{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,4]],"date-time":"2026-11-04T07:16:25Z","timestamp":1793776585814,"version":"4.6.1"},"reference-count":32,"publisher":"American Association for Cancer Research (AACR)","issue":"4","license":[{"start":{"date-parts":[[2024,4,9]],"date-time":"2024-04-09T00:00:00Z","timestamp":1712620800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100000002","name":"HHS | National Institutes of Health","doi-asserted-by":"publisher","award":["P30 CA 008748"],"award-info":[{"award-number":["P30 CA 008748"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["aacrjournals.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,4,9]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title\/>\n                    <jats:p>Cancer research is dependent on accurate and relevant information of patient's medical journey. Data in radiology reports are of extreme value but lack consistent structure for direct use in analytics. At Memorial Sloan Kettering Cancer Center (MSKCC), the radiology reports are curated using gold-standard approach of using human annotators. However, the manual process of curating large volume of retrospective data slows the pace of cancer research. Manual curation process is sensitive to volume of reports, number of data elements and nature of reports and demand appropriate skillset. In this work, we explore state of the art methods in artificial intelligence (AI) and implement end-to-end pipeline for fast and accurate annotation of radiology reports. Language models (LM) are trained using curated data by approaching curation as multiclass or multilabel classification problem. The classification tasks are to predict multiple imaging scan sites, presence of cancer and cancer status from the reports. The trained natural language processing (NLP) model classifiers achieve high weighted F1 score and accuracy. We propose and demonstrate the use of these models to assist in the manual curation process which results in higher accuracy and F1 score with lesser time and cost, thus improving efforts of cancer research.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Significance:<\/jats:title>\n                    <jats:p>Extraction of structured data in radiology for cancer research with manual process is laborious. Using AI for extraction of data elements is achieved using NLP models\u2019 assistance is faster and more accurate.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1158\/2767-9764.crc-24-0064","type":"journal-article","created":{"date-parts":[[2024,4,9]],"date-time":"2024-04-09T11:02:05Z","timestamp":1712660525000},"page":"1041-1049","update-policy":"https:\/\/doi.org\/10.1158\/crossmark_policy","source":"Crossref","is-referenced-by-count":10,"title":["Artificial Intelligence\u2013Assisted Cancer Status Detection in Radiology Reports"],"prefix":"10.1158","volume":"4","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3901-7822","authenticated-orcid":true,"given":"Ankur","family":"Arya","sequence":"first","affiliation":[{"name":"1Digital, Informatics and Technology Solutions, Memorial Sloan Kettering Cancer Center, New York, New York."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-9499-2251","authenticated-orcid":true,"given":"Andrew","family":"Niederhausern","sequence":"additional","affiliation":[{"name":"2Department of Translational Informatics, Memorial Sloan Kettering Cancer Center, New York, New York."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2886-3687","authenticated-orcid":true,"given":"Nadia","family":"Bahadur","sequence":"additional","affiliation":[{"name":"3Clinical & Translational Research Informatics, Memorial Sloan Kettering Cancer Center, New York, New York."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5752-6212","authenticated-orcid":true,"given":"Neil J.","family":"Shah","sequence":"additional","affiliation":[{"name":"4Department of Medicine, Memorial Sloan Kettering Cancer Center, New York, New York."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-4367-2569","authenticated-orcid":true,"given":"Chelsea","family":"Nichols","sequence":"additional","affiliation":[{"name":"4Department of Medicine, Memorial Sloan Kettering Cancer Center, New York, New York."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0492-4839","authenticated-orcid":true,"given":"Avijit","family":"Chatterjee","sequence":"additional","affiliation":[{"name":"1Digital, Informatics and Technology Solutions, Memorial Sloan Kettering Cancer Center, New York, New York."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0535-7178","authenticated-orcid":true,"given":"John","family":"Philip","sequence":"additional","affiliation":[{"name":"3Clinical & Translational Research Informatics, Memorial Sloan Kettering Cancer Center, New York, New York."