{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,14]],"date-time":"2026-09-14T21:03:38Z","timestamp":1789419818534,"version":"build-2803163510"},"reference-count":43,"publisher":"JMIR Publications Inc.","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["J Med Internet Res"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec sec-type=\"background\">\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Accurate measurements of children\u2019s digital technology use are essential for understanding its potential implications on health and well-being. Wearable cameras can provide such measurements, but image coding is a high burden for researchers. Machine learning\u2013based object-recognition models have the potential to reduce this burden by identifying images containing technology.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec sec-type=\"objective\">\n                    <jats:title>Objective<\/jats:title>\n                    <jats:p>This study aims to evaluate the performance of an object recognition model, the Square Eyes model, as a screening tool for identifying technologies in wearable camera images among children for further human review, as well as to examine the potential influence of face-blurring methods on the model\u2019s performance.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec sec-type=\"methods\">\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>This study used data collected on 48 children (aged 3\u201014 y) during an approximately 1-hour laboratory session. The children performed various technology-related tasks while wearing a camera. A total of 221,226 images were coded by humans and processed through the Square Eyes model. The performance of the Square Eyes model as a screening tool was evaluated by (1) assessing agreement between the model and human coding; (2) evaluating the N-back algorithm, an algorithm embedded in the model aimed to flag images requiring human review; and (3) examining the potential influence of facial-blurring on model performance.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec sec-type=\"results\">\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>\n                      Humans detected technology in 92,745 (41.9%) images, and the Square Eyes model detected technologies with an overall accuracy of 78.0%. When considering specific technologies, agreement between the model and human coders was the highest for\n                      <jats:italic>Television<\/jats:italic>\n                      (n=19,148, 54.3%) and\n                      <jats:italic>Laptop<\/jats:italic>\n                      (n=8492, 44.5%) and lowest for smaller devices such as\n                      <jats:italic>Smartphone<\/jats:italic>\n                      (n=2600, 31.3%) and\n                      <jats:italic>Tablet<\/jats:italic>\n                      (n=3685, 25.1%). The model\u2019s N-back algorithm effectively flagged images that required further human review, with only 7144 (3.2%) images that were not flagged for screening containing a human-coded technology. An explorative analysis indicated that using a square face-blurring with border could have reduced the model\u2019s ability to accurately detect technologies.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec sec-type=\"conclusions\">\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>The Square Eyes model demonstrated overall satisfying accuracy in detecting technologies and successfully flagged images that required further review by humans. These findings suggest that the model could be used as an effective screening tool for reducing the burden of human coding. However, the model could be improved to more accurately detect smaller devices, and the form of facial blurring in images should be considered.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.2196\/100559","type":"journal-article","created":{"date-parts":[[2026,8,26]],"date-time":"2026-08-26T16:10:07Z","timestamp":1787760607000},"page":"e100559-e100559","source":"Crossref","is-referenced-by-count":0,"title":["Evaluation of the Square Eyes Model as a Screening Tool for Identifying Digital Technologies in Wearable Camera Images Among Children: Laboratory Study"],"prefix":"10.2196","volume":"28","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2193-5019","authenticated-orcid":false,"given":"Charlotte Lund","family":"Rasmussen","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4504-6008","authenticated-orcid":false,"given":"Taren","family":"Sanders","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9948-7415","authenticated-orcid":false,"given":"Erin