Assessing Medical Accuracy of AI-Generated GERD Educational Social Media Posts.

Assessing Medical Accuracy of AI-Generated GERD Educational Social Media Posts. | Research Square window.SnipcartSettings = { analytics: { enabled: false } }; (function() { var accessVector = localStorage.getItem('access_vector') || ''; window.dataLayer = window.dataLayer || []; if (accessVector) { window.dataLayer.push({ user: { profile: { profileInfo: { snid: accessVector } } } }); } })(); (function(w,d,s,l,i){w[l]=w[l]||[];w[l].push({'gtm.start':new Date().getTime(),event:'gtm.js'});var f=d.getElementsByTagName(s)[0],j=d.createElement(s),dl=l!='dataLayer'?'&l='+l:'';j.async=true;j.src='https://www.googletagmanager.com/gtm.js?id='+i+dl;f.parentNode.insertBefore(j,f);})(window,document,'script','dataLayer','GTM-K279D39R'); Browse Preprints In Review Journals COVID-19 Preprints AJE Video Bytes Research Tools Research Promotion AJE Professional Editing AJE Rubriq About Preprint Platform In Review Editorial Policies Our Team Advisory Board Help Center Sign In Submit a Preprint Cite Share Download PDF Short Report Assessing Medical Accuracy of AI-Generated GERD Educational Social Media Posts. Akash Patel This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-3907046/v1 This work is licensed under a CC BY 4.0 License Status: Posted Version 1 posted You are reading this latest preprint version Abstract Background Gastroesophageal Reflux Disease (GERD) is a prevalent condition requiring effective patient education for management. With the advent of Artificial Intelligence (AI), tools like predis.ai are emerging as novel mediums for disseminating health information. This study evaluates the medical accuracy and guideline adherence of AI-generated social media content for GERD patient education compared to the American Gastroenterological Association (AGA) online material. Methods Social media posts were generated using predis.ai with inputs related to GERD patient education. The resulting content was critically analysed for its medical accuracy and alignment with the AGA's online patient education material. Key areas of evaluation included dietary advice, lifestyle changes, and general health tips for managing GERD. Results The AI-generated posts aligned with AGA material in advocating smaller, frequent meals, avoidance of trigger foods, and postural recommendations. However, they lacked comprehensive dietary guidelines, such as the Mediterranean diet, and omitted advice on sugar and fat intake, alcohol consumption, and the benefits of physical activity. Conclusion AI-generated social media content can serve as an adjunct in disseminating health information for GERD. However, healthcare professionals should verify the content's completeness and accuracy before endorsing it as a standalone educational resource. GERD patient education artificial intelligence social media health communication guideline adherence Figures Figure 1 Figure 2 Figure 3 Figure 4 Figure 5 Figure 6 Figure 7 INTRODUCTION Gastroesophageal Reflux Disease (GERD) is a common gastrointestinal disorder that affects a significant portion of the population worldwide.( 1 ) It is characterized by recurrent reflux of stomach contents into the esophagus, it presents with symptoms such as heartburn and acid regurgitation.( 2 ) The management of GERD often involves lifestyle modifications and patient education is crucial in this regard.( 3 ) In the digital age, the proliferation of Artificial Intelligence (AI) has revolutionized the dissemination of health information.( 4 ) AI tools, particularly those designed for creating content on social media platforms, have the potential to reach wide audiences with educational material.( 5 ) Predis.ai is one such free tool that has been designed to generate informative content for patient education. However, the medical accuracy and adherence of AI-generated content to established guidelines remain a significant concern.( 6 ) The American Gastroenterological Association (AGA) provides comprehensive online materials that serve as a benchmark for patient education in GERD. These materials offer evidence-based recommendations on diet, lifestyle changes, and other interventions that can mitigate the symptoms and improve the quality of life for GERD patients.( 7 ) This study aims to evaluate the efficacy of AI-generated social media content in conveying accurate and guideline-aligned patient education by comparing it to the AGA's online material. By analysing the content created by predis.ai, we aim to understand the potential of AI as a tool for public health communication and patient education. The outcome of this study is expected to contribute to the discourse on the use of AI in healthcare and inform strategies for integrating technology with traditional patient education methods to enhance the management of GERD and potentially other chronic conditions. METHODS Study Design: This research was conducted as a qualitative study to evaluate the effectiveness of AI-generated social media posts in patient education for Gastroesophageal Reflux Disease (GERD). The