{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:44:03Z","timestamp":1785545043802,"version":"3.56.0"},"reference-count":39,"publisher":"JMIR Publications Inc.","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["J Med Internet Res"],"abstract":"Abstract<\/jats:title>\n \n Background<\/jats:title>\n SMS text message reminders have been used to promote many health behaviors, such as improving diet and physical activity, managing chronic health conditions, reminding patients about medical appointments, and supporting medication adherence across a range of health conditions. Despite their promise, developing effective reminders tailored to specific patient populations is resource-intensive. AI may facilitate item development, and online research panels may provide an efficient way to test message content with target users prior to implementing large-scale trials.<\/jats:p>\n <\/jats:sec>\n \n Objective<\/jats:title>\n This study aimed to (1) develop a library of antidepressant adherence\u2013promoting SMS text messages that are perceived as helpful, (2) test whether an online panel approach can be used to evaluate them, and (3) identify message characteristics perceived as most helpful by patients with depression taking antidepressant medication.<\/jats:p>\n <\/jats:sec>\n \n Methods<\/jats:title>\n In total, 83 SMS text message reminders were developed based on barriers to adherence and behavior change technique pairings, with approximately half authored by the study team, and half generated by AI. Using an online panel, we recruited 181 American adults with depression currently prescribed an antidepressant medication. Each participant rated a subset of messages on how much they thought each would help them remember to take their medication. Associations between message characteristics and ratings were estimated using generalized linear models in Stata. Survey weights were used in analyses to align the sample with national antidepressant user demographics.<\/jats:p>\n <\/jats:sec>\n \n Results<\/jats:title>\n \n The online panel was able to rapidly recruit a sample of participants, who provided 7520 item ratings in total. AI-generated messages were rated as significantly more helpful than those authored by humans (adjusted mean difference 0.24 on a 5-point scale, 95% CI 0.12\u20100.36;\n P<\/jats:italic>\n <.001). Messages addressing delayed symptom benefit were preferred over other adherence barriers, and behavior change techniques emphasizing self-monitoring (\n P<\/jats:italic>\n <.001), habit formation (\n P<\/jats:italic>\n <.001), and natural consequences (\n P<\/jats:italic>\n <.001) received significantly higher ratings than those using external influence or support. No difference was observed between motivational and informational message content.\n <\/jats:p>\n <\/jats:sec>\n \n Conclusions<\/jats:title>\n Online panels offer a rapid, scalable approach to evaluating SMS text message reminders for patients currently taking antidepressants. When provided with specific instructions and human-led examples, AI can efficiently generate message content perceived to be helpful in promoting medication adherence. Given that AI-generated content received higher ratings than human-authored messages, future work may consider using this tool to support rapid intervention development. In addition, identifying common barriers to adherence and applying behavior change techniques to address those barriers can inform targeted message development and support adherence. Taken together, these findings demonstrate the utility of combining low-cost methods such as online panel research with AI to accelerate the design and preliminary evaluation of digital health interventions.