Kaye","family":"Howie","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1302-4429","authenticated-orcid":false,"given":"Amber","family":"Beynon","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8701-2212","authenticated-orcid":false,"given":"Danica","family":"Hendry","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6815-7544","authenticated-orcid":false,"given":"Juliana","family":"Zabatiero","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6461-6280","authenticated-orcid":false,"given":"Amity","family":"Campbell","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7786-4128","authenticated-orcid":false,"given":"Leon","family":"Straker","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1010","published-online":{"date-parts":[[2026,9,14]]},"reference":[{"issue":"3","key":"R1","doi-asserted-by":"publisher","first-page":"935","DOI":"10.1007\/s12187-019-09663-1","article-title":"A descriptive epidemiology of screen-based devices by children and adolescents: a scoping review of 130 surveillance studies since 2000","volume":"13","author":"Thomas","journal-title":"Child Ind Res"},{"issue":"4","key":"R2","doi-asserted-by":"publisher","first-page":"605","DOI":"10.1080\/17482798.2024.2394939","article-title":"Digital media and technology use by families with infants, toddlers, and young children: a scoping review and call for forward momentum","volume":"18","author":"Mannell","journal-title":"J Child Media"},{"key":"R3","doi-asserted-by":"crossref","unstructured":"Mann SC Lenhart A Robb MB . The common sense census: media use by kids age zero to eight. Common Sense Media; 2025. URL: https:\/\/www.commonsensemedia.org\/research\/the-2025-common-sense-census-media-use-by-kids-zero-to-eight [Accessed 03-09-2026]","DOI":"10.65077\/AUGG2895"},{"issue":"19","key":"R4","doi-asserted-by":"publisher","first-page":"7324","DOI":"10.3390\/ijerph17197324","article-title":"The relationships between screen use and health indicators among infants, toddlers, and preschoolers: a meta-analysis and systematic review","volume":"17","author":"Li","journal-title":"Int J Environ Res Public Health"},{"issue":"3","key":"R5","doi-asserted-by":"publisher","first-page":"323","DOI":"10.1007\/s40258-016-0289-3","article-title":"Screen time and health indicators among children and youth: current evidence, limitations and future directions","volume":"15","author":"Saunders","journal-title":"Appl Health Econ Health Policy"},{"key":"R6","doi-asserted-by":"publisher","DOI":"10.1016\/j.dr.2016.12.002","article-title":"The relationship between television exposure and children\u2019s cognition and behaviour: a systematic review","volume":"44","author":"Kostyrka-Allchorne","journal-title":"Dev Rev"},{"issue":"1","key":"R7","doi-asserted-by":"publisher","DOI":"10.1186\/s41155-023-00262-2","article-title":"Reducing harm and promoting positive media use strategies: new perspectives in understanding the impact of preschooler media use on health and development","volume":"36","author":"Fitzpatrick","journal-title":"Psicol Refl Cr\u00edt"},{"issue":"1","key":"R8","doi-asserted-by":"publisher","first-page":"82","DOI":"10.1038\/s41562-023-01712-8","article-title":"An umbrella review of the benefits and risks associated with youths\u2019 interactions with electronic screens","volume":"8","author":"Sanders","journal-title":"Nat Hum Behav"},{"issue":"10","key":"R9","doi-asserted-by":"publisher","first-page":"1017","DOI":"10.1001\/jamapediatrics.2024.2620","article-title":"Early childhood screen use contexts and cognitive and psychosocial outcomes: a systematic review and meta-analysis","volume":"178","author":"Mallawaarachchi","journal-title":"JAMA Pediatr"},{"issue":"7","key":"R10","doi-asserted-by":"publisher","DOI":"10.3390\/children11070754","article-title":"Measurement method options to investigate digital screen technology use by children and adolescents: a narrative review","volume":"11","author":"Beynon","journal-title":"Children (Basel)"},{"issue":"11","key":"R11","doi-asserted-by":"publisher","first-page":"1535","DOI":"10.1038\/s41562-021-01117-5","article-title":"A systematic review and meta-analysis of discrepancies between logged and self-reported digital media use","volume":"5","author":"Parry","journal-title":"Nat Hum Behav"},{"issue":"3","key":"R12","doi-asserted-by":"publisher","first-page":"320","DOI":"10.1016\/j.amepre.2012.11.008","article-title":"Wearable cameras in health: the state of the art and future possibilities","volume":"44","author":"Doherty","journal-title":"Am J Prev Med"},{"issue":"11","key":"R13","doi-asserted-by":"publisher","first-page":"2144","DOI":"10.1016\/j.jand.2018.05.013","article-title":"Dietary