primary objective was to assess the medical accuracy and guideline alignment of content created by the AI tool predis.ai. Data Collection: The AI tool predis.ai was utilized to generate social media posts. The process involved selecting the "text to post" feature with a focus on "tips and tricks" for patient education about GERD. The input phrase used was "Patient education for GERD." The tool was set to generate content in a carousel format, which allows for a series of posts on the same topic. Comparison with Guidelines: The content generated by predis.ai was compared with the American Gastroenterology Association (AGA) patient education material to ensure alignment with established medical society recommendations. The AGA material is widely recognized and adheres to current clinical guidelines, serving as a benchmark for accurate and reliable patient information on GERD. Analysis: The analysis was conducted independently by the author. Each AI-generated post was examined for its medical accuracy, relevance, and alignment with the ACG guidelines. The evaluation criteria included the correctness of information, clarity of presentation, and the practical utility of the tips and tricks offered in the context of patient education for GERD. Ethical Considerations: Since the study involved the analysis of publicly available data and did not include human subjects, institutional review board approval was not required. Data Reporting: The findings are reported in a descriptive manner. Visual representations of the AI-generated posts are provided to support the analysis. These images serve as a direct comparison between the AI-generated content and the ACG patient education guidelines. RESULTS Overview of AI-Generated Content: The AI-generated posts provide a series of seven tips aimed at reducing symptoms of GERD. These posts encompass recommendations on lifestyle modifications including dietary habits, postural guidance, and other health-related advice. Comparison with AGA Patient Education Material: A detailed comparison of the AI-generated content with AGA material revealed a strong alignment in several areas, with some notable exceptions and omissions. Alignment with AGA: Small and Frequent Meals: Both the AI-generated content and the AGA material recommend eating smaller, frequent meals (Figure 1). Dietary Recommendations: The avoidance of trigger foods such as those high in fat, caffeine, and certain spices is common advice in both sources (Figure 2). Posture: The guidance on maintaining an upright posture after eating is also a shared recommendation (Figure 3 and 4). Discrepancies and Omissions: Comprehensive Dietary Advice: While the AI content touches upon specific trigger foods and recommends smaller meals, it lacks the comprehensive approach seen in the AGA guidelines, which emphasize a balanced diet with specific proportions of food types and mention the Mediterranean diet as a beneficial approach for GERD patients. Sugar and Fat Intake: The AI posts do not address the reduction of added sugars or the detailed guidance on fat intake, which are significant aspects of the AGA recommendations. Physical Activity: There is no mention of physical activity in the AI-generated posts, whereas the AGA guidelines specifically recommend regular physical activity as part of GERD management. Additional Considerations: Caffeine and Alcohol: The AI posts recommend limiting caffeine, carbonated beverages intake (Figure 5), which aligns with the AGA's advice. However, the AI posts do not address alcohol consumption, which the AGA suggests limiting. Smoking Cessation: Both sources agree on the importance of quitting smoking to alleviate GERD symptoms (Figure 6). Bed Elevation and Clothing: The posts also suggest wearing loose clothing (Figure 7), which are practical tips supported by the AGA guidelines but not explicitly mentioned in their online material. DISCUSSION This study critically evaluated the content of social media posts generated by an AI tool against established patient education material provided online by the American Gastroenterological Association (AGA). The AI tool demonstrated the capacity to produce medically accurate information that aligns with several key recommendations from the AGA online material. The AI-generated content correctly emphasized the importance of meal size and frequency, avoidance of trigger foods, and the benefit of certain postural habits, which are consistent with recommendations for managing GERD symptoms.(8) The significance of these findings lies in the potential of AI tools to reinforce critical lifestyle modifications that can mitigate GERD symptoms, an aspect that should be highlighted in patient education strategies.(9) However, the AI posts did not encompass the breadth of the AGA online material. Notably, the AGA's emphasis on a balanced diet, particularly the Mediterranean diet, and the specifics regarding the management of sugar and fat intake were missing from the AI-generated advice. The absence of such details may limit the comprehensiveness of the patient education provided solely through the AI tool. The lack of information on alcohol consumption and physical activity in the AI posts warrants attention. These factors are integral to comprehensive GERD management.