{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,29]],"date-time":"2026-10-29T20:57:47Z","timestamp":1793307467698,"version":"4.5.0"},"reference-count":47,"publisher":"American Society of Clinical Oncology (ASCO)","issue":"35","content-domain":{"domain":["ascopubs.org"],"crossmark-restriction":true},"short-container-title":["JCO"],"published-print":{"date-parts":[[2024,12,10]]},"abstract":"<jats:sec>\n                    <jats:title>PURPOSE<\/jats:title>\n                    <jats:p>Current approaches to accurately identify immune-related adverse events (irAEs) in large retrospective studies are limited. Large language models (LLMs) offer a potential solution to this challenge, given their high performance in natural language comprehension tasks. Therefore, we investigated the use of an LLM to identify irAEs among hospitalized patients, comparing its performance with manual adjudication and International Classification of Disease (ICD) codes.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>METHODS<\/jats:title>\n                    <jats:p>Hospital admissions of patients receiving immune checkpoint inhibitor (ICI) therapy at a single institution from February 5, 2011, to September 5, 2023, were individually reviewed and adjudicated for the presence of irAEs. ICD codes and an LLM with retrieval-augmented generation were applied to detect frequent irAEs (ICI-induced colitis, hepatitis, and pneumonitis) and the most fatal irAE (ICI-myocarditis) from electronic health records. The performance between ICD codes and LLM was compared via sensitivity and specificity with an \u03b1 = .05, relative to the gold standard of manual adjudication. External validation was performed using a data set of hospital admissions from June 1, 2018, to May 31, 2019, from a second institution.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>RESULTS<\/jats:title>\n                    <jats:p>\n                      Of the 7,555 admissions for patients on ICI therapy in the initial cohort, 2.0% were adjudicated to be due to ICI-colitis, 1.1% ICI-hepatitis, 0.7% ICI-pneumonitis, and 0.8% ICI-myocarditis. The LLM demonstrated higher sensitivity than ICD codes (94.7%\n                      <jats:italic>v<\/jats:italic>\n                      68.7%), achieving significance for ICI-hepatitis (\n                      <jats:italic>P<\/jats:italic>\n                      &lt; .001), myocarditis (\n                      <jats:italic>P<\/jats:italic>\n                      &lt; .001), and pneumonitis (\n                      <jats:italic>P<\/jats:italic>\n                      = .003) while yielding similar specificities (93.7%\n                      <jats:italic>v<\/jats:italic>\n                      92.4%). The LLM spent an average of 9.53 seconds\/chart in comparison with an estimated 15 minutes for adjudication. In the validation cohort (N = 1,270), the mean LLM sensitivity and specificity were 98.1% and 95.7%, respectively.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>CONCLUSION<\/jats:title>\n                    <jats:p>LLMs are a useful tool for the detection of irAEs, outperforming ICD codes in sensitivity and adjudication in efficiency.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1200\/jco.24.00326","type":"journal-article","created":{"date-parts":[[2024,9,3]],"date-time":"2024-09-03T16:01:19Z","timestamp":1725379279000},"page":"4134-4144","update-policy":"https:\/\/doi.org\/10.1200\/crossmark","source":"Crossref","is-referenced-by-count":41,"title":["Enhancing Precision in Detecting Severe Immune-Related Adverse Events: Comparative Analysis of Large Language Models and International Classification of Disease Codes in Patient Records"],"prefix":"10.1200","volume":"42","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1387-2994","authenticated-orcid":true,"given":"Virginia H.","family":"Sun","sequence":"first","affiliation":[{"name":"Harvard Medical School, Boston, MA"},{"name":"Cardiovascular Imaging Research Center, Massachusetts General Hospital, Boston, MA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6892-5227","authenticated-orcid":true,"given":"Julius C.","family":"Heemelaar","sequence":"additional","affiliation":[{"name":"Harvard Medical School, Boston, MA"},{"name":"Cardiovascular Imaging Research Center, Massachusetts General Hospital, Boston, MA"},{"name":"Leiden University Medical Center, Leiden, the Netherlands"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8397-5940","authenticated-orcid":true,"given":"Ibrahim","family":"Hadzic","sequence":"additional","affiliation":[{"name":"Harvard