{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"institution":[{"name":"medRxiv"}],"indexed":{"date-parts":[[2026,9,30]],"date-time":"2026-09-30T10:57:40Z","timestamp":1790765860496,"version":"4.1.0"},"posted":{"date-parts":[[2026,9,26]]},"group-title":"Health Informatics","reference-count":82,"publisher":"openRxiv","license":[{"start":{"date-parts":[[2026,9,26]],"date-time":"2026-09-26T00:00:00Z","timestamp":1790380800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.medrxiv.org\/about\/FAQ#license"}],"funder":[{"name":"NIH","award":["R01LM013995"],"award-info":[{"award-number":["R01LM013995"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"accepted":{"date-parts":[[2026,9,26]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                <jats:sec>\n                  <jats:title>Objective<\/jats:title>\n                  <jats:p>To compare the accuracy, cost, and speed of a low-cost, non-generative structured-judgment model and four general-purpose large language models (LLMs) for extracting smoking status, pack-years, and quit date from clinical notes to support lung cancer screening (LCS) clinical decision support (CDS).<\/jats:p>\n                <\/jats:sec>\n                <jats:sec>\n                  <jats:title>Materials and Methods<\/jats:title>\n                  <jats:p>We built a synthetic, shareable benchmark of 3,000 outpatient notes in three conditions: 1,000 template-generated notes, 1,000 realistic, \u201cmessy\u201d notes written by an LLM from structured facts, and 1,000 \u201cmessy\u201d notes that required complex arithmetic to determine pack-years and quit dates. Ground truth reference labels were programmatically generated before each note was created. We compared TypeSafe Jev 1.13 with Claude Haiku 4.5, Claude Sonnet 5, GPT-6 Luna and GPT-6 Sol, each using an identical structured output schema. We determined United States Preventive Services Task Force (USPSTF) 2021 and American Cancer Society (ACS) 2023 eligibility from each system\u2019s output in code.<\/jats:p>\n                <\/jats:sec>\n                <jats:sec>\n                  <jats:title>Results<\/jats:title>\n                  <jats:p>Jev made the correct eligibility decision for 99.1%, 99.9%, and 94.4% of notes in the three conditions, compared with 97.8%, 98.4%, and 98.1% for Haiku, 100.0%, 99.6%, and 99.8% for Sonnet, 99.7%, 98.8%, and 98.5% for Luna, and 100.0%, 99.8%, and 99.6% for Sol. In the complex condition, Jev produced 27 false positive and 14 false negative screening flags per 1,000 notes, the most of any system. Luna cost $0.12 to $0.21 per 1,000 notes and Jev $0.61 to $0.64, compared with $2.44 to $4.22 for Sol, $3.37 to $4.43 for Haiku, and $3.76 to $6.61 for Sonnet. Jev was the fastest system (median 0.45 to 1.21 seconds per note, compared with 1.71 to 3.50 seconds for the others).<\/jats:p>\n                <\/jats:sec>\n                <jats:sec>\n                  <jats:title>Discussion<\/jats:title>\n                  <jats:p>All models tested had high accuracy. The structured-judgment model had the lowest latency, which could allow for synchronous use in clinical decision support systems rather than batched, cached invocation. The cost of the structured-judgment model was low, but the newest cost-efficient LLM, Luna, was less expensive and more accurate on the complex notes, though its latency was higher. Accuracy, latency, and cost are all moving quickly as new models are released.<\/jats:p>\n                <\/jats:sec>\n                <jats:sec>\n                  <jats:title>Conclusion<\/jats:title>\n                  <jats:p>Fast, low-cost language models could make real-time, note-based CDS practical, and current models are highly accurate. Prices and capabilities are changing rapidly, so continuous benchmarking and system updates are essential.