<\/jats:p>\n <\/jats:sec>","DOI":"10.2196\/86605","type":"journal-article","created":{"date-parts":[[2026,6,19]],"date-time":"2026-06-19T14:10:06Z","timestamp":1781878206000},"page":"e86605-e86605","source":"Crossref","is-referenced-by-count":0,"title":["Rapid Development and Testing of Behavioral Text Message Reminders for Antidepressant Adherence via Online Panels: Survey Study"],"prefix":"10.2196","volume":"28","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-3781-4868","authenticated-orcid":false,"given":"Tia R","family":"Tropea","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7819-3824","authenticated-orcid":false,"given":"Steven C","family":"Marcus","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6514-4441","authenticated-orcid":false,"given":"Amy","family":"Bucher","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5297-9933","authenticated-orcid":false,"given":"Cadence F","family":"Bowden","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3958-5662","authenticated-orcid":false,"given":"Mark","family":"Olfson","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6453-6715","authenticated-orcid":false,"given":"Rebecca E","family":"Stewart","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1010","published-online":{"date-parts":[[2026,7,23]]},"reference":[{"issue":"3","key":"R1","doi-asserted-by":"publisher","DOI":"10.2196\/mhealth.4114","article-title":"Efficacy of a text message-delivered extended contact intervention on maintenance of weight loss, physical activity, and dietary behavior change","volume":"3","author":"Spark","journal-title":"JMIR Mhealth Uhealth"},{"issue":"10","key":"R2","doi-asserted-by":"publisher","DOI":"10.2196\/jmir.4944","article-title":"Text message and internet support for coronary heart disease self-management: results from the Text4Heart randomized controlled trial","volume":"17","author":"Pfaeffli Dale","journal-title":"J Med Internet Res"},{"issue":"1","key":"R3","doi-asserted-by":"publisher","first-page":"142","DOI":"10.1016\/j.amepre.2019.08.014","article-title":"Text message interventions for physical activity: a systematic review and meta-analysis","volume":"58","author":"Smith","journal-title":"Am J Prev Med"},{"key":"R4","doi-asserted-by":"publisher","DOI":"10.1155\/2016\/8487378","article-title":"Text message reminders increase appointment adherence in a pediatric clinic: a randomized controlled trial","volume":"2016","author":"Lin","journal-title":"Int J Pediatr"},{"issue":"4","key":"R5","doi-asserted-by":"publisher","DOI":"10.2196\/mhealth.4917","article-title":"Developing and pretesting a text messaging program for health behavior change: recommended steps","volume":"3","author":"Abroms","journal-title":"JMIR Mhealth Uhealth"},{"issue":"2","key":"R6","doi-asserted-by":"publisher","DOI":"10.1177\/25152459221140388","article-title":"Using market-research panels for behavioral science: an overview and tutorial","volume":"6","author":"Moss","journal-title":"Adv Methods Pract Psychol Sci"},{"key":"R7","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-clinpsy-021815-093623","article-title":"Conducting clinical research using crowdsourced convenience samples","volume":"12","author":"Chandler","journal-title":"Annu Rev Clin Psychol"},{"issue":"3","key":"R8","doi-asserted-by":"publisher","first-page":"340","DOI":"10.1001\/jamainternmed.2015.7667","article-title":"Mobile telephone text messaging for medication adherence in chronic disease: a meta-analysis","volume":"176","author":"Thakkar","journal-title":"JAMA Intern Med"},{"issue":"10","key":"R9","doi-asserted-by":"publisher","first-page":"1153","DOI":"10.1176\/appi.ps.202100634","article-title":"Systematic literature review of text messaging interventions to promote medication adherence among people with serious mental illness","volume":"73","author":"Simon","journal-title":"Psychiatr Serv"},{"issue":"1","key":"R10","doi-asserted-by":"publisher","first-page":"67","DOI":"10.1097\/00005650-199501000-00006","article-title":"The role of the primary care physician in patients\u2019 adherence to antidepressant therapy","volume":"33","author":"Lin","journal-title":"Med Care"},{"issue":"5-6","key":"R11","first-page":"41","volume":"9","author":"Sansone","journal-title":"Innov Clin Neurosci"},{"key":"R12","doi-asserted-by":"publisher","DOI":"10.1016\/j.jad.2023.10.010","article-title":"Reasons for non-adherence with antidepressants using the Medication Adherence Reasons Scale in five European countries and United