{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,23]],"date-time":"2025-09-23T00:40:45Z","timestamp":1758588045630,"version":"3.44.0"},"reference-count":31,"publisher":"American Society of Clinical Oncology (ASCO)","issue":"9","content-domain":{"domain":["ascopubs.org"],"crossmark-restriction":true},"short-container-title":["JCO Clin Cancer Inform"],"published-print":{"date-parts":[[2025,9]]},"abstract":"<jats:sec>\n            <jats:title>PURPOSE<\/jats:title>\n            <jats:p>This study presents a new method based on regular expressions (ReGex) and artificial intelligence for extracting relevant medical data from clinical reports. This hybrid approach is designed to address the limitations of each technique. The pipeline is evaluated for its effectiveness in extracting key clinical information from prostate cancer medical reports.<\/jats:p>\n          <\/jats:sec>\n          <jats:sec>\n            <jats:title>METHODS<\/jats:title>\n            <jats:p>We developed a hybrid pipeline that combines ReGex for initial data extraction with a Natural Language Inference model for classification. This approach was retrospectively applied to 1,000 reports randomly selected among all consultation reports of patients with prostate cancer treated at the institute, focusing on identifying key clinical information such as rectal bleeding, dysuria, pollakiuria, and hematuria. The model's performance was evaluated using precision, recall, accuracy, F1-score, and Cohen's kappa coefficient.<\/jats:p>\n          <\/jats:sec>\n          <jats:sec>\n            <jats:title>RESULTS<\/jats:title>\n            <jats:p>The pipeline demonstrated high performance, with precision scores ranging from 0.778 to 0.954 and recall consistently high at 0.920 to 1.00. F1-scores indicated balanced accuracy across symptoms, and Cohen's kappa values (0.871 to 0.951) reflected strong agreement with physician-labeled data.<\/jats:p>\n          <\/jats:sec>\n          <jats:sec>\n            <jats:title>CONCLUSION<\/jats:title>\n            <jats:p>The proposed pipeline is both efficient and fast while being computationally lightweight. It achieves high accuracy in extracting medical data from clinical reports, making it an effective and practical tool for clinical research and health care applications.<\/jats:p>\n          <\/jats:sec>","DOI":"10.1200\/cci-25-00130","type":"journal-article","created":{"date-parts":[[2025,9,22]],"date-time":"2025-09-22T20:00:16Z","timestamp":1758571216000},"update-policy":"https:\/\/doi.org\/10.1200\/crossmark","source":"Crossref","is-referenced-by-count":0,"title":["Hybrid ReGex and Natural Language Inference Model as a Zero-Shot Classifier for Extracting Data From Medical Reports"],"prefix":"10.1200","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6666-0210","authenticated-orcid":true,"given":"Nicolas","family":"Wagneur","sequence":"first","affiliation":[{"name":"Radiotherapy Department, Institut de Canc\u00e9rologie de l'Ouest, Nantes-Angers, France"},{"name":"Artificial Intelligence Department, Institut de Canc\u00e9rologie de l'Ouest, Nantes-Angers, France"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Olivier","family":"Capitain","sequence":"additional","affiliation":[{"name":"Oncology Department, Institut de Canc\u00e9rologie de l'Ouest, Nantes-Angers, France"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"St\u00e9phane","family":"Supiot","sequence":"additional","affiliation":[{"name":"Radiotherapy Department, Institut de Canc\u00e9rologie de l'Ouest, Nantes-Angers, France"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2361-1608","authenticated-orcid":true,"given":"Florent","family":"Le Borgne","sequence":"additional","affiliation":[{"name":"Data Factory &amp; Analytics Department, Institut de Canc\u00e9rologie de