Pharm-AI: An Intelligent Chatbot for Addressing Medication Accessibility and Information Challenges During the COVID-19 Pandemic | 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 Research Article Pharm-AI: An Intelligent Chatbot for Addressing Medication Accessibility and Information Challenges During the COVID-19 Pandemic HARSINI NATARAJAN, KARTHIK THIYAGARAJAN This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-6252024/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 The COVID-19 pandemic was the cause of the shortage of medicines, the spread of misinformation and the creation of obstacles to the accessibility of the health care system. Therefore, patients got a lot of fake claims about drug interactions, side effects, and availability. For the purposes of addressing these issues, Pharm-AI, an AI-powered chatbot, has been invented to give the patients the right and real-time information about the medicines they need, to help them find the nearest pharmacies, and to clarify any medication-related questions. Pharm-AI uses natural language processing with geolocation mapping to improve healthcare accessibility and decision-making. It uses data from very reliable sources such as PubMed, Scopus, Drug Central, and clinical trials to give evidence-based responses and thus to lower misinformation risks.Some preliminary analyses have demonstrated that Pharm-AI is a very successful tool in the fight against information overload that allows users to get sound drug-related insights very quickly. Its geolocation element provides the data needed to identify the pharmacies where the medicine is available. This results in a 65% decrease in the time needed to locate medications as compared to manual searches. Moreover, Pharm-AI helps people save money especially in the low-income regions by comparing the prices of generic and branded drugs and so, it stimulates the transparency of the costs. One of the weaknesses for example is the platform might have to depend on third party pharmaceutical companies’ inventories and the use of certain languages in regional dialects which are affective limitations. The new solutions will involve using optical character recognition (OCR) for prescription analysis, multilingual support, and affiliating with online pharmacies for automated medication delivery. Pharm-AI is a step forward in the development of AI-driven healthcare solutions, so it is going to make the health care system better and the information about the drugs more reliable. Artificial Intelligence and Machine Learning AI chatbot medication information geolocation mapping healthcare accessibility drug price comparison Figures Figure 1 Figure 2 Figure 3 Figure 4 Full Text 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-6252024","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":430415843,"identity":"30a7055d-a848-453c-9ac4-b10dab076c2e","order_by":0,"name":"HARSINI NATARAJAN","email":"","orcid":"https://orcid.org/0009-0001-8231-0920","institution":"Sri Ramachandra Institute of Higher Education and Research","correspondingAuthor":false,"prefix":"","firstName":"HARSINI","middleName":"","lastName":"NATARAJAN","suffix":""},{"id":430415844,"identity":"5d4983f6-82fa-4743-94d9-4332816f9ee9","order_by":1,"name":"KARTHIK THIYAGARAJAN","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAABDUlEQVRIiWNgGAWjYDACCQZmEJXAxsMG5suBiAMP8OjggWgxgGsxBmtJIEYLA1RLYgPYUjxa7KWbDxv83PMnj4/nWOJjnpo76fPDDj8E2mInp9uAwxaZY8mJPc8Mitl42w4b8xx7lrvxdpoBUEuysdkBXA7LMT7Ac8AgsY2fvU2ah+1w7sbZCSAtBxK34dSS//ngH4iW9t88/w6nG85O/0BASw5zMtgW3rZjzEDHJchL5xCw5UaasbHMAePENp5jyZJz+w4bbpDOKTiQYIDbL+wzkh9Lvjkglzi/J83ww5tvh+XlZ6dv/vChwk4OlxYUwMQDJAzAKg2IUA4CjD+AhHwDkapHwSgYBaNgxAAAorhiCpZU4BMAAAAASUVORK5CYII=","orcid":"https://orcid.org/0009-0002-6603-1347","institution":"Sri Ramachandra Institute of Higher Education and Research","correspondingAuthor":true,"prefix":"","firstName":"KARTHIK","middleName":"","lastName":"THIYAGARAJAN","suffix":""}],"badges":[],"createdAt":"2025-03-18 10:16:43","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-6252024/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-6252024/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":79067146,"identity":"fbca198c-b2c7-4384-bb71-3db4ed0fc1dd","added_by":"auto","created_at":"2025-03-24 04:44:24","extension":"png","order_by":1,"title":"Figure 1","display":"","copyAsset":false,"role":"figure","size":228383,"visible":true,"origin":"","legend":"\u003cp\u003eArchitecture of the Chatbot\u003c/p\u003e","description":"","filename":"project.png","url":"https://assets-eu.researchsquare.com/files/rs-6252024/v1/7deb032b0c5bcd5d3a87cff0.png"},{"id":79067257,"identity":"257b7168-81cb-438a-a686-d631a7b1ba36","added_by":"auto","created_at":"2025-03-24 04:52:24","extension":"png","order_by":2,"title":"Figure 2","display":"","copyAsset":false,"role":"figure","size":193052,"visible":true,"origin":"","legend":"\u003cp\u003eLocation Feature Example\u003c/p\u003e","description":"","filename":"Picture1.png","url":"https://assets-eu.researchsquare.com/files/rs-6252024/v1/86caae27287649aa22a7786c.png"},{"id":79067147,"identity":"ce10d56a-9bb8-40b9-b5c7-c8cec308e8df","added_by":"auto","created_at":"2025-03-24 