Medical School, Boston, MA"},{"name":"Artificial Intelligence in Medicine (AIM) Program, Mass General Brigham, Boston, MA"},{"name":"Brigham and Women's Hospital, Boston, MA"},{"name":"Maastricht University, Maastricht, the Netherlands"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3524-3945","authenticated-orcid":true,"given":"Vineet K.","family":"Raghu","sequence":"additional","affiliation":[{"name":"Harvard Medical School, Boston, MA"},{"name":"Cardiovascular Imaging Research Center, Massachusetts General Hospital, Boston, MA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chia-Yun","family":"Wu","sequence":"additional","affiliation":[{"name":"Division of Hematology and Oncology, Department of Medicine, Massachusetts General Hospital, Boston, MA"},{"name":"Far Eastern Memorial Hospital, New Taipei City, Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4226-7443","authenticated-orcid":true,"given":"Leyre","family":"Zubiri","sequence":"additional","affiliation":[{"name":"Harvard Medical School, Boston, MA"},{"name":"Division of Hematology and Oncology, Department of Medicine, Massachusetts General Hospital, Boston, MA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Azin","family":"Ghamari","sequence":"additional","affiliation":[{"name":"Harvard Medical School, Boston, MA"},{"name":"Cardiovascular Imaging Research Center, Massachusetts General Hospital, Boston, MA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8264-834X","authenticated-orcid":true,"given":"Nicole R.","family":"LeBoeuf","sequence":"additional","affiliation":[{"name":"Harvard Medical School, Boston, MA"},{"name":"Department of Dermatology, Brigham and Women's Hospital, Boston, MA"},{"name":"Center for Cutaneous Oncology, Dana-Farber Cancer Institute, Boston, MA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3904-2673","authenticated-orcid":true,"given":"Osama","family":"Abu-Shawer","sequence":"additional","affiliation":[{"name":"Department of Internal Medicine, Cleveland Clinic, Cleveland, OH"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5339-9797","authenticated-orcid":true,"given":"Kenneth L.","family":"Kehl","sequence":"additional","affiliation":[{"name":"Harvard Medical School, Boston, MA"},{"name":"Division of Population Sciences, Dana-Farber Cancer Institute, Boston, MA"},{"name":"Department of Medical Oncology, Dana-Farber Cancer Institute, Boston, MA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6268-6843","authenticated-orcid":true,"given":"Shilpa","family":"Grover","sequence":"additional","affiliation":[{"name":"Harvard Medical School, Boston, MA"},{"name":"Division of Gastroenterology, Hepatology, and Endoscopy, Brigham and Women's Hospital, Boston, MA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Prabhsimranjot","family":"Singh","sequence":"additional","affiliation":[{"name":"Harvard Medical School, Boston, MA"},{"name":"Department of Medical Oncology, Dana-Farber Cancer Institute, Boston, MA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4274-2761","authenticated-orcid":true,"given":"Giselle A.","family":"Suero-Abreu","sequence":"additional","affiliation":[{"name":"Harvard Medical School, Boston, MA"},{"name":"Cardiovascular Imaging Research Center, Massachusetts General Hospital, Boston, MA"},{"name":"Division of Cardiology, Massachusetts General Hospital, Boston, MA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-3611-8492","authenticated-orcid":true,"given":"Jessica","family":"Wu","sequence":"additional","affiliation":[{"name":"Harvard Medical School, Boston, MA"},{"name":"Cardiovascular Imaging Research Center, Massachusetts General Hospital, Boston, MA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9201-6998","authenticated-orcid":true,"given":"Ayo S.","family":"Falade","sequence":"additional","affiliation":[{"name":"Internal Medicine Department, Massachusetts General Brigham Salem Hospital, Salem, MA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kelley","family":"Grealish","sequence":"additional","affiliation":[{"name":"Division of Hematology and Oncology, Department of Medicine, Massachusetts General Hospital, Boston, MA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Molly F.","family":"Thomas","sequence":"additional","affiliation":[{"name":"Division of Gastroenterology, Oregon Health and Science University, Portland, OR"},{"name":"Department of Medicine, Oregon Health and Science University, Portland, OR"},{"name":"Department