Practical bayesian optimization of machine learning algorithms. Advances in neural information processing systems 2012;25."},{"key":"2025062307250764000_2025.06.18.25329854v1.25","doi-asserted-by":"publisher","DOI":"10.4097\/kja.21209"},{"key":"2025062307250764000_2025.06.18.25329854v1.26","unstructured":"Lundberg SM , Lee S-I. A unified approach to interpreting model predictions. Advances in neural information processing systems 2017;30."},{"key":"2025062307250764000_2025.06.18.25329854v1.27","doi-asserted-by":"publisher","DOI":"10.1111\/cts.70056"},{"key":"2025062307250764000_2025.06.18.25329854v1.28","doi-asserted-by":"publisher","DOI":"10.1080\/14622200701673480"},{"key":"2025062307250764000_2025.06.18.25329854v1.29","doi-asserted-by":"crossref","first-page":"110","DOI":"10.1016\/j.addbeh.2018.01.016","article-title":"Factors associated with successful vs. unsuccessful smoking cessation: Data from a nationally representative study","volume":"80","year":"2018","journal-title":"Addictive behaviors"},{"key":"2025062307250764000_2025.06.18.25329854v1.30","doi-asserted-by":"crossref","first-page":"108134","DOI":"10.1016\/j.drugalcdep.2020.108134","article-title":"Predictive validity of the adult tobacco dependence index: findings from waves 1 and 2 of the Population Assessment of Tobacco and Health (PATH) study","volume":"214","year":"2020","journal-title":"Drug and alcohol dependence"},{"key":"2025062307250764000_2025.06.18.25329854v1.31","doi-asserted-by":"crossref","first-page":"257","DOI":"10.1016\/j.drugalcdep.2017.05.010","article-title":"Indicators of dependence for different types of tobacco product users: Descriptive findings from Wave 1 (2013-2014) of the Population Assessment of Tobacco and Health (PATH) study","volume":"178","year":"2017","journal-title":"Drug Alcohol Depend"},{"key":"2025062307250764000_2025.06.18.25329854v1.32","unstructured":"U.S. Department of Health and Human Services. Smoking Cessation: A Report of the Surgeon General. Atlanta, GA: U.S. Department of Health and Human Services, Centers for Disease Control and Prevention, National Center for Chronic Disease Prevention and Health Promotion, Office on Smoking and Health, 2020."},{"issue":"3","key":"2025062307250764000_2025.06.18.25329854v1.33","doi-asserted-by":"crossref","first-page":"e250089","DOI":"10.1001\/jamanetworkopen.2025.0089","article-title":"Daily or Nondaily Vaping and Smoking Cessation Among Smokers","volume":"8","year":"2025","journal-title":"JAMA Network Open"},{"key":"2025062307250764000_2025.06.18.25329854v1.34","doi-asserted-by":"publisher","DOI":"10.1136\/tobaccocontrol-2021-056901"},{"key":"2025062307250764000_2025.06.18.25329854v1.35","doi-asserted-by":"publisher","DOI":"10.1037\/a0036483"},{"key":"2025062307250764000_2025.06.18.25329854v1.36","doi-asserted-by":"crossref","first-page":"101886","DOI":"10.1016\/j.pmedr.2022.101886","article-title":"Association between family or peer views towards tobacco use and past 30-day smoking cessation among adults with mental health problems","volume":"28","year":"2022","journal-title":"Preventive Medicine Reports"},{"key":"2025062307250764000_2025.06.18.25329854v1.37","first-page":"60","article-title":"Are health conditions and concerns about health effects of smoking predictive of quitting? Findings from the ITC 4CV Survey (2016\u20132018)","volume":"6","year":"2020","journal-title":"Tobacco Prevention & Cessation"},{"key":"2025062307250764000_2025.06.18.25329854v1.38","doi-asserted-by":"crossref","unstructured":"Han H , Guo X , Yu H. Variable selection using mean decrease accuracy and mean decrease gini based on random forest. 2016 7th ieee international conference on software engineering and service science (icsess): IEEE 2016:219\u2013224.","DOI":"10.1109\/ICSESS.2016.7883053"}],"container-title":[],"original-title":[],"link":[{"URL":"https:\/\/syndication.highwire.org\/content\/doi\/10.1101\/2025.06.18.25329854","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,15]],"date-time":"2026-01-15T20:38:47Z","timestamp":1768509527000},"score":1,"resource":{"primary":{"URL":"http:\/\/medrxiv.org\/lookup\/doi\/10.1101\/2025.06.18.25329854"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,20]]},"references-count":38,"URL":"https:\/\/doi.org\/10.1101\/2025.06.18.25329854","relation":{},"subject":[],"published":{"date-parts":[[2025,6,20]]},"subtype":"preprint"}}