(10) The omission of specific dietary advice, such as the Mediterranean diet, which has been associated with a decreased risk of GERD symptoms, represents a missed opportunity for patient education.(11) Similarly, the benefits of physical activity, which the AGA online material suggests, were not communicated by the AI tool, potentially overlooking an important aspect of lifestyle modification.(12) The AI tool’s ability to generate visually engaging and easily digestible content could be particularly effective for social media platforms, where brevity and appeal are essential for engagement. However, reliance on AI for patient education should be approached with caution due to the potential for incomplete information dissemination.(13, 14) It is crucial for healthcare providers to review AI-generated content and ensure it is supplemented with comprehensive, guideline-based information. The study did not assess the impact of AI-generated content on patient behavior or health outcomes, which represents a limitation. Future research should explore how patients interact with AI-generated health information and the effects on their health-related decisions and outcomes. Moreover, the iterative refinement of AI algorithms is necessary to enhance the breadth and depth of content so that it can more reliably mirror comprehensive guidelines like those provided by the AGA. CONCLUSION AI-generated social media posts can serve as an adjunct to traditional patient education methods, potentially increasing the reach and engagement of health education campaigns. However, they should not replace in-depth, personalized patient education provided by healthcare professionals. The role of AI in patient education should be to complement and augment, rather than substitute, the nuanced and comprehensive information provided by established medical guidelines and healthcare providers. Declarations ACKNOWLEDGEMENTS 1. Contributors: Akash Patel. 2. Funders: No funding received. 3. Prior presentations: Not presented to any conference. References El-Serag HB, Sweet S, Winchester CC, Dent J. Update on the epidemiology of gastro-oesophageal reflux disease: a systematic review. Gut. 2014 Jun;63(6):871-80. Antunes C, Aleem A, Curtis SA. Gastroesophageal Reflux Disease. StatPearls. Treasure Island (FL): StatPearls Publishing Copyright © 2024, StatPearls Publishing LLC.; 2024. Ness-Jensen E, Hveem K, El-Serag H, Lagergren J. Lifestyle Intervention in Gastroesophageal Reflux Disease. Clin Gastroenterol Hepatol. 2016 Feb;14(2):175-82.e1-3. Alowais SA, Alghamdi SS, Alsuhebany N, et al. Revolutionizing healthcare: the role of artificial intelligence in clinical practice. BMC Med Educ. 2023 Sep 22;23(1):689. Leung R. Using AI-ML to Augment the Capabilities of Social Media for Telehealth and Remote Patient Monitoring. Healthcare (Basel). 2023 Jun 10;11(12). Homolak J. Opportunities and risks of ChatGPT in medicine, science, and academic publishing: a modern Promethean dilemma. Croat Med J. 2023 Feb 28;64(1):1-3. Association AG. Obesity: GERD and lifestyle changes – Healthy habits for weight management. [cited 2022]; Available from: https://patient.gastro.org/gerd-and-lifestyle-changes/#:~:text=High%2Dfat%20foods%2C%20even%20healthy,)%2C%20and%20eat%20smaller%20portions. Katz PO, Dunbar KB, Schnoll-Sussman FH, Greer KB, Yadlapati R, Spechler SJ. ACG Clinical Guideline for the Diagnosis and Management of Gastroesophageal Reflux Disease. Am J Gastroenterol. 2022 Jan 1;117(1):27-56. Oh YJ, Zhang J, Fang ML, Fukuoka Y. A systematic review of artificial intelligence chatbots for promoting physical activity, healthy diet, and weight loss. Int J Behav Nutr Phys Act. 2021 Dec 11;18(1):160. Chen SH, Wang JW, Li YM. Is alcohol consumption associated with gastroesophageal reflux disease? J Zhejiang Univ Sci B. 2010 Jun;11(6):423-8. Heidarzadeh-Esfahani N, Soleimani D, Hajiahmadi S, Moradi S, Heidarzadeh N, Nachvak SM. Dietary Intake in Relation to the Risk of Reflux Disease: A Systematic Review. Prev Nutr Food Sci. 2021 Dec 31;26(4):367-79. Lam S, Hart AR. Does physical activity protect against the development of gastroesophageal reflux disease, Barrett's esophagus, and esophageal adenocarcinoma? A review of the literature with a meta-analysis. Dis Esophagus. 2017 Nov 1;30(11):1-10. Semrl N, Feigl S, Taumberger N, et al. AI language models in human reproduction research: exploring ChatGPT's potential to assist academic writing. Hum Reprod. 2023 Dec 4;38(12):2281-8. Bouhouita-Guermech S, Gogognon P, Bélisle-Pipon JC. Specific challenges posed by artificial intelligence in research ethics. Front Artif Intell. 