Dual-Model Collaboration with Consistency Calibration for Intelligent Acupuncture Prescription Recommendation

Dual-Model Collaboration with Consistency Calibration for Intelligent Acupuncture Prescription Recommendation | 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 Dual-Model Collaboration with Consistency Calibration for Intelligent Acupuncture Prescription Recommendation Yichu Xu, Xiaoqian Peng, Jing Wen, Xinyu Wang, Youbing Xia, Tiancheng Xu, and 2 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7677489/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 Acupuncture is a core therapeutic modality in traditional Chinese medicine (TCM), widely used for symptom relief and functional regulation, yet its clinical effectiveness relies heavily on individualized acupoint selection. To address the personalized requirements for selecting acupuncture points in TCM, this study investigates a dual-model collaboration strategy for intelligent acupuncture prescription recommendation. The aim is to provide auxiliary decision support for clinical acupuncture treatment. Methods A dual-model collaborative framework for intelligent acupuncture prescription recommendation is proposed. Specifically, symptom-to-acupoint mapping is formulated as an end-to-end text generation task and an intelligent recommendation method based on dual-model collaboration with consistency calibration(DM3C) is proposed. Firstly, a Chinese Bidirectional and Auto-Regressive Transformers(BART) model is fine-tuned on clinical symptom-acupoint pairs to generate baseline acupoint sequences. Then, a retrieval-augmented prompting strategy is used to query large language models (LLMs), producing additional candidate prescriptions from similar historical cases. Finally, a random forest-based consistency calibration module integrates multi-source signals to score and filter candidate acupoints, yielding a reliability-weighted final recommendation. Results Experimental results demonstrate that the DM3C significantly improves acupuncture prescription recommendation performance. When more prompts are retrieved (top-k = 21), the DeepSeek-V3-based collaborative achieves an F1 score of 0.3821, a Recall of 0.5216, and a Coverage of 0.3372, representing a 0.1062 increase in F1 over the original DeepSeek-V3 without model collaboration. The GPT-4o-based model attains an F1 score of 0.3780 and a Recall of 0.4833, with a 0.0169 improvement in Recall compared with its retrieval-enhanced counterpart. Conclusion By combining a domain-fine-tuned generator, retrieval-augmented LLM outputs, and a consistency-calibrated random forest filter, the proposed the DM3C enhances the generalizability and Recall of intelligent acupuncture prescription recommendations, providing effective support for clinical decision-making in TCM acupuncture treatment. Acupuncture Acupuncture prescription intelligent recommendation Large language model Text generation Dual-model collaboration with consistency calibration 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-7677489","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":583426188,"identity":"5929c26c-b636-4d39-9ee0-8ed9c22d67b8","order_by":0,"name":"Yichu Xu","email":"","orcid":"","institution":"Nanjing University of Chinese Medicine","correspondingAuthor":false,"prefix":"","firstName":"Yichu","middleName":"","lastName":"Xu","suffix":""},{"id":583426190,"identity":"fde28ec8-3216-447f-8b74-6354df1af4a2","order_by":1,"name":"Xiaoqian Peng","email":"","orcid":"","institution":"Nanjing University of Chinese Medicine","correspondingAuthor":false,"prefix":"","firstName":"Xiaoqian","middleName":"","lastName":"Peng","suffix":""},{"id":583426191,"identity":"e740ae4c-7bd1-4df2-b2f4-031ba976ff06","order_by":2,"name":"Jing Wen","email":"","orcid":"","institution":"Nanjing University of Chinese Medicine","correspondingAuthor":false,"prefix":"","firstName":"Jing","middleName":"","lastName":"Wen","suffix":""},{"id":583426192,"identity":"0b9c0e04-418e-44a6-a3bb-6e7817b4d573","order_by":3,"name":"Xinyu Wang","email":"","orcid":"","institution":"Nanjing University of Chinese Medicine","correspondingAuthor":false,"prefix":"","firstName":"Xinyu","middleName":"","lastName":"Wang","suffix":""},{"id":583426193,"identity":"ef7cb16a-bb35-4819-8c60-471272fa0d17","order_by":4,"name":"Youbing Xia","email":"","orcid":"","institution":"Nanjing University of Chinese Medicine","correspondingAuthor":false,"prefix":"","firstName":"Youbing","middleName":"","lastName":"Xia","suffix":""},{"id":583426198,"identity":"db49ac8c-85ac-4918-a9d7-384ae417c041","order_by":5,"name":"Tiancheng Xu","email":"","orcid":"","institution":"Nanjing University of Chinese Medicine","correspondingAuthor":false,"prefix":"","firstName":"Tiancheng","middleName":"","lastName":"Xu","suffix":""},{"id":583426200,"identity":"815bff04-11fe-4d9c-9abb-2ec92e9070c4","order_by":6,"name":"Tao Yang","email":"","orcid":"","institution":"Nanjing University of Chinese Medicine","correspondingAuthor":false,"prefix":"","firstName":"Tao","middleName":"","lastName":"Yang","suffix":""},{"id":583426201,"identity":"f26062b7-4263-4400-8711-b37ffb315007","order_by":7,"name":"Kongfa