<\/jats:p>\n                <\/jats:sec>","DOI":"10.64898\/2026.09.24.26363906","type":"posted-content","created":{"date-parts":[[2026,9,26]],"date-time":"2026-09-26T18:00:18Z","timestamp":1790445618000},"source":"Crossref","is-referenced-by-count":0,"title":["Extracting smoking history from clinical notes for lung cancer screening decision support: comparing a structured-judgment model with general-purpose large language models"],"prefix":"10.64898","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6844-145X","authenticated-orcid":false,"given":"Adam","family":"Wright","sequence":"first","affiliation":[{"name":"Department of Biomedical Informatics, Vanderbilt University Medical Center, Nashville, TN, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Siru","family":"Liu","sequence":"additional","affiliation":[{"name":"Department of Biomedical Informatics, Vanderbilt University Medical Center, Nashville, TN, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Aileen","family":"Wright","sequence":"additional","affiliation":[{"name":"Department of Biomedical Informatics, Vanderbilt University Medical Center, Nashville, TN, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"54368","reference":[{"key":"2026093003051281000_2026.09.24.26363906v1.1","doi-asserted-by":"publisher","DOI":"10.1136\/bmj.38398.500764.8F"},{"key":"2026093003051281000_2026.09.24.26363906v1.2","doi-asserted-by":"publisher","DOI":"10.7326\/0003-4819-157-1-201207030-00450"},{"key":"2026093003051281000_2026.09.24.26363906v1.3","doi-asserted-by":"publisher","DOI":"10.1136\/bmj.m3216"},{"key":"2026093003051281000_2026.09.24.26363906v1.4","doi-asserted-by":"publisher","DOI":"10.1197\/jamia.M2334"},{"key":"2026093003051281000_2026.09.24.26363906v1.5","doi-asserted-by":"publisher","DOI":"10.1093\/jamia\/ocw005"},{"key":"2026093003051281000_2026.09.24.26363906v1.6","doi-asserted-by":"publisher","DOI":"10.1093\/jamia\/ocx106"},{"key":"2026093003051281000_2026.09.24.26363906v1.7","doi-asserted-by":"publisher","DOI":"10.1093\/jamia\/ocac150"},{"key":"2026093003051281000_2026.09.24.26363906v1.8","doi-asserted-by":"publisher","DOI":"10.1016\/j.jbi.2010.09.009"},{"key":"2026093003051281000_2026.09.24.26363906v1.9","doi-asserted-by":"publisher","DOI":"10.1136\/amiajnl-2011-000121"},{"key":"2026093003051281000_2026.09.24.26363906v1.10","doi-asserted-by":"publisher","DOI":"10.1136\/amiajnl-2011-000521"},{"key":"2026093003051281000_2026.09.24.26363906v1.11","doi-asserted-by":"publisher","DOI":"10.1093\/jamia\/ocad020"},{"key":"2026093003051281000_2026.09.24.26363906v1.12","doi-asserted-by":"publisher","DOI":"10.1055\/s-0038-1638592"},{"key":"2026093003051281000_2026.09.24.26363906v1.13","doi-asserted-by":"publisher","DOI":"10.1016\/j.jbi.2009.08.007"},{"key":"2026093003051281000_2026.09.24.26363906v1.14","first-page":"218","article-title":"How essential are unstructured clinical narratives and information fusion to clinical trial recruitment?","volume":"2014","year":"2014","journal-title":"AMIA Joint Summits on Translational Science