2023;6:1149082. Additional Declarations The authors declare no competing interests. Cite Share Download PDF Status: Posted Version 1 posted You are reading this latest preprint version Research Square lets you share your work early, gain feedback from the community, and start making changes to your manuscript prior to peer review in a journal. As a division of Research Square Company, we’re committed to making research communication faster, fairer, and more useful. We do this by developing innovative software and high quality services for the global research community. Our growing team is made up of researchers and industry professionals working together to solve the most critical problems facing scientific publishing. Also discoverable on Platform About Our Team In Review Editorial Policies Advisory Board Help Center Resources Author Services Accessibility API Access RSS feed Manage Cookie Preferences © Research Square 2026 | ISSN 2693-5015 (online) Privacy Policy Terms of Service Do Not Sell My Personal Information {"props":{"pageProps":{"initialData":{"identity":"rs-3907046","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Short Report","associatedPublications":[],"authors":[{"id":269759046,"identity":"a7dcc252-ecf8-4cbc-9c78-f795774d78ca","order_by":0,"name":"Akash Patel","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA7ElEQVRIiWNgGAWjYDACHgYGZgaD//X87M0HgFwJGSK1FDAnSPYcSwBp4SFSywfmBIMbPgZQPgHA33P48ecCA7Y8gxs8n1/dqLHgYWA/fHQDPi0SZ9vMpGcY8BRL3u7dZp1zDOgwnrS0G3itOc9gxsxjIMHYd+fsNuMcNqAWCR4zvFrkz7N//sxjYMDYcCPnmXHOPyK0GJztMZDmMUhInHAjh/lxbhsRWgzPnCkDajlgDAxkM+bcPgkeNkJ+kTuTvvkzz58DcsCofPw551sdkHH4GH7vIwE2CTBJrHIQYP5AiupRMApGwSgYOQAAbSFIcaLKKwYAAAAASUVORK5CYII=","orcid":"","institution":"Eisenhower Medical Center","correspondingAuthor":true,"prefix":"","firstName":"Akash","middleName":"","lastName":"Patel","suffix":""}],"badges":[],"createdAt":"2024-01-28 22:27:57","currentVersionCode":1,"declarations":{"humanSubjects":false,"vertebrateSubjects":false,"conflictsOfInterestStatement":false,"humanSubjectEthicalGuidelines":false,"humanSubjectConsent":false,"humanSubjectClinicalTrial":false,"humanSubjectCaseReport":false,"vertebrateSubjectEthicalGuidelines":false},"doi":"10.21203/rs.3.rs-3907046/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-3907046/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":50384544,"identity":"7464a6d5-cda5-4edf-a966-aa3af100dd43","added_by":"auto","created_at":"2024-01-30 17:31:02","extension":"png","order_by":1,"title":"Figure 1","display":"","copyAsset":false,"role":"figure","size":316317,"visible":true,"origin":"","legend":"\u003cp\u003eAI-generated advice on meal size, consistent with AGA.\u003c/p\u003e\n\u003cp\u003eAbbreviations: AI: Artificial intelligence, AGA: American Gastroenterological Associations.\u003c/p\u003e","description":"","filename":"floatimage1.png","url":"https://assets-eu.researchsquare.com/files/rs-3907046/v1/245bb0a5d5a6f4f53496c19d.png"},{"id":50383118,"identity":"0485720c-1fc1-4d4f-ad09-6f2d14f4d1a3","added_by":"auto","created_at":"2024-01-30 17:23:02","extension":"png","order_by":2,"title":"Figure 2","display":"","copyAsset":false,"role":"figure","size":373276,"visible":true,"origin":"","legend":"\u003cp\u003eAI-post on dietary adjustments mirroring AGA material.\u003c/p\u003e\n\u003cp\u003eAbbreviations: AI: Artificial intelligence, AGA: American Gastroenterological Associations.\u003c/p\u003e","description":"","filename":"floatimage2.png","url":"https://assets-eu.researchsquare.com/files/rs-3907046/v1/4f7e5b2328c2009c6bf4ed10.png"},{"id":50383121,"identity":"e39e354a-1564-4992-95dc-c59b2ee458b3","added_by":"auto","created_at":"2024-01-30 17:23:02","extension":"png","order_by":3,"title":"Figure 3","display":"","copyAsset":false,"role":"figure","size":293936,"visible":true,"origin":"","legend":"\u003cp\u003ePostural advice on head of bed elevation from AI-content aligning with AGA.\u003c/p\u003e\n\u003cp\u003eAbbreviations: AI: Artificial intelligence, AGA: American Gastroenterological Associations.\u003c/p\u003e","description":"","filename":"floatimage3.png","url":"https://assets-eu.researchsquare.com/files/rs-3907046/v1/573ad3f2aea76c8147a2a83f.png"},{"id":50383120,"identity":"5cfb271a-3c37-4f64-a67a-7993116c72c0","added_by":"auto","created_at":"2024-01-30 17:23:02","extension":"png","order_by":4,"title":"Figure 4","display":"","copyAsset":false,"role":"figure","size":215563,"visible":true,"origin":"","legend":"\u003cp\u003ePostural advice on staying upright from AI-content aligning with AGA.\u003c/p\u003e\n\u003cp\u003eAbbreviations: AI: Artificial intelligence, AGA: American Gastroenterological Associations.\u003c/p\u003e","description":"","filename":"floatimage4.png","url":"https://assets-eu.researchsquare.com/files/rs-3907046/v1/78a36f608f45cc3b10bc6bdd.png"},{"id":50383124,"identity":"659a75d9-95be-4dd7-b76f-856a9c702a9d","added_by":"auto","created_at":"2024-01-30 17:23:02","extension":"png","order_by":5,"title":"Figure 5","display":"","copyAsset":false,"role":"figure","size":295972,"visible":true,"origin":"","legend":"\u003cp\u003eAdvice on limiting caffeine from AI-content aligning with AGA.\u003c/p\u003e\n\u003cp\u003eAbbreviations: AI: Artificial intelligence, AGA: American Gastroenterological Associations.