{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"institution":[{"name":"medRxiv"}],"indexed":{"date-parts":[[2026,10,29]],"date-time":"2026-10-29T23:57:25Z","timestamp":1793318245086,"version":"4.5.0"},"posted":{"date-parts":[[2025,6,3]]},"group-title":"Health Informatics","reference-count":49,"publisher":"openRxiv","license":[{"start":{"date-parts":[[2025,6,3]],"date-time":"2025-06-03T00:00:00Z","timestamp":1748908800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"accepted":{"date-parts":[[2025,6,3]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                <jats:p>\n                  Laboratory tests are crucial for diagnosing and managing health conditions, providing essential reference ranges for result interpretation. The diversity of lab tests, influenced by variables like the specimen type (e.g., blood, urine), gender, age-specific, and other influencing factors such as pregnancy, makes automated interpretation challenging. Automated clinical decision support systems attempting to interpret these values must account for such nuances to avoid misdiagnoses or incorrect clinical decisions. In this regard, we present\n                  <jats:bold>LabQAR<\/jats:bold>\n                  (\n                  <jats:bold>Lab<\/jats:bold>\n                  oratory\n                  <jats:bold>Q<\/jats:bold>\n                  uestion\n                  <jats:bold>A<\/jats:bold>\n                  nswering with\n                  <jats:bold>R<\/jats:bold>\n                  eference Ranges), a manually curated dataset comprising 550 lab test reference ranges derived from authoritative medical sources, encompassing 363 unique lab tests and including multiple-choice questions with annotations on reference ranges, specimen types, and other factors impacting interpretation. We also assess the performance of several large language models (LLMs), including LLaMA 3.1, GatorTronGPT, GPT-3.5, GPT-4, and GPT-4o, in predicting reference ranges and classifying results as normal, low, or high. The findings indicate that GPT-4o outperforms other models, showcasing the potential of LLMs in clinical decision support.\n                <\/jats:p>","DOI":"10.1101\/2025.06.03.25328882","type":"posted-content","created":{"date-parts":[[2025,6,4]],"date-time":"2025-06-04T05:31:39Z","timestamp":1749015099000},"source":"Crossref","is-referenced-by-count":1,"title":["LabQAR: A Manually Curated Dataset for Question Answering on Laboratory Test Reference Ranges and Interpretation"],"prefix":"10.64898","author":[{"given":"Balu","family":"Bhasuran","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1268-7239","authenticated-orcid":false,"given":"Qiao","family":"Jin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Angelique","family":"Deville","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yonghui","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Karim","family":"Hanna","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhiyong","family":"Lu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3608-0244","authenticated-orcid":false,"given":"Zhe","family":"He","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"54368","reference":[{"key":"2025060516400813000_2025.06.03.25328882v1.1","first-page":"1","article-title":"Biomedical Question Answering: A Survey of Approaches and Challenges","volume":"55","year":"2023","journal-title":"ACM Comput. Surv"},{"key":"2025060516400813000_2025.06.03.25328882v1.2","unstructured":"Health Online 2013. One in three American adults have gone online to figure out a medical condition https:\/\/www.pewresearch.org\/internet\/2013\/01\/15\/health-online-2013\/."},{"key":"2025060516400813000_2025.06.03.25328882v1.3","doi-asserted-by":"crossref","first-page":"191","DOI":"10.1007\/s10791-006-7149-y","article-title":"Automatic question answering using the web: Beyond the Factoid","volume":"9","year":"2006","journal-title":"Inf Retrieval"},{"key":"2025060516400813000_2025.06.03.25328882v1.4","doi-asserted-by":"crossref","first-page":"170","DOI":"10.1038\/s41597-023-02068-4","article-title":"BioASQ-QA: A manually curated corpus for Biomedical Question Answering","volume":"10","year":"2023","journal-title":"Sci