States","volume":"344","author":"Unni","journal-title":"J Affect Disord"},{"issue":"1","key":"R13","doi-asserted-by":"publisher","first-page":"19","DOI":"10.3390\/ph3010019","article-title":"The timing of antidepressant effects: a comparison of diverse pharmacological and somatic treatments","volume":"3","author":"Machado-Vieira","journal-title":"Pharmaceuticals (Basel)"},{"issue":"6","key":"R14","doi-asserted-by":"publisher","first-page":"827","DOI":"10.4088\/JCP.09m05528blu","article-title":"Reasons for antidepressant nonadherence among veterans treated in primary care clinics","volume":"72","author":"Fortney","journal-title":"J Clin Psychiatry"},{"issue":"24","key":"R15","doi-asserted-by":"publisher","DOI":"10.3390\/ijerph192416788","article-title":"Barriers and facilitating factors of adherence to antidepressant treatments: an exploratory qualitative study with patients and psychiatrists","volume":"19","author":"Gonz\u00e1lez de Le\u00f3n","journal-title":"Int J Environ Res Public Health"},{"issue":"1","key":"R16","doi-asserted-by":"publisher","first-page":"81","DOI":"10.1007\/s12160-013-9486-6","article-title":"The behavior change technique taxonomy (v1) of 93 hierarchically clustered techniques: building an international consensus for the reporting of behavior change interventions","volume":"46","author":"Michie","journal-title":"Ann Behav Med"},{"issue":"4","key":"R17","doi-asserted-by":"publisher","first-page":"749","DOI":"10.1007\/s41347-025-00491-5","article-title":"Comparing large language model AI and human-generated coaching messages for behavioral weight loss","volume":"10","author":"Huang","journal-title":"J Technol Behav Sci"},{"key":"R18","doi-asserted-by":"publisher","DOI":"10.3389\/fcomm.2023.1129082","article-title":"Artificial intelligence for health message generation: an empirical study using a large language model (LLM) and prompt engineering","volume":"8","author":"Lim","journal-title":"Front Commun"},{"issue":"7","key":"R19","doi-asserted-by":"publisher","first-page":"715","DOI":"10.1093\/ced\/llad456","article-title":"Comparing the quality of ChatGPT- and physician-generated responses to patients\u2019 dermatology questions in the electronic medical record","volume":"49","author":"Reynolds","journal-title":"Clin Exp Dermatol"},{"key":"R20","doi-asserted-by":"publisher","DOI":"10.2196\/68409","article-title":"Clinical performance and communication skills of ChatGPT versus physicians in emergency medicine: simulated patient study","volume":"13","author":"Park","journal-title":"JMIR Med Inform"},{"issue":"5","key":"R21","doi-asserted-by":"publisher","first-page":"344","DOI":"10.1097\/YCO.0000000000000086","article-title":"Factors predicting adherence to antidepressant treatment","volume":"27","author":"Hung","journal-title":"Curr Opin Psychiatry"},{"issue":"3","key":"R22","doi-asserted-by":"publisher","first-page":"174","DOI":"10.1080\/10810730.2023.2299003","article-title":"A COM-B and Theoretical Domains Framework mapping of the barriers and facilitators to effective communication and help-seeking among people with, or seeking a diagnosis of, endometriosis","volume":"29","author":"Hearn","journal-title":"J Health Commun"},{"key":"R23","doi-asserted-by":"publisher","DOI":"10.1186\/1748-5908-6-42","article-title":"The behaviour change wheel: a new method for characterising and designing behaviour change interventions","volume":"6","author":"Michie","journal-title":"Implement Sci"},{"key":"R24","unstructured":"CloudResearch. URL: https:\/\/www.cloudresearch.com\/products\/connect-for-researchers\/ [Accessed 08-07-2026]"},{"issue":"18","key":"R25","doi-asserted-by":"publisher","first-page":"3385","DOI":"10.1007\/s00213-015-3988-9","article-title":"The impact of age and gender on adherence to antidepressants: a 4-year population-based cohort study","volume":"232","author":"Krivoy","journal-title":"Psychopharmacology (Berl)"},{"issue":"4","key":"R26","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0265928","article-title":"Antidepressants and health-related quality of life (HRQoL) for patients with depression: analysis of the medical expenditure panel survey from the