\u003c/p\u003e","description":"","filename":"floatimage5.png","url":"https://assets-eu.researchsquare.com/files/rs-3907046/v1/83d8a70263afb2438f4b8ba2.png"},{"id":50384542,"identity":"951ee99b-f4c3-4438-8d1d-fdb7d4c27ee5","added_by":"auto","created_at":"2024-01-30 17:31:02","extension":"png","order_by":6,"title":"Figure 6","display":"","copyAsset":false,"role":"figure","size":257280,"visible":true,"origin":"","legend":"\u003cp\u003eAI-generated post advocating for smoking cessation in line with AGA.\u003c/p\u003e\n\u003cp\u003eAbbreviations: AI: Artificial intelligence, AGA: American Gastroenterological Associations.\u003c/p\u003e","description":"","filename":"floatimage6.png","url":"https://assets-eu.researchsquare.com/files/rs-3907046/v1/0990bf771e66340d41a79908.png"},{"id":50384543,"identity":"73512881-1c19-48ae-aed1-2a61d1b2c87f","added_by":"auto","created_at":"2024-01-30 17:31:02","extension":"png","order_by":7,"title":"Figure 7","display":"","copyAsset":false,"role":"figure","size":324972,"visible":true,"origin":"","legend":"\u003cp\u003eAI-generated post advocating for wearing loose clothing (not explicitly mentioned in AGA).\u003c/p\u003e\n\u003cp\u003eAbbreviations: AI: Artificial intelligence, AGA: American Gastroenterological Associations.\u003c/p\u003e","description":"","filename":"floatimage7.png","url":"https://assets-eu.researchsquare.com/files/rs-3907046/v1/89ec6a3e576c1ee493f9bc18.png"},{"id":50385872,"identity":"e5527e52-258a-4812-b14a-f2a297268d5e","added_by":"auto","created_at":"2024-01-30 17:39:03","extension":"pdf","order_by":0,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":2346834,"visible":true,"origin":"","legend":"","description":"","filename":"manuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-3907046/v1/06727624-da90-4440-a36c-d1c1505877ce.pdf"}],"financialInterests":"The authors declare no competing interests.","formattedTitle":"\u003cp\u003eAssessing Medical Accuracy of AI-Generated GERD Educational Social Media Posts.\u003c/p\u003e","fulltext":[{"header":"INTRODUCTION","content":"\u003cp\u003eGastroesophageal Reflux Disease (GERD) is a common gastrointestinal disorder that affects a significant portion of the population worldwide.(\u003cspan citationid=\"CR1\" class=\"CitationRef\"\u003e1\u003c/span\u003e) It is characterized by recurrent reflux of stomach contents into the esophagus, it presents with symptoms such as heartburn and acid regurgitation.(\u003cspan citationid=\"CR2\" class=\"CitationRef\"\u003e2\u003c/span\u003e) The management of GERD often involves lifestyle modifications and patient education is crucial in this regard.(\u003cspan citationid=\"CR3\" class=\"CitationRef\"\u003e3\u003c/span\u003e)\u003c/p\u003e \u003cp\u003eIn the digital age, the proliferation of Artificial Intelligence (AI) has revolutionized the dissemination of health information.(\u003cspan citationid=\"CR4\" class=\"CitationRef\"\u003e4\u003c/span\u003e) AI tools, particularly those designed for creating content on social media platforms, have the potential to reach wide audiences with educational material.(\u003cspan citationid=\"CR5\" class=\"CitationRef\"\u003e5\u003c/span\u003e) Predis.ai is one such free tool that has been designed to generate informative content for patient education. However, the medical accuracy and adherence of AI-generated content to established guidelines remain a significant concern.(\u003cspan citationid=\"CR6\" class=\"CitationRef\"\u003e6\u003c/span\u003e)\u003c/p\u003e \u003cp\u003eThe American Gastroenterological Association (AGA) provides comprehensive online materials that serve as a benchmark for patient education in GERD. These materials offer evidence-based recommendations on diet, lifestyle changes, and other interventions that can mitigate the symptoms and improve the quality of life for GERD patients.(\u003cspan citationid=\"CR7\" class=\"CitationRef\"\u003e7\u003c/span\u003e)\u003c/p\u003e \u003cp\u003eThis study aims to evaluate the efficacy of AI-generated social media content in conveying accurate and guideline-aligned patient education by comparing it to the AGA's online material. By analysing the content created by predis.ai, we aim to understand the potential of AI as a tool for public health communication and patient education.\u003c/p\u003e \u003cp\u003eThe outcome of this study is expected to contribute to the discourse on the use of AI in healthcare and inform strategies for integrating technology with traditional patient education methods to enhance the management of GERD and potentially other chronic conditions.\u003c/p\u003e"},{"header":"METHODS","content":"\u003cdiv id=\"Sec3\" class=\"Section2\"\u003e \u003ch2\u003eStudy Design:\u003c/h2\u003e \u003cp\u003eThis research was conducted as a qualitative study to evaluate the effectiveness of AI-generated social media posts in patient education for Gastroesophageal Reflux Disease (GERD). The primary objective was to assess the medical accuracy and guideline alignment of content created by the AI tool predis.ai.\u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec4\" class=\"Section2\"\u003e \u003ch2\u003eData Collection:\u003c/h2\u003e \u003cp\u003eThe AI tool predis.ai was utilized to generate social media posts. The process involved selecting the \"text to post\" feature with a focus on \"tips and tricks\" for patient education about GERD. The input phrase used was \"Patient education for GERD.