{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,9]],"date-time":"2026-07-09T15:18:47Z","timestamp":1783610327851,"version":"3.55.0"},"reference-count":26,"publisher":"Oxford University Press (OUP)","license":[{"start":{"date-parts":[[2026,7,9]],"date-time":"2026-07-09T00:00:00Z","timestamp":1783555200000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"name":"Bloomberg Initiative to Reduce Tobacco Use"},{"DOI":"10.13039\/100020365","name":"CDC Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100020365","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Introduction<\/jats:title>\n                    <jats:p>The e-cigarette market evolves faster than regulation and enforcement. In recent years, e-cigarette manufacturers have introduced vapes featuring not just addictive, flavored nicotine, but also technological features that appeal to youth. These products with digital screens have the potential to gamify the use of an addictive drug. To keep pace with these developments, automated tools capable of rapidly analyzing the online marketplace could inform regulatory enforcement.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>The goal of this work is to automatically detect and classify e-cigarette devices with screens. To do this, we first use an object detection model to filter web-scraped images that contain e-cigarettes. Product images and descriptions are then provided to a vision language model (VLM) to determine if the e-cigarette contains a screen. We evaluated the pipeline with images and text descriptions from five e-cigarette online retailers and manually validated predictions.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>The object detection model was trained on approximately 7000 images and tested on 3920 images achieving an accuracy, precision, recall, and F1 score of 0.95, 0.98, 0.94, 0.96 respectively in identifying e-cigarette devices. The VLM was tested on 2401 images and was able to detect screens on e-cigarette devices with an accuracy of 0.92, precision of 0.96, recall of 0.87, and F1 score of 0.92.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>Object detection models and VLMs can be combined to automatically detect and classify e-cigarettes with integrated screens. This method can enable rapid-response pipelines to identify youth-appealing features in emerging e-cigarette products and provide policymakers insights into their proliferation in the online marketplace.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Implications<\/jats:title>\n                    <jats:p>New e-cigarettes with potentially youth-appealing technological features, such as integrated screens, continue to be introduced to the US market, challenging timely and effective tobacco product surveillance and regulatory efforts. Digital screens on e-cigarettes offer greater user control and make products that deliver addictive, flavored nicotine resemble entertainment devices, rather than tobacco products. Our automated screen detection pipeline provides a scalable, rapid-response tool for monitoring online e-cigarette retailers in near real-time, quantifying the proliferation of products with specific features. This pipeline could be adapted to accommodate a variety of new features for detection, here we use the presence of screens as a test example. Rapid identification and classification of new tobacco products available online could help inform interventions before the sale and use of such products becomes widespread.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1093\/ntr\/ntag125","type":"journal-article","created":{"date-parts":[[2026,7,9]],"date-time":"2026-07-09T15:01:12Z","timestamp":1783609272000},"source":"Crossref","is-referenced-by-count":0,"title":["Automatic detection of e-cigarette screens using object detection and vision language models"],"prefix":"10.1093","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-1224-5669","authenticated-orcid":false,"given":"Hunter","family":"Morera","sequence":"first","affiliation":[{"name":"Georgia Tech Research Institute , 756 W Peachtree St NW, Atlanta, GA 30318 ,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"James","family":"Jun","sequence":"additional","affiliation":[{"name":"Georgia Tech Research Institute , 756 W Peachtree St NW, Atlanta, GA 30318 ,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Charity","family":"Hilton","sequence":"additional","affiliation":[{"name":"Georgia Tech Research Institute , 756 W Peachtree St NW, Atlanta, GA 30318 ,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dianna","family":"King","sequence":"additional","affiliation":[{"name":"Georgia Tech Research Institute , 756 W Peachtree St NW, Atlanta, GA 30318 ,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Elizabeth L","family":"Seaman Jones","sequence":"additional","affiliation":[{"name":"CDC Foundation , 600 Peachtree St NE #1000, Atlanta, GA 30308 ,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3385-6468","authenticated-orcid":false,"given":"Kristy","family":"Marynak","sequence":"additional","affiliation":[{"name":"CDC Foundation , 600 Peachtree St NE #1000, Atlanta, GA 30308 ,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Elisha","family":"Crane","sequence":"additional","affiliation":[{"name":"CDC Foundation , 600 Peachtree St NE #1000, Atlanta, GA 30308 ,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2026,7,9]]},"reference":[{"key":"2026070911010563600_ref1","doi-asserted-by":"publisher","first-page":"774","DOI":"10.15585\/mmwr.mm7335a3","article-title":"Notes from the field: e-cigarette and nicotine pouch use among middle and high school students\u2014United States, 2024","volume":"73","author":"Park-Lee","year":"2024","journal-title":"MMWR Morb Mortal Wkly Rep"},{"key":"2026070911010563600_ref2","doi-asserted-by":"publisher","first-page":"849","DOI":"10.1136\/tc-2024-058794","article-title":"Pac-Man on a vape: electronic cigarettes that target youth as handheld multimedia and gaming devices","volume":"34","author":"Wong","year":"2024","journal-title":"Tob Control"},{"key":"2026070911010563600_ref3","doi-asserted-by":"publisher","first-page":"536","DOI":"10.1001\/jama.2024.25255","article-title":"Vaping","volume":"333","author":"Marynak","year":"2025","journal-title":"JAMA"},{"key":"2026070911010563600_ref4","volume-title":"Monitoring U.S. E-Cigarette Sales: National Trends Data Brief (Issue 31)","author":"CDC Foundation","year":"2025"},{"key":"2026070911010563600_ref5","volume-title":"TEEN+ Data Snapshot (Issue 2): Smart Vapes."