}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1086","published-online":{"date-parts":[[2024,4,9]]},"reference":[{"key":"2024040915014937800_bib1","doi-asserted-by":"crossref","first-page":"e18755","DOI":"10.1200\/JCO.2021.39.15_suppl.e18755","article-title":"A comprehensive Memorial Sloan Kettering Cancer Center real-world data model: core clinical data elements","volume":"39","author":"Shah","year":"2021","journal-title":"J Clin Oncol"},{"key":"2024040915014937800_bib2","article-title":"GENIE: Real-world application","author":"Schrag","year":"2018"},{"key":"2024040915014937800_bib3","doi-asserted-by":"crossref","first-page":"818","DOI":"10.1158\/2159-8290.CD-17-0151","article-title":"AACR project GENIE: powering precision medicine through an international consortium","volume":"7","author":"AACR Project GENIE Consortium","year":"2017","journal-title":"Cancer Discov"},{"key":"2024040915014937800_bib4","doi-asserted-by":"crossref","first-page":"982","DOI":"10.1016\/j.cell.2017.10.032","article-title":"Core clinical data elements for cancer genomic repositories: a multi-stakeholder consensus","volume":"171","author":"Conley","year":"2017","journal-title":"Cell"},{"key":"2024040915014937800_bib5","doi-asserted-by":"crossref","first-page":"104779","DOI":"10.1016\/j.ijmedinf.2022.104779","article-title":"Applications of natural language processing in radiology: a systematic review","volume":"163","author":"Linna","year":"2022","journal-title":"Int J Med Informat"},{"key":"2024040915014937800_bib6","doi-asserted-by":"crossref","first-page":"734","DOI":"10.2214\/AJR.18.19869","article-title":"Automatic disease annotation from radiology reports using artificial intelligence implemented by a recurrent neural network","volume":"212","author":"Lee","year":"2019","journal-title":"Am J Roentgenol"},{"key":"2024040915014937800_bib7","article-title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","author":"Devlin","year":"2018"},{"key":"2024040915014937800_bib8","doi-asserted-by":"crossref","first-page":"20220769","DOI":"10.1259\/bjr.20220769","article-title":"Transformer versus traditional natural language processing: how much data is enough for automated radiology report classification?","volume":"96","author":"Yang","year":"2023","journal-title":"Br J Radiol"},{"key":"2024040915014937800_bib9","doi-asserted-by":"crossref","DOI":"10.18653\/v1\/D19-1371","article-title":"SciBERT: A Pretrained Language model for Scientific text","author":"Beltagy","year":"2019"},{"key":"2024040915014937800_bib10","doi-asserted-by":"crossref","first-page":"1234","DOI":"10.1093\/bioinformatics\/btz682","article-title":"BioBERT: a pre-trained biomedical language representation model for biomedical text mining","volume":"36","author":"Lee","year":"2019","journal-title":"Bioinformatics"},{"key":"2024040915014937800_bib11","first-page":"e210258","article-title":"RadBERT: Adapting transformer-based language models to Radiology","volume":"4","author":"Yan","year":"2022","journal-title":"Radiology"},{"key":"2024040915014937800_bib12","article-title":"ClinicalBERT: Modeling clinical notes and predicting hospital readmission","author":"Huang","year":"2019"},{"key":"2024040915014937800_bib13","doi-asserted-by":"crossref","first-page":"86","DOI":"10.1038\/s41746-021-00455-y","article-title":"Med-BERT: pretrained contextualized embeddings on large-scale structured electronic health records for disease prediction","volume":"4","author":"Rasmy","year":"2021","journal-title":"NPJ Digit Med"},{"key":"2024040915014937800_bib14","doi-asserted-by":"crossref","first-page":"194","DOI":"10.1038\/s41746-022-00742-2","article-title":"A large language model for electronic health records","volume":"5","author":"Yang","year":"2022","journal-title":"NPJ Digit Med"},{"key":"2024040915014937800_bib15","first-page":"e220055","article-title":"Deep learning\u2013based assessment of oncologic outcomes from natural language processing of structured radiology reports","volume":"4","author":"Fink","year":"2022","journal-title":"Radiology"},{"key":"2024040915014937800_bib16","first-page":"e220007","article-title":"Performance of multiple pretrained BERT models to automate and accelerate data annotation for large datasets","volume":"4","author":"Tejani","year":"2022","journal-title":"Radiology"},{"key":"2024040915014937800_bib17","doi-asserted-by":"crossref","first-page":"4909","DOI":"10.3390\/cancers15204909","article-title":"Applying natural language processing to single-report prediction of metastatic disease response using the OR-RADS lexicon","volume":"15","author":"Elbatarny","year":"2023","journal-title":"Cancers"},{"key":"2024040915014937800_bib18","article-title":"Alpaca: a strong, replicable instruction-following