\" The tool was set to generate content in a carousel format, which allows for a series of posts on the same topic.\u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec5\" class=\"Section2\"\u003e \u003ch2\u003eComparison with Guidelines:\u003c/h2\u003e \u003cp\u003eThe content generated by predis.ai was compared with the American Gastroenterology Association (AGA) patient education material to ensure alignment with established medical society recommendations. The AGA material is widely recognized and adheres to current clinical guidelines, serving as a benchmark for accurate and reliable patient information on GERD.\u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec6\" class=\"Section2\"\u003e \u003ch2\u003eAnalysis:\u003c/h2\u003e \u003cp\u003eThe analysis was conducted independently by the author. Each AI-generated post was examined for its medical accuracy, relevance, and alignment with the ACG guidelines. The evaluation criteria included the correctness of information, clarity of presentation, and the practical utility of the tips and tricks offered in the context of patient education for GERD.\u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec7\" class=\"Section2\"\u003e \u003ch2\u003eEthical Considerations:\u003c/h2\u003e \u003cp\u003eSince the study involved the analysis of publicly available data and did not include human subjects, institutional review board approval was not required.\u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec8\" class=\"Section2\"\u003e \u003ch2\u003eData Reporting:\u003c/h2\u003e \u003cp\u003eThe findings are reported in a descriptive manner. Visual representations of the AI-generated posts are provided to support the analysis. These images serve as a direct comparison between the AI-generated content and the ACG patient education guidelines.\u003c/p\u003e \u003c/div\u003e"},{"header":"RESULTS","content":"\u003cdiv id=\"Sec10\" class=\"Section2\"\u003e\n \u003ch2\u003eOverview of AI-Generated Content:\u003c/h2\u003e\n \u003cp\u003eThe AI-generated posts provide a series of seven tips aimed at reducing symptoms of GERD. These posts encompass recommendations on lifestyle modifications including dietary habits, postural guidance, and other health-related advice.\u003c/p\u003e\n\u003c/div\u003e\n\u003cdiv id=\"Sec11\" class=\"Section2\"\u003e\n \u003ch2\u003eComparison with AGA Patient Education Material:\u003c/h2\u003e\n \u003cp\u003eA detailed comparison of the AI-generated content with AGA material revealed a strong alignment in several areas, with some notable exceptions and omissions.\u003c/p\u003e\n\u003c/div\u003e\n\u003cdiv id=\"Sec12\" class=\"Section2\"\u003e\n \u003ch2\u003eAlignment with AGA:\u003c/h2\u003e\n \u003cp\u003e\u003cem\u003eSmall and Frequent Meals:\u003c/em\u003e Both the AI-generated content and the AGA material recommend eating smaller, frequent meals (Figure 1).\u003c/p\u003e\n \u003cp\u003e\u003cem\u003eDietary Recommendations:\u003c/em\u003e The avoidance of trigger foods such as those high in fat, caffeine, and certain spices is common advice in both sources (Figure 2).\u003c/p\u003e\n \u003cp\u003e\u003cem\u003ePosture:\u003c/em\u003e The guidance on maintaining an upright posture after eating is also a shared recommendation (Figure 3 and 4).\u003c/p\u003e\n \u003cp\u003e\u003cstrong\u003eDiscrepancies and Omissions:\u003c/strong\u003e\u003c/p\u003e\n \u003cp\u003e\u003cem\u003eComprehensive Dietary Advice:\u003c/em\u003e While the AI content touches upon specific trigger foods and recommends smaller meals, it lacks the comprehensive approach seen in the AGA guidelines, which emphasize a balanced diet with specific proportions of food types and mention the Mediterranean diet as a beneficial approach for GERD patients.\u003c/p\u003e\n \u003cp\u003e\u003cem\u003eSugar and Fat Intake:\u003c/em\u003e The AI posts do not address the reduction of added sugars or the detailed guidance on fat intake, which are significant aspects of the AGA recommendations.\u003c/p\u003e\n \u003cp\u003ePhysical Activity: There is no mention of physical activity in the AI-generated posts, whereas the AGA guidelines specifically recommend regular physical activity as part of GERD management.\u003c/p\u003e\n \u003cp\u003e\u003cstrong\u003eAdditional Considerations:\u003c/strong\u003e\u003c/p\u003e\n \u003cp\u003e\u003cem\u003eCaffeine and Alcohol:\u003c/em\u003e The AI posts recommend limiting caffeine, carbonated beverages intake (Figure 5), which aligns with the AGA\u0026apos;s advice. However, the AI posts do not address alcohol consumption, which the AGA suggests limiting.\u003c/p\u003e\n \u003cp\u003e\u003cem\u003eSmoking Cessation:\u003c/em\u003e Both sources agree on the importance of quitting smoking to alleviate GERD symptoms (Figure 6).\u003c/p\u003e\n \u003cp\u003e\u003cem\u003eBed Elevation and Clothing:\u003c/em\u003e The posts also suggest wearing loose clothing (Figure 7), which are practical tips supported by the AGA guidelines but not explicitly mentioned in their online material.