assessment with a wearable camera among children: feasibility and intercoder reliability","volume":"118","author":"Beltran","journal-title":"J Acad Nutr Diet"},{"issue":"1","key":"R14","doi-asserted-by":"publisher","DOI":"10.1186\/s12966-017-0570-3","article-title":"Children\u2019s everyday exposure to food marketing: an objective analysis using wearable cameras","volume":"14","author":"Signal","journal-title":"Int J Behav Nutr Phys Act"},{"key":"R15","doi-asserted-by":"publisher","DOI":"10.1016\/j.healthplace.2017.06.003","article-title":"Children\u2019s exposure to alcohol marketing within supermarkets: an objective analysis using GPS technology and wearable cameras","volume":"46","author":"Chambers","journal-title":"Health Place"},{"issue":"2","key":"R16","doi-asserted-by":"publisher","first-page":"306","DOI":"10.1111\/cch.12631","article-title":"Are children smoke-free at home? Using wearable cameras to study children\u2019s exposure to smoking and smoking paraphernalia in private spaces","volume":"45","author":"Gurtner","journal-title":"Child Care Health Dev"},{"key":"R17","doi-asserted-by":"publisher","DOI":"10.1016\/j.jth.2023.101604","article-title":"Fun, food and friends: a wearable camera analysis of children\u2019s school journeys","volume":"30","author":"Gage","journal-title":"J Transp Health"},{"issue":"18","key":"R18","doi-asserted-by":"publisher","DOI":"10.3390\/nu17182990","article-title":"Wearable camera-based objective screen time and its combined associations with dietary and physical activity factors in relation to childhood obesity","volume":"17","author":"Liu","journal-title":"Nutrients"},{"key":"R19","unstructured":"Hou X Shen S Li X et al. Enhancing screen time identification in children with a multi-view vision language model and screen time tracker. arXiv. Preprint posted online on Oct 2, 2024. [doi: 10.48550\/arXiv.2410.01966]"},{"issue":"1578","key":"R20","doi-asserted-by":"publisher","first-page":"12","DOI":"10.26635\/6965.6023","article-title":"Watching the watchers: assessing the nature and extent of children\u2019s screen time using wearable cameras","volume":"136","author":"Lowe","journal-title":"N Z Med J"},{"issue":"1","key":"R21","doi-asserted-by":"publisher","DOI":"10.2196\/28208","article-title":"Using wearable cameras to categorize the type and context of screen-based behaviors among adolescents: observational study","volume":"5","author":"Thomas","journal-title":"JMIR Pediatr Parent"},{"issue":"3","key":"R22","doi-asserted-by":"publisher","first-page":"417","DOI":"10.1016\/j.amepre.2019.04.012","article-title":"Feasibility of automated cameras to measure screen use in adolescents","volume":"57","author":"Smith","journal-title":"Am J Prev Med"},{"issue":"5","key":"R23","doi-asserted-by":"publisher","first-page":"923","DOI":"10.1016\/j.amepre.2023.05.004","article-title":"Development of a protocol for objectively measuring digital device use in youth","volume":"65","author":"Brosnan","journal-title":"Am J Prev Med"},{"issue":"8","key":"R24","doi-asserted-by":"publisher","first-page":"6511","DOI":"10.1007\/s00146-025-02372-0","article-title":"A systematic review: object detection","volume":"40","author":"Guleria","journal-title":"AI Soc"},{"key":"R25","doi-asserted-by":"crossref","unstructured":"Li X Holiday S Cribbet M et al. Non-invasive screen exposure time assessment using wearable sensor and object detection. Presented at: 2022 44th Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC); Jul 11-15, 2022; Glasgow, Scotland, United Kingdom. [doi: 10.1109\/EMBC48229.2022.9871903]","DOI":"10.1109\/EMBC48229.2022.9871903"},{"key":"R26","doi-asserted-by":"publisher","DOI":"10.1016\/j.buildenv.2024.111720","article-title":"Assessing personal screen exposure with ever-changing contexts using wearable cameras and computer vision","volume":"261","author":"Su","journal-title":"Build Environ"},{"key":"R27","unstructured":"Sanders T . Motivation-and-behaviour\/squareeyes. GitHub. 2025. URL: https:\/\/github.com\/Motivation-and-Behaviour\/SquareEyes [Accessed 07-09-2026]"},{"key":"R28","unstructured":"DP200101912 \u2014 Australian Catholic University. Australian Research Council. 