Proceedings"},{"key":"2026093003051281000_2026.09.24.26363906v1.15","doi-asserted-by":"publisher","DOI":"10.1016\/j.jbi.2017.11.011"},{"key":"2026093003051281000_2026.09.24.26363906v1.16","doi-asserted-by":"publisher","DOI":"10.1136\/amiajnl-2012-001576"},{"key":"2026093003051281000_2026.09.24.26363906v1.17","doi-asserted-by":"publisher","DOI":"10.1197\/jamia.M2408"},{"key":"2026093003051281000_2026.09.24.26363906v1.18","doi-asserted-by":"publisher","DOI":"10.1197\/jamia.M2437"},{"key":"2026093003051281000_2026.09.24.26363906v1.19","doi-asserted-by":"publisher","DOI":"10.1186\/s12911-019-0863-3"},{"key":"2026093003051281000_2026.09.24.26363906v1.20","doi-asserted-by":"publisher","DOI":"10.1109\/ICHI48887.2020.9374369"},{"key":"2026093003051281000_2026.09.24.26363906v1.21","doi-asserted-by":"publisher","DOI":"10.1200\/CCI-25-00223"},{"key":"2026093003051281000_2026.09.24.26363906v1.22","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.130"},{"key":"2026093003051281000_2026.09.24.26363906v1.23","doi-asserted-by":"publisher","DOI":"10.1038\/s41591-023-02448-8"},{"key":"2026093003051281000_2026.09.24.26363906v1.24","doi-asserted-by":"publisher","DOI":"10.1038\/s41746-023-00970-0"},{"key":"2026093003051281000_2026.09.24.26363906v1.25","doi-asserted-by":"publisher","DOI":"10.1038\/s41746-024-01079-8"},{"key":"2026093003051281000_2026.09.24.26363906v1.26","doi-asserted-by":"publisher","DOI":"10.1038\/s41746-024-01233-2"},{"key":"2026093003051281000_2026.09.24.26363906v1.27","doi-asserted-by":"publisher","DOI":"10.1038\/s41746-025-02009-y"},{"key":"2026093003051281000_2026.09.24.26363906v1.28","doi-asserted-by":"publisher","DOI":"10.1093\/jamiaopen\/ooaf182"},{"key":"2026093003051281000_2026.09.24.26363906v1.29","doi-asserted-by":"publisher","DOI":"10.1093\/jamia\/ocad072"},{"key":"2026093003051281000_2026.09.24.26363906v1.30","doi-asserted-by":"publisher","DOI":"10.1093\/jamia\/ocae041"},{"key":"2026093003051281000_2026.09.24.26363906v1.31","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijmedinf.2025.106104"},{"key":"2026093003051281000_2026.09.24.26363906v1.32","doi-asserted-by":"publisher","DOI":"10.1001\/jama.2026.13187"},{"key":"2026093003051281000_2026.09.24.26363906v1.33","doi-asserted-by":"publisher","DOI":"10.1001\/jama.2021.1117"},{"key":"2026093003051281000_2026.09.24.26363906v1.34","doi-asserted-by":"publisher","DOI":"10.3322\/caac.21811"},{"key":"2026093003051281000_2026.09.24.26363906v1.35","unstructured":"Centers for Medicare & Medicaid Services. Decision memo: Screening for lung cancer with low dose computed tomography (LDCT) (CAG-00439R). National Coverage Analysis decision memo, February 10, 2022, February 2022. URL https:\/\/www.cms.gov\/medicare-coverage-database\/view\/ncacal-decision-memo.aspx?proposed=N&ncaid=304. Accessed September 18, 2026."},{"key":"2026093003051281000_2026.09.24.26363906v1.36","doi-asserted-by":"publisher","DOI":"10.1001\/jamainternmed.2024.1655"},{"key":"2026093003051281000_2026.09.24.26363906v1.37","doi-asserted-by":"publisher","DOI":"10.1016\/j.chest.2023.04.040"},{"key":"2026093003051281000_2026.09.24.26363906v1.38","doi-asserted-by":"publisher","DOI":"10.1001\/jamanetworkopen.2024.15383"},{"key":"2026093003051281000_2026.09.24.26363906v1.39","doi-asserted-by":"publisher","DOI":"10.1513\/AnnalsATS.201612-984OC"},{"key":"2026093003051281000_2026.09.24.26363906v1.40","first-page":"1392","article-title":"Challenges with collecting smoking status in electronic health records","volume":"2017","year":"2017","journal-title":"AMIA Annual Symposium Proceedings"},{"key":"2026093003051281000_2026.09.24.26363906v1.41","doi-asserted-by":"publisher","DOI":"10.1093\/jamia\/ocac020"},{"key":"2026093003051281000_2026.09.24.26363906v1.42","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijmedinf.2023.105136"},{"key":"2026093003051281000_2026.09.24.26363906v1.43","doi-asserted-by":"publisher","DOI":"10.1038\/s41746-024-01315-1"},{"key":"2026093003051281000_2026.09.24.26363906v1.44","unstructured":"Anthropic. Batch processing. Claude Platform documentation (Message Batches API), 2026. URL https:\/\/platform.claude.com\/docs\/en\/build-with-claude\/batch-processing. Accessed September 18, 2026."