\u003c/p\u003e\n\u003c/div\u003e"},{"header":"DISCUSSION","content":"\u003cp\u003eThis study critically evaluated the content of social media posts generated by an AI tool against established patient education material provided online by the American Gastroenterological Association (AGA). The AI tool demonstrated the capacity to produce medically accurate information that aligns with several key recommendations from the AGA online material.\u003c/p\u003e\n\u003cp\u003eThe AI-generated content correctly emphasized the importance of meal size and frequency, avoidance of trigger foods, and the benefit of certain postural habits, which are consistent with recommendations for managing GERD symptoms.(8) The significance of these findings lies in the potential of AI tools to reinforce critical lifestyle modifications that can mitigate GERD symptoms, an aspect that should be highlighted in patient education strategies.(9)\u003c/p\u003e\n\u003cp\u003eHowever, the AI posts did not encompass the breadth of the AGA online material. Notably, the AGA\u0026apos;s emphasis on a balanced diet, particularly the Mediterranean diet, and the specifics regarding the management of sugar and fat intake were missing from the AI-generated advice. The absence of such details may limit the comprehensiveness of the patient education provided solely through the AI tool.\u003c/p\u003e\n\u003cp\u003eThe lack of information on alcohol consumption and physical activity in the AI posts warrants attention. These factors are integral to comprehensive GERD management.(10) The omission of specific dietary advice, such as the Mediterranean diet, which has been associated with a decreased risk of GERD symptoms, represents a missed opportunity for patient education.(11) Similarly, the benefits of physical activity, which the AGA online material suggests, were not communicated by the AI tool, potentially overlooking an important aspect of lifestyle modification.(12)\u003c/p\u003e\n\u003cp\u003eThe AI tool\u0026rsquo;s ability to generate visually engaging and easily digestible content could be particularly effective for social media platforms, where brevity and appeal are essential for engagement. However, reliance on AI for patient education should be approached with caution due to the potential for incomplete information dissemination.(13, 14) It is crucial for healthcare providers to review AI-generated content and ensure it is supplemented with comprehensive, guideline-based information.\u003c/p\u003e\n\u003cp\u003eThe study did not assess the impact of AI-generated content on patient behavior or health outcomes, which represents a limitation. Future research should explore how patients interact with AI-generated health information and the effects on their health-related decisions and outcomes. Moreover, the iterative refinement of AI algorithms is necessary to enhance the breadth and depth of content so that it can more reliably mirror comprehensive guidelines like those provided by the AGA.\u003c/p\u003e"},{"header":"CONCLUSION","content":"\u003cp\u003eAI-generated social media posts can serve as an adjunct to traditional patient education methods, potentially increasing the reach and engagement of health education campaigns. However, they should not replace in-depth, personalized patient education provided by healthcare professionals. The role of AI in patient education should be to complement and augment, rather than substitute, the nuanced and comprehensive information provided by established medical guidelines and healthcare providers.\u003c/p\u003e"},{"header":"Declarations","content":"\u003cp\u003e\u003cstrong\u003eACKNOWLEDGEMENTS\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003e1. Contributors: Akash Patel.\u003c/p\u003e\n\u003cp\u003e2. Funders: No funding received.\u003c/p\u003e\n\u003cp\u003e3. Prior presentations: Not presented to any conference.\u003c/p\u003e"},{"header":"References","content":"\u003col\u003e\n\u003cli\u003eEl-Serag HB, Sweet S, Winchester CC, Dent J. Update on the epidemiology of gastro-oesophageal reflux disease: a systematic review. Gut. 2014 Jun;63(6):871-80.\u003c/li\u003e\n\u003cli\u003eAntunes C, Aleem A, Curtis SA. Gastroesophageal Reflux Disease. StatPearls. Treasure Island (FL): StatPearls Publishing Copyright \u0026copy; 2024, StatPearls Publishing LLC.; 2024.\u003c/li\u003e\n\u003cli\u003eNess-Jensen E, Hveem K, El-Serag H, Lagergren J. Lifestyle Intervention in Gastroesophageal Reflux Disease. Clin Gastroenterol Hepatol. 2016 Feb;14(2):175-82.e1-3.\u003c/li\u003e\n\u003cli\u003eAlowais SA, Alghamdi SS, Alsuhebany N, et al. Revolutionizing healthcare: the role of artificial intelligence in clinical practice. BMC Med Educ. 2023 Sep 22;23(1):689.\u003c/li\u003e\n\u003cli\u003eLeung R. Using AI-ML to Augment the Capabilities of Social Media for Telehealth and Remote Patient Monitoring. Healthcare (Basel). 2023 Jun 10;11(12).\u003c/li\u003e\n\u003cli\u003eHomolak J. Opportunities and risks of ChatGPT in medicine, science, and academic publishing: a modern Promethean dilemma. Croat Med J. 2023 Feb 28;64(1):1-3.