04:44:24","extension":"png","order_by":3,"title":"Figure 3","display":"","copyAsset":false,"role":"figure","size":163187,"visible":true,"origin":"","legend":"\u003cp\u003eSide Effects Example\u003c/p\u003e","description":"","filename":"Picture2.png","url":"https://assets-eu.researchsquare.com/files/rs-6252024/v1/15b5d1137a5ce1a28f8854be.png"},{"id":79067149,"identity":"2a78bd66-ec7e-4325-8a7b-de9fc42ff20a","added_by":"auto","created_at":"2025-03-24 04:44:24","extension":"png","order_by":4,"title":"Figure 4","display":"","copyAsset":false,"role":"figure","size":270113,"visible":true,"origin":"","legend":"\u003cp\u003eDrug information Example\u003c/p\u003e","description":"","filename":"Picture4.png","url":"https://assets-eu.researchsquare.com/files/rs-6252024/v1/e17adcbbd9637947ee3a1fc8.png"},{"id":79067643,"identity":"f26eff09-6646-4e7b-ba62-fd4e17130635","added_by":"auto","created_at":"2025-03-24 05:00:26","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":451225,"visible":true,"origin":"","legend":"","description":"","filename":"Pharmaimanuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-6252024/v1_covered_e7a6eb3e-7959-4acc-842e-2a7a84af4e4b.pdf"}],"financialInterests":"The authors declare no competing interests.","formattedTitle":"\u003cp\u003e\u003cstrong\u003ePharm-AI: An Intelligent Chatbot for Addressing Medication Accessibility and Information Challenges During the COVID-19 Pandemic\u003c/strong\u003e\u003c/p\u003e","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"hideJournal":true,"highlight":"","institution":"Sri Ramachandra Institute of Higher Education and Research","isAcceptedByJournal":false,"isAuthorSuppliedPdf":true,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":true,"isPdf":true,"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":"AI chatbot, medication information, geolocation mapping, healthcare accessibility, drug price comparison","lastPublishedDoi":"10.21203/rs.3.rs-6252024/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-6252024/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eThe COVID-19 pandemic was the cause of the shortage of medicines, the spread of misinformation and the creation of obstacles to the accessibility of the health care system. Therefore, patients got a lot of fake claims about drug interactions, side effects, and availability. For the purposes of addressing these issues, Pharm-AI, an AI-powered chatbot, has been invented to give the patients the right and real-time information about the medicines they need, to help them find the nearest pharmacies, and to clarify any medication-related questions. Pharm-AI uses natural language processing with geolocation mapping to improve healthcare accessibility and decision-making. It uses data from very reliable sources such as PubMed, Scopus, Drug Central, and clinical trials to give evidence-based responses and thus to lower misinformation risks.Some preliminary analyses have demonstrated that Pharm-AI is a very successful tool in the fight against information overload that allows users to get sound drug-related insights very quickly. Its geolocation element provides the data needed to identify the pharmacies where the medicine is available. This results in a 65% decrease in the time needed to locate medications as compared to manual searches. Moreover, Pharm-AI helps people save money especially in the low-income regions by comparing the prices of generic and branded drugs and so, it stimulates the transparency of the costs. One of the weaknesses for example is the platform might have to depend on third party pharmaceutical companies’ inventories and the use of certain languages in regional dialects which are affective limitations. The new solutions will involve using optical character recognition (OCR) for prescription analysis, multilingual support, and affiliating with online pharmacies for automated medication delivery. Pharm-AI is a step forward in the development of AI-driven healthcare solutions, so it is going to make the health care system better and the information about the drugs more reliable.\u003c/p\u003e","manuscriptTitle":"Pharm-AI: An Intelligent Chatbot for Addressing Medication Accessibility and Information Challenges During the COVID-19 Pandemic","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-03-24 04:44:19","doi":"10.21203/rs.3.rs-6252024/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":"c8fcf389-cd5c-486e-b3b7-b4fb110de685","owner":[],"postedDate":"March 24th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":45841269,"name":"Artificial Intelligence and Machine Learning"}],"tags":[],"updatedAt":"2025-03-24T04:44:19+00:00","versionOfRecord":[],"versionCreatedAt":"2025-03-24 04:44:19","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-6252024","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-6252024","identity":"rs-6252024","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}
Text is read by the "Ask this paper" AI Q&A widget below.
Extraction quality varies by source — PMC NXML preserves structure
cleanly, OA-HTML may include some navigation residue, and OA-PDF can
have broken hyphenation. The publisher copy
(via DOI)
is the canonical version.