of Cell, Developmental, and Cancer Biology, Oregon Health and Science University, Portland, OR"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-2428-9367","authenticated-orcid":true,"given":"Nora","family":"Hathaway","sequence":"additional","affiliation":[{"name":"Division of Hematology and Oncology, Department of Medicine, Massachusetts General Hospital, Boston, MA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2558-0449","authenticated-orcid":true,"given":"Benjamin D.","family":"Medoff","sequence":"additional","affiliation":[{"name":"Harvard Medical School, Boston, MA"},{"name":"Division of Pulmonary and Critical Care Medicine, Massachusetts General Hospital, Boston, MA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hannah K.","family":"Gilman","sequence":"additional","affiliation":[{"name":"Harvard Medical School, Boston, MA"},{"name":"Cardiovascular Imaging Research Center, Massachusetts General Hospital, Boston, MA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7461-0408","authenticated-orcid":true,"given":"Alexandra-Chloe","family":"Villani","sequence":"additional","affiliation":[{"name":"Harvard Medical School, Boston, MA"},{"name":"Center for Immunology and Inflammatory Diseases (CIID), Massachusetts General Hospital Krantz Family Center for Cancer Research, Boston, MA"},{"name":"Broad Institute of MIT and Harvard, Cambridge, MA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jor Sam","family":"Ho","sequence":"additional","affiliation":[{"name":"Harvard Medical School, Boston, MA"},{"name":"Cardiovascular Imaging Research Center, Massachusetts General Hospital, Boston, MA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8289-8015","authenticated-orcid":true,"given":"Meghan J.","family":"Mooradian","sequence":"additional","affiliation":[{"name":"Harvard Medical School, Boston, MA"},{"name":"Division of Hematology and Oncology, Department of Medicine, Massachusetts General Hospital, Boston, MA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4327-9713","authenticated-orcid":true,"given":"Meghan E.","family":"Sise","sequence":"additional","affiliation":[{"name":"Harvard Medical School, Boston, MA"},{"name":"Division of Nephrology, Massachusetts General Hospital, Boston, MA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9007-7295","authenticated-orcid":true,"given":"Daniel A.","family":"Zlotoff","sequence":"additional","affiliation":[{"name":"Harvard Medical School, Boston, MA"},{"name":"Division of Cardiology, Massachusetts General Hospital, Boston, MA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6030-7192","authenticated-orcid":true,"given":"Steven M.","family":"Blum","sequence":"additional","affiliation":[{"name":"Harvard Medical School, Boston, MA"},{"name":"Division of Hematology and Oncology, Department of Medicine, Massachusetts General Hospital, Boston, MA"},{"name":"Center for Immunology and Inflammatory Diseases (CIID), Massachusetts General Hospital Krantz Family Center for Cancer Research, Boston, MA"},{"name":"Broad Institute of MIT and Harvard, Cambridge, MA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9266-2009","authenticated-orcid":true,"given":"Michael","family":"Dougan","sequence":"additional","affiliation":[{"name":"Harvard Medical School, Boston, MA"},{"name":"Division of Gastroenterology, Massachusetts General Hospital, Boston, MA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ryan J.","family":"Sullivan","sequence":"additional","affiliation":[{"name":"Harvard Medical School, Boston, MA"},{"name":"Division of Hematology and Oncology, Department of Medicine, Massachusetts General Hospital, Boston, MA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1513-8833","authenticated-orcid":true,"given":"Tomas G.","family":"Neilan","sequence":"additional","affiliation":[{"name":"Harvard Medical School, Boston, MA"},{"name":"Cardiovascular Imaging Research Center, Massachusetts General Hospital, Boston, MA"},{"name":"Division of Cardiology, Massachusetts General Hospital, Boston, MA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7793-654X","authenticated-orcid":true,"given":"Kerry L.","family":"Reynolds","sequence":"additional","affiliation":[{"name":"Harvard Medical School, Boston, MA"},{"name":"Division of Hematology and Oncology, Department of Medicine, Massachusetts General