{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"institution":[{"name":"medRxiv"}],"indexed":{"date-parts":[[2026,10,21]],"date-time":"2026-10-21T22:30:55Z","timestamp":1792621855820,"version":"4.5.0"},"posted":{"date-parts":[[2024,3,18]]},"group-title":"Genetic and Genomic Medicine","reference-count":14,"publisher":"openRxiv","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"accepted":{"date-parts":[[2024,3,15]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                <jats:p>The advent of precision medicine has revolutionized cancer treatment by integrating individual genetic, lifestyle, and environmental factors to tailor patient care (Huang et al., 2020; Ginsburg and Phillips, 2018). However, the complexity and heterogeneity of diseases like Multiple Myeloma (MM) pose significant challenges in leveraging the vast amounts of genomic data and biomedical literature available for personalized treatment planning (Rajkumar, 2014; R\u00f6llig et al., 2015). To address this, we present an innovative Retrieval-Augmented Generation (RAG) based chatbot framework that harnesses the power of Natural Language Processing (NLP) and state-of-the-art language models to curate and analyze MM-specific literature and provide personalized treatment recommendations based on patient-specific genomic data (Lewis et al., 2020).<\/jats:p>\n                <jats:p>Our framework integrates the BioMed-RoBERTa-base model for embedding generation (Gururangan et al., 2020) and the Mistral-7B language model for question answering (Anthropic, 2023), enabling effective understanding and response to complex clinical queries. The retrieval component is enhanced by Amazon OpenSearch Service, ensuring fast and accurate access to relevant information. A comprehensive data analysis pipeline, including exploratory data analysis, semantic search, clustering, and topic modeling, provides valuable insights into the MM research landscape, informing the chatbot\u2019s knowledge base and uncovering potential research directions (Blei et al., 2003; Mikolov et al., 2013).<\/jats:p>\n                <jats:p>Deployed using Amazon Kendra, our RAG chatbot offers a user-friendly and scalable platform for accessing MM information, incorporating features such as user authentication, customizable web interface, and continuous improvement based on user feedback. The framework aims to democratize access to precision medicine by providing clinicians with a sophisticated tool for interpreting complex genomic data in the context of MM, streamlining clinical workflows, and facilitating the development of personalized treatment plans (Patel et al., 2015).<\/jats:p>\n                <jats:p>This paper presents the conceptualization, development, and potential impact of our RAG-based chatbot framework on the landscape of MM treatment and precision medicine. We argue that the synergistic integration of AI, NLP, and domain-specific knowledge marks a new era of healthcare, characterized by highly personalized, data-driven, and effective treatment modalities (Thong et al., 2021). Our framework not only advances the field of precision medicine in MM but also serves as a blueprint for the development of similar systems in other complex diseases, ultimately improving patient outcomes and quality of life.<\/jats:p>","DOI":"10.1101\/2024.03.14.24304293","type":"posted-content","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T10:25:41Z","timestamp":1710757541000},"source":"Crossref","is-referenced-by-count":32,"title":["A RAG Chatbot for Precision Medicine of Multiple Myeloma"],"prefix":"10.64898","author":[{"given":"Mujahid Ali","family":"Quidwai","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alessandro","family":"Lagana","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"54368","reference":[{"key":"2024032010151566000_2024.03.14.24304293v1.1","unstructured":"Anthropic. 2023. Mistral-7b. https:\/\/www.anthropic.com\/index\/mistral."},{"key":"2024032010151566000_2024.03.14.24304293v1.2","first-page":"993","article-title":"Latent dirichlet allocation","volume":"3","year":"2003","journal-title":"In Journal of Machine Learning Research"},{"issue":"1","key":"2024032010151566000_2024.03.14.24304293v1.3","first-page":"1","article-title":"Next-generation sequencing to guide cancer therapy","volume":"7","year":"2015","journal-title":"Genome Medicine"},{"key":"2024032010151566000_2024.03.14.24304293v1.4","doi-asserted-by":"publisher","DOI":"10.1377\/hlthaff.2017.1624"},{"key":"2024032010151566000_2024.03.14.24304293v1.5","article-title":"Don\u2019t stop pretraining: adapt language models to domains and tasks","year":"2020","journal-title":"arXiv preprint"},{"issue":"10","key":"2024032010151566000_2024.03.14.24304293v1.6","first-page":"1446","article-title":"Pre-cision medicine in cancer: challenges and recommendations from an eu-funded cervical cancer biobanking study","volume":"122","year":"2020","journal-title":"British Journal of Cancer"},{"key":"2024032010151566000_2024.03.14.24304293v1.7","article-title":"Retrieval-augmented generation for knowledge-intensive nlp tasks","year":"2020","journal-title":"arXiv preprint"},{"key":"2024032010151566000_2024.03.14.24304293v1.8","unstructured":"Tomas Mikolov , Ilya Sutskever , Kai Chen , Greg S Corrado , and Jeff Dean . 2013. Distributed representations of words and phrases and their compositionality. In Advances in Neural Information Processing Systems, pages 3111\u20133119."},{"issue":"2","key":"2024032010151566000_2024.03.14.24304293v1.9","first-page":"117","article-title":"Implications of the growing use of precision medicine for health technology assessment","volume":"4","year":"2015","journal-title":"Health Policy and Technology"},{"issue":"9","key":"2024032010151566000_2024.03.14.24304293v1.10","doi-asserted-by":"crossref","first-page":"543","DOI":"10.1038\/nrc.2017.63","article-title":"Evolutionary biology of high-risk multiple myeloma","volume":"17","year":"2017","journal-title":"Nature Reviews Cancer"},{"issue":"10","key":"2024032010151566000_2024.03.14.24304293v1.11","first-page":"999","article-title":"Multiple myeloma: 2014 update on diagnosis, risk-stratification, and management","volume":"89","year":"2014","journal-title":"American Journal of Hesmatology"},{"issue":"9983","key":"2024032010151566000_2024.03.14.24304293v1.12","doi-asserted-by":"crossref","first-page":"2197","DOI":"10.1016\/S0140-6736(14)60493-1","article-title":"Multiple myeloma: update on management","volume":"385","year":"2015","journal-title":"The Lancet"},{"key":"2024032010151566000_2024.03.14.24304293v1.13","first-page":"e2100404","article-title":"Precision medicine in oncology: The future of patient care","volume":"6","year":"2022","journal-title":"JCO Precision Oncology"},{"key":"2024032010151566000_2024.03.14.24304293v1.14","first-page":"40","article-title":"Artificial intelligence in cancer diagnosis and prognosis: Opportunities and challenges","volume":"505","year":"2021","journal-title":"Cancer Letters"}],"container-title":[],"original-title":[],"link":[{"URL":"https:\/\/syndication.highwire.org\/content\/doi\/10.1101\/2024.03.14.24304293","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,15]],"date-time":"2026-01-15T19:55:32Z","timestamp":1768506932000},"score":1,"resource":{"primary":{"URL":"http:\/\/medrxiv.org\/lookup\/doi\/10.1101\/2024.03.14.24304293"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,3,18]]},"references-count":14,"URL":"https:\/\/doi.org\/10.1101\/2024.03.14.24304293","relation":{},"subject":[],"published":{"date-parts":[[2024,3,18]]},"subtype":"preprint"}}