ChestX-VQA: AI Tool for Multimodal Chest X-ray Analysis and Clinical QA

ChestX-VQA: AI Tool for Multimodal Chest X-ray Analysis and Clinical QA | 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 Article ChestX-VQA: AI Tool for Multimodal Chest X-ray Analysis and Clinical QA Charanpreet kaur, Nishtha Hooda This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7563215/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 Chest radiographs are an important aspect of medical diagnosis, but accurate interpretation often requires combining the image with relevant clinical context. This work presents a multimodal large language model (M-LLM)-based chatbot designed to perform visual question answering (VQA) by processing chest X-ray images and associated clinical text. The publicly available VQA-RAD dataset, which contains chest radiographs and corresponding question–answer pairs, is used for evaluation. The study conducts a comparative evaluation of GIT, CLIP, BLIP, FLAVA, and VLIT, focusing on overall BERTScore, readability, and response time. In addition to automatic metrics, a human assessment by medical practitioners is also carried out to evaluate the clinical relevance and accuracy of the responses. The integration of GIT and T5 yields the best performance with an overall BERTScore of 0.92. The chatbot enables users to upload chest radiographs along with clinical notes and receive clear,context-sensitive responses in the field of healthcare. Biological sciences/Computational biology and bioinformatics Health sciences/Health care Physical sciences/Mathematics and computing Health sciences/Medical research Full Text Additional Declarations No competing interests reported. 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-7563215","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":533485534,"identity":"a7b215fd-44f9-4e7b-827a-6d32dd578740","order_by":0,"name":"Charanpreet kaur","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA3klEQVRIiWNgGAWjYBACfoYDDAwJBhJy/MyMDQcgYowNeLVINh5gbHhQYGMs2QzUcoAYLQaHDzA2PviQlmgAUn6AKJcdO53+IMHgcILxcebGwx/bGOT5G5jbHuDTwdhzdmMDUEue2WGgww62MRjOOMDYboBPC7MEREsxTAvjBgbGNgl8Wtjk34K1JG5uhmixJ6iFhwFsS1riBmaIlkSCWiSAWmYkGNgYS4AcduacRPKMwwS02B84u+Hjjz/AqOw//vhDRZmNbX97+zO8WjBtZWAmRf0oGAWjYBSMAqwAACQVVYnOpr6BAAAAAElFTkSuQmCC","orcid":"","institution":"Indian Institute of Information Technology Una","correspondingAuthor":true,"prefix":"","firstName":"Charanpreet","middleName":"","lastName":"kaur","suffix":""},{"id":533485535,"identity":"1be88082-1d27-4282-a18f-08ee6213aa05","order_by":1,"name":"Nishtha Hooda","email":"","orcid":"","institution":"Indian Institute of Information Technology Una","correspondingAuthor":false,"prefix":"","firstName":"Nishtha","middleName":"","lastName":"Hooda","suffix":""}],"badges":[],"createdAt":"2025-09-08 10:38:38","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-7563215/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7563215/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":94227016,"identity":"26990651-a2dd-4c58-bf0b-6db8bb62f5da","added_by":"auto","created_at":"2025-10-23 20:02:01","extension":"json","order_by":0,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":3860,"visible":true,"origin":"","legend":"","description":"","filename":"eb5e872e226949c0855ca662fbcbe1c6.json","url":"https://assets-eu.researchsquare.com/files/rs-7563215/v1/41d88e728d7d7bd4e7aeafbd.json"},{"id":98436367,"identity":"7a2cc8ac-757a-483b-968c-2b5381de6d96","added_by":"auto","created_at":"2025-12-17 16:55:31","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":616185,"visible":true,"origin":"","legend":"","description":"","filename":"jppkcrfmdwpnffpgkjczhngydpgmgpmj.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7563215/v1_covered_2566e428-a3dd-4d99-9b0a-042151fa8cdf.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"ChestX-VQA: AI Tool for Multimodal Chest X-ray Analysis and Clinical QA","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":true,"highlight":"","institution":"","isAcceptedByJournal":false,"isAuthorSuppliedPdf":true,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"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":"","lastPublishedDoi":"10.21203/rs.3.rs-7563215/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7563215/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Chest radiographs are an important aspect of medical diagnosis, but accurate interpretation often requires combining the image with relevant clinical context. This work presents a multimodal large language model (M-LLM)-based chatbot designed to perform visual question answering (VQA) by processing chest X-ray images and associated clinical text. The publicly available VQA-RAD dataset, which contains chest radiographs and corresponding question–answer pairs, is used for evaluation. The study conducts a comparative evaluation of GIT, CLIP, BLIP, FLAVA, and VLIT, focusing on overall BERTScore, readability, and response time. In addition to automatic metrics, a human assessment by medical practitioners is also carried out to evaluate the clinical relevance and accuracy of the responses. The integration of GIT and T5 yields the best performance with an overall BERTScore of 0.92. The chatbot enables users to upload chest radiographs along with clinical notes and receive clear,context-sensitive responses in the field of healthcare.","manuscriptTitle":"ChestX-VQA: AI Tool for Multimodal Chest X-ray Analysis and Clinical QA","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-10-23 20:01:57","doi":"10.21203/rs.3.rs-7563215/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":"829c0239-658e-4e7f-81e2-ab4beba2ab6c","owner":[],"postedDate":"October 23rd, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":56720708,"name":"Biological sciences/Computational biology and bioinformatics"},{"id":56720709,"name":"Health sciences/Health care"},{"id":56720710,"name":"Physical sciences/Mathematics and computing"},{"id":56720711,"name":"Health sciences/Medical research"}],"tags":[],"updatedAt":"2025-12-16T14:39:35+00:00","versionOfRecord":[],"versionCreatedAt":"2025-10-23 20:01:57","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-7563215","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7563215","identity":"rs-7563215","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}