Hu","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAxUlEQVRIiWNgGAWjYBACCeYzDAwfGNggPB6itLDlMDDOIFkLM1wlUVok23iPSdvu4Evsn3aA8cHbNgZ5c0JapNn40qRzz7AlzridwGw4t43BcGcDAS1y8j1m0rltbIkbpBPYpHnbGBIMDhDSwsZjJm0J0cL+mygt0iAtjFBbmInSItnGY2zZ28ZmPON2YrPknHMShhsIaZE4xmN442fbMdn+2ckHP7wps5EnaAsUHANixgaQEcSpB4IaolWOglEwCkbBCAQALrk2FvwiQNQAAAAASUVORK5CYII=","orcid":"","institution":"Nanjing University of Chinese Medicine","correspondingAuthor":true,"prefix":"","firstName":"Kongfa","middleName":"","lastName":"Hu","suffix":""}],"badges":[],"createdAt":"2025-09-22 13:53:42","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-7677489/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7677489/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":102418258,"identity":"a723f00b-8c8b-4ba8-91d9-d1106df7c9a1","added_by":"auto","created_at":"2026-02-11 13:12:56","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1124657,"visible":true,"origin":"","legend":"","description":"","filename":"MultiModelCollaborationwithConsistencyCalibrationforIntelligentAcupuncturePrescriptionRecommendation.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7677489/v1_covered_394491e5-8f29-4194-9620-78abd285f69d.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Dual-Model Collaboration with Consistency Calibration for Intelligent Acupuncture Prescription Recommendation","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":"Acupuncture, Acupuncture prescription intelligent recommendation, Large language model, Text generation, Dual-model collaboration with consistency calibration","lastPublishedDoi":"10.21203/rs.3.rs-7677489/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7677489/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003ch2\u003eBackground\u003c/h2\u003e \u003cp\u003eAcupuncture is a core therapeutic modality in traditional Chinese medicine (TCM), widely used for symptom relief and functional regulation, yet its clinical effectiveness relies heavily on individualized acupoint selection. To address the personalized requirements for selecting acupuncture points in TCM, this study investigates a dual-model collaboration strategy for intelligent acupuncture prescription recommendation. The aim is to provide auxiliary decision support for clinical acupuncture treatment.\u003c/p\u003e\u003ch2\u003eMethods\u003c/h2\u003e \u003cp\u003eA dual-model collaborative framework for intelligent acupuncture prescription recommendation is proposed. Specifically, symptom-to-acupoint mapping is formulated as an end-to-end text generation task and an intelligent recommendation method based on dual-model collaboration with consistency calibration(DM3C) is proposed. Firstly, a Chinese Bidirectional and Auto-Regressive Transformers(BART) model is fine-tuned on clinical symptom-acupoint pairs to generate baseline acupoint sequences. Then, a retrieval-augmented prompting strategy is used to query large language models (LLMs), producing additional candidate prescriptions from similar historical cases. Finally, a random forest-based consistency calibration module integrates multi-source signals to score and filter candidate acupoints, yielding a reliability-weighted final recommendation.\u003c/p\u003e\u003ch2\u003eResults\u003c/h2\u003e \u003cp\u003eExperimental results demonstrate that the DM3C significantly improves acupuncture prescription recommendation performance. When more prompts are retrieved (top-k\u0026thinsp;=\u0026thinsp;21), the DeepSeek-V3-based collaborative achieves an F1 score of 0.3821, a Recall of 0.5216, and a Coverage of 0.3372, representing a 0.1062 increase in F1 over the original DeepSeek-V3 without model collaboration. The GPT-4o-based model attains an F1 score of 0.3780 and a Recall of 0.4833, with a 0.0169 improvement in Recall compared with its retrieval-enhanced counterpart.\u003c/p\u003e\u003ch2\u003eConclusion\u003c/h2\u003e \u003cp\u003eBy combining a domain-fine-tuned generator, retrieval-augmented LLM outputs, and a consistency-calibrated random forest filter, the proposed the DM3C enhances the generalizability and Recall of intelligent acupuncture prescription recommendations, providing effective support for clinical decision-making in TCM acupuncture treatment.\u003c/p\u003e","manuscriptTitle":"Dual-Model Collaboration with Consistency Calibration for Intelligent Acupuncture Prescription Recommendation","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-02-05 14:30:46","doi":"10.21203/rs.3.rs-7677489/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":"e2451b2c-b67c-4c27-ab93-102032db8bf3","owner":[],"postedDate":"February 5th, 2026","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2026-02-11T13:11:20+00:00","versionOfRecord":[],"versionCreatedAt":"2026-02-05 14:30:46","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-7677489","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7677489","identity":"rs-7677489","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}