},{"key":"2026093003051281000_2026.09.24.26363906v1.45","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1423"},{"key":"2026093003051281000_2026.09.24.26363906v1.46","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W19-1909"},{"key":"2026093003051281000_2026.09.24.26363906v1.47","doi-asserted-by":"publisher","DOI":"10.1038\/s41746-022-00742-2"},{"key":"2026093003051281000_2026.09.24.26363906v1.48","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1404"},{"key":"2026093003051281000_2026.09.24.26363906v1.49","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.naacl-long.300"},{"key":"2026093003051281000_2026.09.24.26363906v1.50","unstructured":"Lewis Tunstall , Nils Reimers , Unso Eun Seo Jo , Luke Bates , Daniel Korat , Moshe Wasserblat , and Oren Pereg . Efficient few-shot learning without prompts. arXiv preprint arXiv:2209.11055, 2022. URL https:\/\/arxiv.org\/abs\/2209.11055."},{"key":"2026093003051281000_2026.09.24.26363906v1.51","unstructured":"Marah Abdin , Jyoti Aneja , Hany Awadalla , Ahmed Awadallah , Ammar Ahmad Awan , Nguyen Bach , Amit Bahree , Arash Bakhtiari , Jianmin Bao , Harkirat Behl , Alon Benhaim , Misha Bilenko , Johan Bjorck , S\u00e9bastien Bubeck , Martin Cai , Qin Cai , Vishrav Chaudhary , Dong Chen , Dongdong Chen , Weizhu Chen , Yen-Chun Chen , Yi-Ling Chen , Hao Cheng , Parul Chopra , Xiyang Dai , Matthew Dixon , Ronen Eldan , Victor Fragoso , Jianfeng Gao , Mei Gao , Min Gao , Amit Garg , Allie Del Giorno , Abhishek Goswami , Suriya Gunasekar , Emman Haider , Junheng Hao , Russell J. Hewett , Wenxiang Hu , Jamie Huynh , Dan Iter , Sam Ade Jacobs , Mojan Javaheripi , Xin Jin , Nikos Karampatziakis , Piero Kauffmann , Mahoud Khademi , Dongwoo Kim , Young Jin Kim , Lev Kurilenko , James R. Lee , Yin Tat Lee , Yuanzhi Li , Yunsheng Li , Chen Liang , Lars Liden , Xihui Lin , Zeqi Lin , Ce Liu , Liyuan Liu , Mengchen Liu , Weishung Liu , Xiaodong Liu , Chong Luo , Piyush Madan , Ali Mahmoudzadeh , David Majercak , Matt Mazzola , Caio C\u00e9sar Teodoro Mendes , Arindam Mitra , Hardik Modi , Anh Nguyen , Brandon Norick , Barun Patra , Daniel Perez-Becker , Thomas Portet , Reid Pryzant , Heyang Qin , Marko Radmilac , Liliang Ren , Gustavo de Rosa , Corby Rosset , Sambudha Roy , Olatunji Ruwase , Olli Saarikivi , Amin Saied , Adil Salim , Michael Santacroce , Shital Shah , Ning Shang , Hiteshi Sharma , Yelong Shen , Swadheen Shukla , Xia Song , Masahiro Tanaka , Andrea Tupini , Praneetha Vaddamanu , Chunyu Wang , Guanhua Wang , Lijuan Wang , Shuohang Wang , Xin Wang , Yu Wang , Rachel Ward , Wen Wen , Philipp Witte , Haiping Wu , Xiaoxia Wu , Michael Wyatt , Bin Xiao , Can Xu , Jiahang Xu , Weijian Xu , Jilong Xue , Sonali Yadav , Fan Yang , Jianwei Yang , Yifan Yang , Ziyi Yang , Donghan Yu , Lu Yuan , Chenruidong Zhang , Cyril Zhang , Jianwen Zhang , Li Lyna Zhang , Yi Zhang , Yue Zhang , Yunan Zhang , and Xiren Zhou . Phi-3 technical report: A highly capable language model locally on your phone. arXiv preprint arXiv:2404.14219, 2024. URL https:\/\/arxiv.org\/abs\/2404.14219."},{"key":"2026093003051281000_2026.09.24.26363906v1.52","unstructured":"Brandon T. Willard and R\u00e9mi Louf . Efficient guided generation for large language models. arXiv preprint arXiv:2307.09702, 2023. URL https:\/\/arxiv.org\/abs\/2307.09702."},{"key":"2026093003051281000_2026.09.24.26363906v1.53","doi-asserted-by":"publisher","DOI":"10.1001\/jama.2023.9458"},{"key":"2026093003051281000_2026.09.24.26363906v1.54","unstructured":"U.S. Department of Health and Human Services, Office for Civil Rights. Guidance on HIPAA & cloud computing. HHS.gov; content last reviewed December 23, 2022, 2022. URL https:\/\/www.hhs.gov\/hipaa\/for-professionals\/special-topics\/health-information-technology\/cloud-computing\/index.html. Accessed September 18, 2026."