Data"},{"key":"2025060516400813000_2025.06.03.25328882v1.5","doi-asserted-by":"publisher","DOI":"10.1186\/s12859-015-0564-6"},{"key":"2025060516400813000_2025.06.03.25328882v1.6","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1909.06146"},{"key":"2025060516400813000_2025.06.03.25328882v1.7","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.bionlp-1.15"},{"key":"2025060516400813000_2025.06.03.25328882v1.8","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-1140"},{"key":"2025060516400813000_2025.06.03.25328882v1.9","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1258"},{"key":"2025060516400813000_2025.06.03.25328882v1.10","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2203.14371"},{"key":"2025060516400813000_2025.06.03.25328882v1.11","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1906.04701"},{"key":"2025060516400813000_2025.06.03.25328882v1.12","doi-asserted-by":"crossref","first-page":"773329","DOI":"10.3389\/fnbot.2022.773329","article-title":"SentiMedQAer: A Transfer Learning-Based Sentiment-Aware Model for Biomedical Question Answering","volume":"16","year":"2022","journal-title":"Front Neurorobot"},{"key":"2025060516400813000_2025.06.03.25328882v1.13","doi-asserted-by":"crossref","first-page":"329","DOI":"10.1038\/s41597-023-02203-1","article-title":"CHQ-SocioEmo: Identifying Social and Emotional Support Needs in Consumer-Health Questions","volume":"10","year":"2023","journal-title":"Sci Data"},{"key":"2025060516400813000_2025.06.03.25328882v1.14","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"2025060516400813000_2025.06.03.25328882v1.15","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/n19-1423"},{"key":"2025060516400813000_2025.06.03.25328882v1.16","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2005.14165"},{"key":"2025060516400813000_2025.06.03.25328882v1.17","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btz682"},{"key":"2025060516400813000_2025.06.03.25328882v1.18","first-page":"1","article-title":"Domain-Specific Language Model Pretraining for Biomedical Natural Language Processing","volume":"3","year":"2022","journal-title":"ACM Trans. Comput. Healthcare"},{"key":"2025060516400813000_2025.06.03.25328882v1.19","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1904.03323"},{"key":"2025060516400813000_2025.06.03.25328882v1.20","unstructured":"Introducing GPT-4.5. https:\/\/openai.com\/index\/introducing-gpt-4-5\/."},{"key":"2025060516400813000_2025.06.03.25328882v1.21","unstructured":"The Llama 4 herd: The beginning of a new era of natively multimodal AI innovation. https:\/\/ai.meta.com\/blog\/llama-4-multimodal-intelligence\/."},{"key":"2025060516400813000_2025.06.03.25328882v1.22","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2312.11805"},{"key":"2025060516400813000_2025.06.03.25328882v1.23","unstructured":"Introducing PaLM 2. https:\/\/blog.google\/technology\/ai\/google-palm-2-ai-large-language-model\/."},{"key":"2025060516400813000_2025.06.03.25328882v1.24","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-023-06291-2"},{"key":"2025060516400813000_2025.06.03.25328882v1.25","doi-asserted-by":"crossref","first-page":"943","DOI":"10.1038\/s41591-024-03423-7","article-title":"Toward expert-level medical question answering with large language models","volume":"31","year":"2025","journal-title":"Nat Med"},{"key":"2025060516400813000_2025.06.03.25328882v1.26","unstructured":"MedGemma model card. https:\/\/developers.google.com\/health-ai-developer-foundations\/medgemma\/model-card."},{"key":"2025060516400813000_2025.06.03.25328882v1.27","doi-asserted-by":"publisher","DOI":"10.1001\/jamainternmed.2025.0821"},{"key":"2025060516400813000_2025.06.03.25328882v1.28","doi-asserted-by":"publisher","DOI":"10.1038\/s41591-024-02855-5"},{"key":"2025060516400813000_2025.06.03.25328882v1.29","doi-asserted-by":"crossref","first-page":"9074","DOI":"10.1038\/s41467-024-53081-z","article-title":"Matching patients to clinical trials with large language models","volume":"15","year":"2024","journal-title":"Nat Commun"},{"key":"2025060516400813000_2025.06.03.25328882v1.30","doi-asserted-by":"crossref","first-page":"166","DOI":"10.1038\/s41746-025-01556-8","article-title":"Preliminary analysis of the impact of lab results on large language model generated differential diagnoses","volume":"8","year":"2025","journal-title":"NPJ Digit Med"},{"key":"2025060516400813000_2025.06.03.25328882v1.31","doi-asserted-by":"crossref","first-page":"939","DOI":"10.1093\/clinchem\/hvad058","article-title":"Assessing the Accuracy and Clinical Utility