model","author":"Taori","year":"2023"},{"key":"2024040915014937800_bib19","article-title":"Vicuna: an open-source chatbot impressing GPT-4 with 90%* ChatGPT quality","author":"Chiang","year":"2023"},{"key":"2024040915014937800_bib20","article-title":"Llama 2: Open foundation and Fine-Tuned chat models","author":"Touvron","year":"2023"},{"key":"2024040915014937800_bib21","article-title":"GPT-4 Technical report","author":"OpenAI","year":"2023"},{"key":"2024040915014937800_bib22","article-title":"Gemini technical report","author":"Google","year":"2023"},{"key":"2024040915014937800_bib23","doi-asserted-by":"crossref","first-page":"172","DOI":"10.1038\/s41586-023-06291-2","article-title":"Large language models encode clinical knowledge","volume":"620","author":"Singhal","year":"2023","journal-title":"Nature"},{"key":"2024040915014937800_bib24","article-title":"MEDITRON-70B: scaling medical pretraining for large language models","author":"Chen","year":"2023"},{"key":"2024040915014937800_bib25","doi-asserted-by":"crossref","first-page":"1930","DOI":"10.1038\/s41591-023-02448-8","article-title":"Large language models in medicine","volume":"29","author":"Thirunavukarasu","year":"2023","journal-title":"Nat Med"},{"key":"2024040915014937800_bib26","doi-asserted-by":"crossref","first-page":"e231362","DOI":"10.1148\/radiol.231362","article-title":"Potential of ChatGPT and GPT-4 for data mining of Free-Text CT reports on lung cancer","volume":"308","author":"Fink","year":"2023","journal-title":"Radiology"},{"key":"2024040915014937800_bib27","doi-asserted-by":"crossref","first-page":"e231147","DOI":"10.1148\/radiol.231147","article-title":"Feasibility of using the privacy-preserving large language model Vicuna for labeling radiology reports","volume":"309","author":"Mukherjee","year":"2023","journal-title":"Radiology"},{"key":"2024040915014937800_bib28","doi-asserted-by":"crossref","first-page":"210","DOI":"10.1038\/s41746-023-00958-w","article-title":"A study of generative large language model for medical research and healthcare","volume":"6","author":"Peng","year":"2023","journal-title":"NPJ Digit Med"},{"key":"2024040915014937800_bib29","article-title":"A survey of large language models in medicine: progress, application, and challenge","author":"Zhou","year":"2023"},{"key":"2024040915014937800_bib30","author":"Google"},{"key":"2024040915014937800_bib31","first-page":"4768","article-title":"A unified approach to interpreting model predictions","volume":"30","author":"Lundberg","year":"2017","journal-title":"Neural Informat Process Sys"},{"key":"2024040915014937800_bib32","article-title":"Database HSM-CXR. (version 2.0.0)","author":"Johnson","year":"2019","journal-title":"PhysioNet"}],"container-title":["Cancer Research Communications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/aacrjournals.org\/cancerrescommun\/article-pdf\/4\/4\/1041\/3441057\/crc-24-0064.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/aacrjournals.org\/cancerrescommun\/article-pdf\/4\/4\/1041\/3441057\/crc-24-0064.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,4,9]],"date-time":"2024-04-09T11:02:21Z","timestamp":1712660541000},"score":1,"resource":{"primary":{"URL":"https:\/\/aacrjournals.org\/cancerrescommun\/article\/4\/4\/1041\/742961\/Artificial-Intelligence-Assisted-Cancer-Status"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,9]]},"references-count":32,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2024,4,9]]}},"URL":"https:\/\/doi.org\/10.1158\/2767-9764.crc-24-0064","relation":{"has-preprint":[{"id-type":"doi","id":"10.1158\/2767-9764.c.7172905.v1","asserted-by":"object"},{"id-type":"doi","id":"10.1158\/2767-9764.c.7172905","asserted-by":"object"}],"is-supplemented-by":[{"id-type":"doi","id":"10.1158\/2767-9764.25569286","asserted-by":"object"},{"id-type":"doi","id":"10.1158\/2767-9764.25569283","asserted-by":"object"},{"id-type":"doi","id":"10.1158\/2767-9764.25569292","asserted-by":"object"},{"id-type":"doi","id":"10.1158\/2767-9764.25569289.v1","asserted-by":"object"},{"id-type":"doi","id":"10.1158\/2767-9764.25569280","asserted-by":"object"},{"id-type":"doi","id":"10.1158\/2767-9764.25569280.v1","asserted-by":"object"},{"id-type":"doi","id":"10.1158\/2767-9764.25569286.v1","asserted-by":"object"},{"id-type":"doi","id":"10.1158\/2767-9764.25569283.v1","asserted-by":"object"},{"id-type":"doi","id":"10.1158\/2767-9764.25569277.v1","asserted-by":"object"},{"id-type":"doi","id":"10.1158\/2767-9764.25569292.v1","asserted-by":"object"},{"id-type":"doi","id":"10.1158\/2767-9764.25569289","asserted-by":"object"},{"id-type":"doi","id":"10.1158\/2767-9764.25569277","asserted-by":"object"}]},"ISSN":["2767-9764"],"issn-type":[{"value":"2767-9764","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,4,9]]}}}