\u003c/li\u003e\n\u003cli\u003eAssociation AG. Obesity: GERD and lifestyle changes \u0026ndash; Healthy habits for weight management. [cited 2022]; Available from: https://patient.gastro.org/gerd-and-lifestyle-changes/#:~:text=High%2Dfat%20foods%2C%20even%20healthy,)%2C%20and%20eat%20smaller%20portions.\u003c/li\u003e\n\u003cli\u003eKatz PO, Dunbar KB, Schnoll-Sussman FH, Greer KB, Yadlapati R, Spechler SJ. ACG Clinical Guideline for the Diagnosis and Management of Gastroesophageal Reflux Disease. Am J Gastroenterol. 2022 Jan 1;117(1):27-56.\u003c/li\u003e\n\u003cli\u003eOh YJ, Zhang J, Fang ML, Fukuoka Y. A systematic review of artificial intelligence chatbots for promoting physical activity, healthy diet, and weight loss. Int J Behav Nutr Phys Act. 2021 Dec 11;18(1):160.\u003c/li\u003e\n\u003cli\u003eChen SH, Wang JW, Li YM. Is alcohol consumption associated with gastroesophageal reflux disease? J Zhejiang Univ Sci B. 2010 Jun;11(6):423-8.\u003c/li\u003e\n\u003cli\u003eHeidarzadeh-Esfahani N, Soleimani D, Hajiahmadi S, Moradi S, Heidarzadeh N, Nachvak SM. Dietary Intake in Relation to the Risk of Reflux Disease: A Systematic Review. Prev Nutr Food Sci. 2021 Dec 31;26(4):367-79.\u003c/li\u003e\n\u003cli\u003eLam S, Hart AR. Does physical activity protect against the development of gastroesophageal reflux disease, Barrett\u0026apos;s esophagus, and esophageal adenocarcinoma? A review of the literature with a meta-analysis. Dis Esophagus. 2017 Nov 1;30(11):1-10.\u003c/li\u003e\n\u003cli\u003eSemrl N, Feigl S, Taumberger N, et al. AI language models in human reproduction research: exploring ChatGPT\u0026apos;s potential to assist academic writing. Hum Reprod. 2023 Dec 4;38(12):2281-8.\u003c/li\u003e\n\u003cli\u003eBouhouita-Guermech S, Gogognon P, B\u0026eacute;lisle-Pipon JC. Specific challenges posed by artificial intelligence in research ethics. Front Artif Intell. 2023;6:1149082.\u003c/li\u003e\n\u003c/ol\u003e"}],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":true,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"hideJournal":true,"highlight":"","institution":"Eisenhower Medical Center","isAcceptedByJournal":false,"isAuthorSuppliedPdf":false,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":false,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true},"keywords":"GERD, patient education, artificial intelligence, social media, health communication, guideline adherence","lastPublishedDoi":"10.21203/rs.3.rs-3907046/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-3907046/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003ch2\u003eBackground\u003c/h2\u003e \u003cp\u003eGastroesophageal Reflux Disease (GERD) is a prevalent condition requiring effective patient education for management. With the advent of Artificial Intelligence (AI), tools like predis.ai are emerging as novel mediums for disseminating health information. This study evaluates the medical accuracy and guideline adherence of AI-generated social media content for GERD patient education compared to the American Gastroenterological Association (AGA) online material.\u003c/p\u003e\u003ch2\u003eMethods\u003c/h2\u003e \u003cp\u003eSocial media posts were generated using predis.ai with inputs related to GERD patient education. The resulting content was critically analysed for its medical accuracy and alignment with the AGA's online patient education material. Key areas of evaluation included dietary advice, lifestyle changes, and general health tips for managing GERD.\u003c/p\u003e\u003ch2\u003eResults\u003c/h2\u003e \u003cp\u003eThe AI-generated posts aligned with AGA material in advocating smaller, frequent meals, avoidance of trigger foods, and postural recommendations. However, they lacked comprehensive dietary guidelines, such as the Mediterranean diet, and omitted advice on sugar and fat intake, alcohol consumption, and the benefits of physical activity.\u003c/p\u003e\u003ch2\u003eConclusion\u003c/h2\u003e \u003cp\u003eAI-generated social media content can serve as an adjunct in disseminating health information for GERD. However, healthcare professionals should verify the content's completeness and accuracy before endorsing it as a standalone educational resource.\u003c/p\u003e","manuscriptTitle":"Assessing Medical Accuracy of AI-Generated GERD Educational Social Media Posts.","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-01-30 17:22:57","doi":"10.21203/rs.3.rs-3907046/v1","editorialEvents":[{"type":"communityComments","content":0}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"004ea7b4-11e6-42e4-b824-79c746997e7d","owner":[],"postedDate":"January 30th, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2024-01-30T17:22:58+00:00","versionOfRecord":[],"versionCreatedAt":"2024-01-30 17:22:57","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-3907046","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-3907046","identity":"rs-3907046","version":["v1"]},"buildId":"qtupq5eGEP_6zYnWcrvyt","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}