Hospital, Boston, MA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"233","reference":[{"key":"e_1_3_7_2_2","doi-asserted-by":"publisher","DOI":"10.1056\/NEJMsb2300232"},{"key":"e_1_3_7_3_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41571-022-00600-w"},{"key":"e_1_3_7_4_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41573-023-00723-4"},{"key":"e_1_3_7_5_2","doi-asserted-by":"publisher","DOI":"10.1136\/jitc-2021-002896"},{"key":"e_1_3_7_6_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41571-021-00597-8"},{"key":"e_1_3_7_7_2","article-title":"Automated identification of patients with immune-related adverse events from clinical notes using word embedding and machine learning","author":"Gupta S","unstructured":"Gupta S, Belouali A, Shah NJ, et al: Automated identification of patients with immune-related adverse events from clinical notes using word embedding and machine learning. JCO Clin Cancer Inform 10.1200\/CCI.20.00109","journal-title":"JCO Clin Cancer Inform"},{"key":"e_1_3_7_8_2","first-page":"311","article-title":"Corrigendum: Current diagnosis and management of immune related adverse events (irAEs) induced by immune checkpoint inhibitor therapy","volume":"8","author":"Kumar V","year":"2017","unstructured":"Kumar V, Chaudhary N, Garg M, et al: Corrigendum: Current diagnosis and management of immune related adverse events (irAEs) induced by immune checkpoint inhibitor therapy. Front Pharmacol 8:311, 2017","journal-title":"Front Pharmacol"},{"key":"e_1_3_7_9_2","doi-asserted-by":"publisher","DOI":"10.1634\/theoncologist.2018-0130"},{"key":"e_1_3_7_10_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.jacc.2018.02.037"},{"key":"e_1_3_7_11_2","article-title":"The role of natural language processing techniques versus conventional methods to gain ICI safety insights from unstructured EHR data","author":"Block MS","unstructured":"Block MS, Barman H, Venkateswaran S, et al: The role of natural language processing techniques versus conventional methods to gain ICI safety insights from unstructured EHR data. JCO Glob Oncol 10.1200\/GO.2023.9.Supplement_1.136","journal-title":"JCO Glob Oncol"},{"key":"e_1_3_7_12_2","doi-asserted-by":"publisher","DOI":"10.1002\/onco.13740"},{"key":"e_1_3_7_13_2","doi-asserted-by":"crossref","unstructured":"Zubiri L Molina GE Mooradian M et al: Impact of multidisciplinary severe immunotherapy complication service on outcomes for cancer patients receiving immune checkpoint inhibition. J Clin Oncol 39:2654 2021 (abstr 2654)","DOI":"10.1200\/JCO.2021.39.15_suppl.2654"},{"key":"e_1_3_7_14_2","doi-asserted-by":"publisher","DOI":"10.1136\/jamia.2010.008607"},{"key":"e_1_3_7_15_2","doi-asserted-by":"publisher","DOI":"10.1210\/jendso\/bvad019"},{"key":"e_1_3_7_16_2","doi-asserted-by":"publisher","DOI":"10.1136\/jitc-2022-004670"},{"key":"e_1_3_7_17_2","doi-asserted-by":"publisher","DOI":"10.1007\/s00415-023-11667-5"},{"key":"e_1_3_7_18_2","doi-asserted-by":"publisher","DOI":"10.1007\/s00262-021-02880-0"},{"key":"e_1_3_7_19_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-023-27578-4"},{"key":"e_1_3_7_20_2","doi-asserted-by":"publisher","DOI":"10.1080\/2162402X.2023.2188719"},{"key":"e_1_3_7_21_2","doi-asserted-by":"publisher","DOI":"10.1186\/s12885-023-10701-z"},{"key":"e_1_3_7_22_2","doi-asserted-by":"publisher","DOI":"10.1093\/jamia\/ocy068"},{"key":"e_1_3_7_23_2","first-page":"345","article-title":"Quantification of BERT diagnosis generalizability across medical specialties using semantic dataset distance","volume":"2021","author":"Khambete MP","year":"2021","unstructured":"Khambete MP, Su W, Garcia JC, et al: Quantification of BERT diagnosis generalizability across medical specialties using semantic dataset distance. AMIA Jt Summits Transl Sci Proc 2021:345-354, 2021","journal-title":"AMIA Jt Summits Transl Sci Proc"},{"key":"e_1_3_7_24_2","doi-asserted-by":"publisher","DOI":"10.3389\/fphar.2023.1218679"},{"key":"e_1_3_7_25_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41591-023-02448-8"},{"key":"e_1_3_7_26_2","doi-asserted-by":"publisher","DOI":"10.1161\/CIRCULATIONAHA.119.044703"},{"key":"e_1_3_7_27_2","doi-asserted-by":"publisher","DOI":"10.1001\/jamaoncol.2018.3923"},{"key":"e_1_3_7_28_2","first-page":"1044","article-title":"Calculating the benefits of a research patient data repository","volume":"2006","author":"Nalichowski R","year":"2006","unstructured":"Nalichowski R, Keogh D, Chueh HC, et al: Calculating the benefits of a research patient data repository. AMIA Annu Symp Proc 2006:1044, 2006","journal-title":"AMIA Annu Symp Proc"},{"key":"e_1_3_7_29_2","unstructured":"EIO: Massachusetts General Hospital: Digitizing patient