},{"key":"2026070911010563600_ref6","doi-asserted-by":"crossref","first-page":"2149","DOI":"10.1080\/10826084.2024.2392547","article-title":"Vaping devices with video games","volume":"59","author":"Unger","year":"2024","journal-title":"Subst Use Misuse"},{"key":"2026070911010563600_ref7","doi-asserted-by":"publisher","first-page":"136","DOI":"10.1038\/s44159-023-00153-4","article-title":"A taxonomy of technology design features that promote potentially addictive online behaviours","volume":"2","author":"Flayelle","year":"2023","journal-title":"Nat Rev Psychol"},{"key":"2026070911010563600_ref8","doi-asserted-by":"publisher","first-page":"693","DOI":"10.1136\/tc-2022-057908","article-title":"Playtime: vaping devices designed as cartoons and toys may appeal to kids","volume":"33","author":"Tatum","year":"2024","journal-title":"Tob Control"},{"key":"2026070911010563600_ref9","volume-title":"Retailers Warned to Stop Selling Illegal e-Cigarettes Resembling Youth-Appealing Characters, School Supplies, Toys, and Drinks."},{"key":"2026070911010563600_ref10","doi-asserted-by":"publisher","first-page":"e99","DOI":"10.1016\/j.amepre.2022.03.028","article-title":"Different times call for different measures: using retail sales to monitor the tobacco product landscape","volume":"63","author":"Seaman","year":"2022","journal-title":"Am J Prev Med"},{"key":"2026070911010563600_ref11","journal-title":"How to Start a Profitable Vape Wholesale Business."},{"key":"2026070911010563600_ref12","doi-asserted-by":"publisher","first-page":"552","DOI":"10.1093\/ntr\/ntad224","article-title":"Scalable surveillance of e-cigarette products on Instagram and TikTok using computer vision","volume":"26","author":"Vassey","year":"2023","journal-title":"Nicotine Tob Res"},{"key":"2026070911010563600_ref13","doi-asserted-by":"publisher","first-page":"S36","DOI":"10.1093\/ntr\/ntad184","article-title":"Using computer vision to detect e-cigarette content in TikTok videos","volume":"26","author":"Murthy","year":"2024","journal-title":"Nicotine Tob Res"},{"key":"2026070911010563600_ref14","doi-asserted-by":"publisher","first-page":"873","DOI":"10.1093\/ntr\/ntaf206","article-title":"Computer vision models for detecting large cigars on social media","volume":"28","author":"Kong","year":"2025","journal-title":"Nicotine Tob Res"},{"key":"2026070911010563600_ref15","doi-asserted-by":"publisher","first-page":"2063","DOI":"10.1093\/ntr\/ntaf057","article-title":"Demographic trends in e-cigarette social media marketing: perceiving gender presentation and facial age via computer vision","volume":"27","author":"Kennedy","year":"2025","journal-title":"Nicotine Tob Res"},{"key":"2026070911010563600_ref16","volume-title":"Version 4.22.0.","author":"Selenium Python Bindings [Computer Software]","year":"2024"},{"key":"2026070911010563600_ref17","doi-asserted-by":"publisher","first-page":"214","DOI":"10.3390\/s25010214","article-title":"A comprehensive survey of machine learning techniques and models for object detection","volume":"25","author":"Hsu","year":"2024","journal-title":"Sensors (Basel)"},{"key":"2026070911010563600_ref18","doi-asserted-by":"publisher","volume-title":"2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).","DOI":"10.1109\/CVPR.2016.91"},{"key":"2026070911010563600_ref19","volume-title":"Ultralytics YOLOv8 [Computer Software]. Version 8.2.0.","author":"Jocher","year":"2023"},{"key":"2026070911010563600_ref20","article-title":"Cigarette & E-cigarette detection dataset [data set]","author":"Takoyati.","year":"2025","journal-title":"Roboflow"},{"key":"2026070911010563600_ref21","volume-title":"CVAT: Annotate Better with CVAT, the Industry-Leading Data Engine for Machine Learning. Version [computer software]. Version 2.14.0.","author":"CVAT.ai","year":"2024"},{"key":"2026070911010563600_ref22"},{"key":"2026070911010563600_ref23","doi-asserted-by":"publisher","volume-title":"2023 IEEE International Conference on Big Data (Big Data)","DOI":"10.1109\/BigData59044.2023.10386743"},{"key":"2026070911010563600_ref24","volume-title":"Proceedings of the 38th International Conference on Machine Learning (ICML)."},{"key":"2026070911010563600_ref25","author":"Chen"},{"key":"2026070911010563600_ref26","author":"Wang"}],"container-title":["Nicotine &amp; Tobacco Research"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/ntr\/advance-article-pdf\/doi\/10.1093\/ntr\/ntag125\/68706962\/ntag125.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/ntr\/advance-article-pdf\/doi\/10.1093\/ntr\/ntag125\/68706962\/ntag125.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,9]],"date-time":"2026-07-09T15:01:15Z","timestamp":1783609275000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/ntr\/advance-article\/doi\/10.1093\/ntr\/ntag125\/8726025"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,9]]},"references-count":26,"URL":"https:\/\/doi.org\/10.1093\/ntr\/ntag125","relation":{},"ISSN":["1469-994X"],"issn-type":[{"value":"1469-994X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,9]]},"article-number":"ntag125"}}