},{"key":"2026093003051281000_2026.09.24.26363906v1.55","unstructured":"TypeSafe AI. System one. TypeSafe documentation, 2026. URL https:\/\/docs.typesafe.ai\/concepts\/system-one. Accessed September 18, 2026."},{"key":"2026093003051281000_2026.09.24.26363906v1.56","unstructured":"Daniel Kahneman . Thinking, Fast and Slow. Farrar, Straus and Giroux, New York, 2011. ISBN 9780374275631."},{"key":"2026093003051281000_2026.09.24.26363906v1.57","unstructured":"TypeSafe AI. Introduction. TypeSafe documentation, 2026. URL https:\/\/docs.typesafe.ai\/introduction. Accessed September 18, 2026."},{"key":"2026093003051281000_2026.09.24.26363906v1.58","unstructured":"TypeSafe AI. Primitives (questions). TypeSafe documentation, 2026. URL https:\/\/docs.typesafe.ai\/primitives. Accessed September 18, 2026."},{"key":"2026093003051281000_2026.09.24.26363906v1.59","unstructured":"TypeSafe AI. Confidence. TypeSafe documentation, 2026. URL https:\/\/docs.typesafe.ai\/confidence. Accessed September 18, 2026."},{"key":"2026093003051281000_2026.09.24.26363906v1.60","unstructured":"TypeSafe AI. AI primer. TypeSafe documentation, 2026. URL https:\/\/docs.typesafe.ai\/introduction\/machine-learning-primer. Accessed September 18, 2026."},{"key":"2026093003051281000_2026.09.24.26363906v1.61","unstructured":"Chuan Guo , Geoff Pleiss , Yu Sun , and Kilian Q. Weinberger . On calibration of modern neural networks. In Doina Precup and Yee Whye Teh, editors, Proceedings of the 34th International Conference on Machine Learning, volume 70 of Proceedings of Machine Learning Research, pages 1321\u20131330. PMLR, 2017. URL https:\/\/proceedings.mlr.press\/v70\/guo17a.html."},{"key":"2026093003051281000_2026.09.24.26363906v1.62","unstructured":"Saurav Kadavath , Tom Conerly , Amanda Askell , Tom Henighan , Dawn Drain , Ethan Perez , Nicholas Schiefer , Zac Hatfield-Dodds , Nova DasSarma , Eli Tran-Johnson , Scott Johnston , Sheer El-Showk , Andy Jones , Nelson Elhage , Tristan Hume , Anna Chen , Yuntao Bai , Sam Bowman , Stanislav Fort , Deep Ganguli , Danny Hernandez , Josh Jacobson , Jackson Kernion , Shauna Kravec , Liane Lovitt , Kamal Ndousse , Catherine Olsson , Sam Ringer , Dario Amodei , Tom Brown , Jack Clark , Nicholas Joseph , Ben Mann , Sam McCandlish , Chris Olah , and Jared Kaplan . Language models (mostly) know what they know. arXiv preprint arXiv:2207.05221, 2022. URL https:\/\/arxiv.org\/abs\/2207.05221."},{"key":"2026093003051281000_2026.09.24.26363906v1.63","unstructured":"TypeSafe AI. Jev 1.13 jaggedness. TypeSafe documentation; last reviewed 2026-09-17, 2026. URL https:\/\/docs.typesafe.ai\/model-jaggedness\/jev-1.13. Accessed September 18, 2026."},{"key":"2026093003051281000_2026.09.24.26363906v1.64","unstructured":"TypeSafe AI. Models. TypeSafe documentation, 2026. URL https:\/\/docs.typesafe.ai\/models. Accessed September 18, 2026."},{"key":"2026093003051281000_2026.09.24.26363906v1.65","unstructured":"Anthropic. Pricing. Claude Platform documentation, 2026. URL https:\/\/platform.claude.com\/docs\/en\/about-claude\/pricing. Accessed September 18, 2026."},{"key":"2026093003051281000_2026.09.24.26363906v1.66","unstructured":"Anthropic. Models overview. Claude Platform documentation, 2026. URL https:\/\/platform.claude.com\/docs\/en\/models\/overview. Accessed September 18, 2026."},{"key":"2026093003051281000_2026.09.24.26363906v1.67","unstructured":"Department of Biomedical Informatics, Harvard Medical School. n2c2 NLP research data sets. DBMI Data Portal. Archived copy of September 6, 2024 (Internet Archive) showing the notice \u201cThe n2c2 datasets are temporarily unavailable\u201d, 2024. URL https:\/\/web.archive.org\/web\/20240906082638\/ https:\/\/portal.dbmi.hms.harvard.edu\/projects\/n2c2-nlp\/. Accessed September 18, 2026."