care. https:\/\/d3.harvard.edu\/platform-digit\/submission\/massachusetts-general-hospital-digitizing-patient-care\/"},{"key":"e_1_3_7_30_2","article-title":"Severe immune-related adverse effects (irAE) requiring hospital admission in patients treated with immune checkpoint inhibitors for advanced malignancy: Temporal trends and clinical significance","volume":"36","author":"Reynolds KL","year":"2018","unstructured":"Reynolds KL, Cohen JV, Ryan DP, et al: Severe immune-related adverse effects (irAE) requiring hospital admission in patients treated with immune checkpoint inhibitors for advanced malignancy: Temporal trends and clinical significance. J Clin Oncol 36, 2018 (suppl 15; abstr 3096)","journal-title":"J Clin Oncol"},{"key":"e_1_3_7_31_2","doi-asserted-by":"publisher","DOI":"10.1634\/theoncologist.2018-0883"},{"key":"e_1_3_7_32_2","doi-asserted-by":"publisher","DOI":"10.1200\/JCO.2017.77.6385"},{"key":"e_1_3_7_33_2","doi-asserted-by":"publisher","DOI":"10.1200\/JCO.21.01440"},{"key":"e_1_3_7_34_2","doi-asserted-by":"publisher","DOI":"10.6004\/jnccn.2022.0020"},{"key":"e_1_3_7_35_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.annonc.2022.10.001"},{"key":"e_1_3_7_36_2","doi-asserted-by":"publisher","DOI":"10.1136\/jitc-2021-002435"},{"key":"e_1_3_7_37_2","doi-asserted-by":"publisher","DOI":"10.1002\/cam4.2397"},{"key":"e_1_3_7_38_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.cgh.2023.12.011"},{"key":"e_1_3_7_39_2","unstructured":"ICD10Data.com: The Web's free 2024 ICD-10-CM\/PCS medical coding reference. ICD10Data.com"},{"key":"e_1_3_7_40_2","first-page":"9459","article-title":"Retrieval-augmented generation for knowledge-intensive NLP tasks","volume":"33","author":"Lewis P","year":"2020","unstructured":"Lewis P, Perez E, Piktus A, et al: Retrieval-augmented generation for knowledge-intensive NLP tasks. Adv Neural Inf Process Syst 33:9459-9474, 2020","journal-title":"Adv Neural Inf Process Syst"},{"key":"e_1_3_7_41_2","doi-asserted-by":"publisher","unstructured":"Kessler JS: Scattertext: A browser-based tool for visualizing how corpora differ. arXiv 10.48550\/arXiv.1703.00565","DOI":"10.48550\/arXiv.1703.00565"},{"key":"e_1_3_7_42_2","doi-asserted-by":"publisher","DOI":"10.1136\/jitc-2020-000992"},{"key":"e_1_3_7_43_2","unstructured":"Stock C Hielscher T Discacciati A: DTComPair: Comparison of binary diagnostic tests in a paired study design. R package version 1.2.2; 2023."},{"key":"e_1_3_7_44_2","unstructured":"Morgan J Yang M MacDonald B et al: Ollama.ai version 0.1.25 2024. https:\/\/ollama.ai\/"},{"key":"e_1_3_7_45_2","unstructured":"Alignment Lab: Mistral-7B-OpenOrca. https:\/\/huggingface.co\/Open-Orca\/Mistral-7B-OpenOrca"},{"key":"e_1_3_7_46_2","unstructured":"IBM Data and AI Team: Open source large language models: Benefits risks and types. https:\/\/www.ibm.com\/blog\/open-source-large-language-models-benefits-risks-and-types\/"},{"key":"e_1_3_7_47_2","doi-asserted-by":"publisher","unstructured":"Thompson WE Vidmar DM De Freitas JK et al: Large language models with retrieval-augmented generation for zero-shot disease phenotyping. arXiv 10.48550\/arXiv.2312.06457","DOI":"10.48550\/arXiv.2312.06457"},{"key":"e_1_3_7_48_2","doi-asserted-by":"publisher","unstructured":"Chen Z Cano AH Romanou A et al: MEDITRON-70B: Scaling medical pretraining for large language models. arXiv 10.48550\/arXiv.2311.16079","DOI":"10.48550\/arXiv.2311.16079"}],"container-title":["Journal of Clinical Oncology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/ascopubs.org\/doi\/pdfdirect\/10.1200\/JCO.24.00326","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,5]],"date-time":"2024-12-05T17:59:35Z","timestamp":1733421575000},"score":1,"resource":{"primary":{"URL":"https:\/\/ascopubs.org\/doi\/10.1200\/JCO.24.00326"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,10]]},"references-count":47,"journal-issue":{"issue":"35","published-print":{"date-parts":[[2024,12,10]]}},"alternative-id":["10.1200\/JCO.24.00326"],"URL":"https:\/\/doi.org\/10.1200\/jco.24.00326","relation":{},"ISSN":["0732-183X","1527-7755"],"issn-type":[{"value":"0732-183X","type":"print"},{"value":"1527-7755","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,12,10]]},"assertion":[{"value":"2024-02-15","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-05-20","order":1,"name":"revised","label":"Revised","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-06-24","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-09-03","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}