of ChatGPT in Laboratory Medicine","volume":"69","year":"2023","journal-title":"Clin Chem"},{"key":"2025060516400813000_2025.06.03.25328882v1.32","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2303.08774"},{"key":"2025060516400813000_2025.06.03.25328882v1.33","doi-asserted-by":"crossref","first-page":"e56655","DOI":"10.2196\/56655","article-title":"Quality of Answers of Generative Large Language Models Versus Peer Users for Interpreting Laboratory Test Results for Lay Patients: Evaluation Study","volume":"26","year":"2024","journal-title":"J Med Internet Res"},{"key":"2025060516400813000_2025.06.03.25328882v1.34","doi-asserted-by":"crossref","first-page":"1122","DOI":"10.1093\/clinchem\/hvae093","article-title":"ChatGPT vs Medical Professional: Analyzing Responses to Laboratory Medicine Questions on Social Media","volume":"70","year":"2024","journal-title":"Clin Chem"},{"key":"2025060516400813000_2025.06.03.25328882v1.35","doi-asserted-by":"crossref","first-page":"2425","DOI":"10.1515\/cclm-2024-0246","article-title":"Comparison of ChatGPT, Gemini, and Le Chat with physician interpretations of medical laboratory questions from an online health forum","volume":"62","year":"2024","journal-title":"Clin Chem Lab Med"},{"key":"2025060516400813000_2025.06.03.25328882v1.36","doi-asserted-by":"crossref","first-page":"83","DOI":"10.1016\/j.annemergmed.2023.08.003","article-title":"ChatGPT and Generating a Differential Diagnosis Early in an Emergency Department Presentation","volume":"83","year":"2024","journal-title":"Annals of Emergency Medicine"},{"key":"2025060516400813000_2025.06.03.25328882v1.37","unstructured":"Laposata, M. Clinical Laboratory Reference Values. in Laposata\u2019s Laboratory Medicine: Diagnosis of Disease in the Clinical Laboratory, 3e (McGraw-Hill Education, New York, NY, 2019)."},{"key":"2025060516400813000_2025.06.03.25328882v1.38","unstructured":"ABIM Laboratory Test Reference Ranges. https:\/\/www.abim.org\/Media\/bfijryql\/laboratory-reference-ranges.pdf."},{"key":"2025060516400813000_2025.06.03.25328882v1.39","unstructured":"The Stanford Clinical Laboratory. https:\/\/stanfordlab.com\/test-directory\/critical-values.html."},{"key":"2025060516400813000_2025.06.03.25328882v1.40","unstructured":"Clinical Guide to Laboratory Tests. (W.B. Saunders, Philadelphia London, 1995)."},{"key":"2025060516400813000_2025.06.03.25328882v1.41","unstructured":"Laposata, M. SI Unit Conversion Guide. (NEJM Books, Boston, Mass, 1992)."},{"key":"2025060516400813000_2025.06.03.25328882v1.42","unstructured":"AMA Manual of Style: A Guide for Authors and Editors. (Oxford Univ. Pr, Oxford, 2007)."},{"key":"2025060516400813000_2025.06.03.25328882v1.43","unstructured":"Jacobs & DeMott Laboratory Test Handbook. (Lexi-Comp, Hudson [Ohio], 2001)."},{"key":"2025060516400813000_2025.06.03.25328882v1.44","unstructured":"Clinical Diagnosis and Management by Laboratory Methods. (Saunders, Philadelphia, Pa. London, 2001)."},{"key":"2025060516400813000_2025.06.03.25328882v1.45","doi-asserted-by":"publisher","DOI":"10.1056\/NEJMcpc049016"},{"key":"2025060516400813000_2025.06.03.25328882v1.46","unstructured":"Tietz Textbook of Clinical Chemistry and Molecular Diagnostics. (Saunders, St. Louis, Mo, 2013)."},{"key":"2025060516400813000_2025.06.03.25328882v1.47","unstructured":"Introducing Llama 3.1: Our most capable models to date. https:\/\/ai.meta.com\/blog\/meta-llama-3-1\/."},{"key":"2025060516400813000_2025.06.03.25328882v1.48","doi-asserted-by":"crossref","unstructured":"Peng, C. et al. A study of generative large language model for medical research and healthcare. npj Digit. Med. 6, (2023).","DOI":"10.1038\/s41746-023-00958-w"},{"key":"2025060516400813000_2025.06.03.25328882v1.49","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2410.21276"}],"container-title":[],"original-title":[],"link":[{"URL":"https:\/\/syndication.highwire.org\/content\/doi\/10.1101\/2025.06.03.25328882","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,15]],"date-time":"2026-01-15T20:37:36Z","timestamp":1768509456000},"score":1,"resource":{"primary":{"URL":"http:\/\/medrxiv.org\/lookup\/doi\/10.1101\/2025.06.03.25328882"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,3]]},"references-count":49,"URL":"https:\/\/doi.org\/10.1101\/2025.06.03.25328882","relation":{},"subject":[],"published":{"date-parts":[[2025,6,3]]},"subtype":"preprint"}}