2020. URL: https:\/\/dataportal.arc.gov.au\/NCGP\/Web\/Grant\/Grant\/DP200101912 [Accessed 03-09-2026]"},{"issue":"3","key":"R29","doi-asserted-by":"publisher","first-page":"314","DOI":"10.1016\/j.amepre.2012.11.006","article-title":"An ethical framework for automated, wearable cameras in health behavior research","volume":"44","author":"Kelly","journal-title":"Am J Prev Med"},{"key":"R30","doi-asserted-by":"crossref","unstructured":"L\u00e9bl M \u0160roubek F Flusser J . Impact of image blur on classification and augmentation of deep convolutional networks. In: Gade R Felsberg M K\u00e4m\u00e4r\u00e4inen JK , editors. Image Analysis: 22nd Scandinavian Conference, SCIA 2023, Sirkka, Finland, April 18\u201321, 2023, Proceedings, Part II. Springer; 2023:108-117. [doi: 10.1007\/978-3-031-31438-4_8]","DOI":"10.1007\/978-3-031-31438-4_8"},{"issue":"3","key":"R31","doi-asserted-by":"publisher","first-page":"232","DOI":"10.1016\/j.jsams.2015.01.009","article-title":"Longitudinal levels and bouts of objectively measured sedentary time among young Australian children in the HAPPY study","volume":"19","author":"Carson","journal-title":"J Sci Med Sport"},{"issue":"40-7","key":"R32","doi-asserted-by":"publisher","first-page":"40","DOI":"10.1016\/j.ypmed.2016.11.010","article-title":"Sedentary behaviour across the primary-secondary school transition: a systematic review","volume":"94","author":"Pearson","journal-title":"Prev Med"},{"issue":"59","key":"R33","doi-asserted-by":"publisher","DOI":"10.1186\/s12966-015-0218-0","article-title":"Changing from primary to secondary school highlights opportunities for school environment interventions aiming to increase physical activity and reduce sedentary behaviour: a longitudinal cohort study","volume":"12","author":"Marks","journal-title":"Int J Behav Nutr Phys Act"},{"key":"R34","doi-asserted-by":"publisher","DOI":"10.1016\/j.chb.2020.106501","article-title":"Trajectories of screen use during early childhood: predictors and associated behavior and learning outcomes","volume":"113","author":"McArthur","journal-title":"Comput Human Behav"},{"issue":"3","key":"R35","doi-asserted-by":"publisher","first-page":"290","DOI":"10.1016\/j.amepre.2012.11.004","article-title":"Using the SenseCam to improve classifications of sedentary behavior in free-living settings","volume":"44","author":"Kerr","journal-title":"Am J Prev Med"},{"issue":"3","key":"R36","doi-asserted-by":"publisher","first-page":"257","DOI":"10.1093\/ptj\/85.3.257","article-title":"The kappa statistic in reliability studies: use, interpretation, and sample size requirements","volume":"85","author":"Sim","journal-title":"Phys Ther"},{"key":"R37","unstructured":"Jocher G Chaurasia A Jing Q . Ultralytics yolov8. 8.0.0 ed. Ultralytics. 2023. URL: https:\/\/docs.ultralytics.com\/models\/yolov8 [Accessed 03-09-2026]"},{"key":"R38","doi-asserted-by":"crossref","unstructured":"Redmon J Divvala S Girshick R Farhadi A . You only look once: unified, real-time object detection. Presented at: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR); Jun 27-30, 2016; Las Vegas, NV, USA. [doi: 10.1109\/CVPR.2016.91]","DOI":"10.1109\/CVPR.2016.91"},{"issue":"5","key":"R39","doi-asserted-by":"publisher","first-page":"423","DOI":"10.1016\/0895-4356(93)90018-v","article-title":"Bias, prevalence and kappa","volume":"46","author":"Byrt","journal-title":"J Clin Epidemiol"},{"issue":"1","key":"R40","doi-asserted-by":"publisher","first-page":"159","DOI":"10.2307\/2529310","article-title":"The measurement of observer agreement for categorical data","volume":"33","author":"Landis","journal-title":"Biometrics"},{"issue":"5","key":"R41","doi-asserted-by":"publisher","first-page":"658","DOI":"10.1080\/00140139.2017.1401671","article-title":"Mobile technology dominates school children\u2019s IT use in an advantaged school community and is associated with musculoskeletal and visual symptoms","volume":"61","author":"Straker","journal-title":"Ergonomics"},{"issue":"1","key":"R42","doi-asserted-by":"publisher","DOI":"10.1186\/s12859-023-05156-9","article-title":"Evaluation of a decided sample size in machine learning applications","volume":"24","author":"Rajput","journal-title":"BMC Bioinformatics"},{"issue":"23","key":"R43","doi-asserted-by":"publisher","DOI":"10.3390\/s22239376","article-title":"Effect of face blurring on human pose estimation: ensuring subject privacy for medical and occupational health applications","volume":"22","author":"Jiang","journal-title":"Sensors (Basel)"}],"container-title":["Journal of Medical Internet Research"],"original-title":[],"language":"en","deposited":{"date-parts":[[2026,9,14]],"date-time":"2026-09-14T20:11:27Z","timestamp":1789416687000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.jmir.org\/2026\/1\/e100559"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,14]]},"references-count":43,"URL":"https:\/\/doi.org\/10.2196\/100559","relation":{},"ISSN":["1438-8871"],"issn-type":[{"value":"1438-8871","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,14]]},"article-number":"v28i3e100559"}}