},{"key":"2026093003051281000_2026.09.24.26363906v1.68","unstructured":"PhysioNet. Responsible use of MIMIC data with online services like GPT. PhysioNet news post, April 18, 2023, April 2023. URL https:\/\/physionet.org\/news\/post\/gpt-responsible-use\/. Accessed September 18, 2026."},{"key":"2026093003051281000_2026.09.24.26363906v1.69","doi-asserted-by":"publisher","DOI":"10.1093\/jamia\/ocx079"},{"key":"2026093003051281000_2026.09.24.26363906v1.70","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pdig.0000082"},{"key":"2026093003051281000_2026.09.24.26363906v1.71","doi-asserted-by":"publisher","DOI":"10.1038\/s41746-023-00927-3"},{"key":"2026093003051281000_2026.09.24.26363906v1.72","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.305"},{"key":"2026093003051281000_2026.09.24.26363906v1.73","unstructured":"Anthropic. Structured outputs. Claude Platform documentation, 2026. URL https:\/\/platform.claude.com\/docs\/en\/build-with-claude\/structured-outputs. Accessed September 18, 2026."},{"key":"2026093003051281000_2026.09.24.26363906v1.74","unstructured":"Anthropic. Prompt caching. Claude API documentation, 2026. URL https:\/\/platform.claude.com\/docs\/en\/build-with-claude\/prompt-caching. Accessed September 23, 2026."},{"key":"2026093003051281000_2026.09.24.26363906v1.75","unstructured":"OpenAI. Models. OpenAI API documentation; GPT-6 Sol and GPT-6 Luna released September 22, 2026, 2026. URL https:\/\/developers.openai.com\/api\/docs\/models. Accessed September 23, 2026."},{"key":"2026093003051281000_2026.09.24.26363906v1.76","unstructured":"OpenAI. Pricing. OpenAI API documentation, 2026. URL https:\/\/developers.openai.com\/api\/docs\/pricing. Accessed September 23, 2026."},{"key":"2026093003051281000_2026.09.24.26363906v1.77","unstructured":"Vanderbilt Institute for Clinical and Translational Research. Data resource \u2013 SD (Synthetic Derivative). VICTR website, 2026. URL https:\/\/victr.vumc.org\/data-resource-sd\/. Accessed September 18, 2026."},{"key":"2026093003051281000_2026.09.24.26363906v1.78","doi-asserted-by":"publisher","DOI":"10.1016\/j.jbi.2014.02.003"},{"key":"2026093003051281000_2026.09.24.26363906v1.79","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-022-19358-3"},{"key":"2026093003051281000_2026.09.24.26363906v1.80","doi-asserted-by":"publisher","DOI":"10.1093\/jamia\/ocx059"},{"key":"2026093003051281000_2026.09.24.26363906v1.81","unstructured":"Walter J. Doherty and Ahrvind J. Thadani . The economic value of rapid response time. Technical Report GE20-0752-0, IBM Corporation, November 1982."},{"key":"2026093003051281000_2026.09.24.26363906v1.82","unstructured":"Anthropic. API and data retention. Claude Platform documentation (zero data retention and HIPAA readiness), 2026. URL https:\/\/platform.claude.com\/docs\/en\/manage-claude\/api-and-data-retention. Accessed September 18, 2026."}],"container-title":[],"original-title":[],"link":[{"URL":"https:\/\/syndication.highwire.org\/content\/doi\/10.64898\/2026.09.24.26363906","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,30]],"date-time":"2026-09-30T10:05:26Z","timestamp":1790762726000},"score":1,"resource":{"primary":{"URL":"http:\/\/medrxiv.org\/lookup\/doi\/10.64898\/2026.09.24.26363906"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,26]]},"references-count":82,"URL":"https:\/\/doi.org\/10.64898\/2026.09.24.26363906","relation":{},"subject":[],"published":{"date-parts":[[2026,9,26]]},"subtype":"preprint"}}