United States","volume":"17","author":"Almohammed","journal-title":"PLoS One"},{"key":"R27","unstructured":"Census Bureau releases new educational attainment data. US Census Bureau. Feb 24, 2022. URL: https:\/\/www.census.gov\/newsroom\/press-releases\/2022\/educational-attainment.html [Accessed 17-07-2026]"},{"key":"R28","unstructured":"Poverty guidelines. Assistant Secretary for Planning and Evaluation (ASPE); URL: http:\/\/aspe.hhs.gov\/topics\/poverty-economic-mobility\/poverty-guidelines [Accessed 17-10-2025]"},{"key":"R29","unstructured":"CloudResearch pricing. CloudResearch. URL: https:\/\/www.cloudresearch.com\/pricing\/ [Accessed 17-10-2025]"},{"key":"R30","unstructured":"Sharma M Tong M Korbak T et al. Towards understanding sycophancy in language models. arXiv. Preprint posted online on Oct 20, 2023. [doi: 10.48550\/arXiv.2310.13548]"},{"issue":"6","key":"R31","doi-asserted-by":"publisher","DOI":"10.1136\/bmjopen-2026-121721","article-title":"Three-arm randomised controlled trial of text message reminders and financial incentives to improve antidepressant adherence among adults in primary care with depression: study protocol","volume":"16","author":"Marcus","journal-title":"BMJ Open"},{"key":"R32","doi-asserted-by":"publisher","DOI":"10.2147\/PPA.S328785","article-title":"Patient and provider perspectives on medication non-adherence among patients with depression and\/or diabetes in diverse community settings - a qualitative analysis","volume":"16","author":"Hamilton","journal-title":"Patient Prefer Adherence"},{"issue":"4","key":"R33","doi-asserted-by":"publisher","DOI":"10.2196\/17883","article-title":"Habit strength, medication adherence, and habit-based mobile health interventions across chronic medical conditions: systematic review","volume":"22","author":"Badawy","journal-title":"J Med Internet Res"},{"issue":"2","key":"R34","doi-asserted-by":"publisher","DOI":"10.1111\/nhs.70153","article-title":"Barriers and facilitators to medication adherence among individuals with mental disorders: a qualitative systematic review and evidence synthesis","volume":"27","author":"Issac","journal-title":"Nurs Health Sci"},{"issue":"2","key":"R35","doi-asserted-by":"publisher","first-page":"160","DOI":"10.1177\/109019817800600107","article-title":"Development of the Multidimensional Health Locus of Control (MHLC) Scales","volume":"6","author":"Wallston","journal-title":"Health Educ Monogr"},{"key":"R36","doi-asserted-by":"publisher","DOI":"10.1016\/j.ypmed.2016.07.027","article-title":"Health professional advice, use of medications and smoking cessation: a population-based prospective cohort study","volume":"91","author":"Zhang","journal-title":"Prev Med"},{"issue":"2","key":"R37","doi-asserted-by":"publisher","first-page":"249","DOI":"10.1037\/0033-2909.132.2.249","article-title":"Does changing behavioral intentions engender behavior change? A meta-analysis of the experimental evidence","volume":"132","author":"Webb","journal-title":"Psychol Bull"},{"key":"R38","unstructured":"Marcus SC . Antidepressant adherence for depressed adults in primary care. ClinicalTrials.gov. URL: https:\/\/www.clinicaltrials.gov\/study\/NCT06496646 [Accessed 08-07-2026]"},{"key":"R39","doi-asserted-by":"publisher","DOI":"10.2196\/49024","article-title":"Cross-cutting mHealth behavior change techniques to support treatment adherence and self-management of complex medical conditions: systematic review","volume":"12","author":"Eaton","journal-title":"JMIR Mhealth Uhealth"}],"container-title":["Journal of Medical Internet Research"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.jmir.org\/2026\/1\/e86605","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,31]],"date-time":"2026-07-31T22:25:27Z","timestamp":1785536727000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.jmir.org\/2026\/1\/e86605"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,23]]},"references-count":39,"URL":"https:\/\/doi.org\/10.2196\/86605","relation":{},"ISSN":["1438-8871"],"issn-type":[{"value":"1438-8871","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,23]]},"article-number":"v28i3e86605"}}