l'Ouest, Nantes-Angers, France"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-6247-1506","authenticated-orcid":true,"given":"Fran\u00e7ois","family":"Bocquet","sequence":"additional","affiliation":[{"name":"Data Factory &amp; Analytics Department, Institut de Canc\u00e9rologie de l'Ouest, Nantes-Angers, France"},{"name":"Law and Social Change Laboratory, Faculty of Law and Political Sciences, CNRS UMR 6297, Nantes University, Nantes, France"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mario","family":"Campone","sequence":"additional","affiliation":[{"name":"Oncology Department, Institut de Canc\u00e9rologie de l'Ouest, Nantes-Angers, France"},{"name":"Center for Research in Cancerology and Immunology Nantes-Angers, INSERM UMR 1232, Nantes University and Angers University, Nantes-Angers, France"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1118-2271","authenticated-orcid":true,"given":"Tanguy","family":"Perennec","sequence":"additional","affiliation":[{"name":"Radiotherapy Department, Institut de Canc\u00e9rologie de l'Ouest, Nantes-Angers, France"},{"name":"Artificial Intelligence Department, Institut de Canc\u00e9rologie de l'Ouest, Nantes-Angers, France"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"233","reference":[{"key":"e_1_3_4_2_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijmedinf.2007.09.001"},{"key":"e_1_3_4_3_2","doi-asserted-by":"publisher","DOI":"10.1007\/s00530-020-00736-8"},{"key":"e_1_3_4_4_2","doi-asserted-by":"publisher","DOI":"10.1038\/498255a"},{"key":"e_1_3_4_5_2","doi-asserted-by":"publisher","DOI":"10.3390\/ijerph20021645"},{"key":"e_1_3_4_6_2","doi-asserted-by":"publisher","DOI":"10.1007\/s40290-022-00441-z"},{"key":"e_1_3_4_7_2","doi-asserted-by":"publisher","DOI":"10.48101\/ujms.v127.8260"},{"key":"e_1_3_4_8_2","doi-asserted-by":"publisher","DOI":"10.1213\/ANE.0000000000006300"},{"key":"e_1_3_4_9_2","doi-asserted-by":"publisher","DOI":"10.1002\/hcs2.40"},{"key":"e_1_3_4_10_2","volume-title":"Methods in Structural Linguistics","author":"Harris ZS","year":"1951","unstructured":"Harris ZS: Methods in Structural Linguistics. Chicago, IL, University of Chicago Press, 1951"},{"key":"e_1_3_4_11_2","doi-asserted-by":"publisher","DOI":"10.1186\/1472-6947-12-106"},{"key":"e_1_3_4_12_2","article-title":"A scoping review of using large language models (LLMs) to investigate electronic health records (EHRs)","author":"Li L","unstructured":"Li L, Zhou J, Gao Z, et al: A scoping review of using large language models (LLMs) to investigate electronic health records (EHRs), 2024. arxiv. 10.48550\/arXiv.2405.03066","journal-title":"arxiv"},{"key":"e_1_3_4_13_2","doi-asserted-by":"publisher","DOI":"10.1056\/AIdbp2300040"},{"key":"e_1_3_4_14_2","article-title":"A survey of large language models","author":"Zhao WX","unstructured":"Zhao WX, Zhou K, Li J, et al: A survey of large language models. arXiv 10.48550\/arXiv.2303.18223","journal-title":"arXiv"},{"key":"e_1_3_4_15_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPEC58863.2023.10363447"},{"key":"e_1_3_4_16_2","article-title":"Fine-tuned \u201csmall\u201d LLMs (still) significantly outperform zero-shot generative AI models in text classification","author":"Bucher MJJ","unstructured":"Bucher MJJ, Martini M: Fine-tuned \u201csmall\u201d LLMs (still) significantly outperform zero-shot generative AI models in text classification. arXiv 10.48550\/arXiv.2406.08660","journal-title":"arXiv"},{"key":"e_1_3_4_17_2","article-title":"Large language models are few-shot clinical information extractors","author":"Agrawal M","unstructured":"Agrawal M, Hegselmann S, Lang H, et al: Large language models are few-shot clinical information extractors. arXiv 10.48550\/arXiv.2205.12689","journal-title":"arXiv"},{"key":"e_1_3_4_18_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.icte.2023.08.012"},{"key":"e_1_3_4_19_2","article-title":"Benchmarking zero-shot text classification: Datasets, evaluation and entailment approach","author":"Yin W","unstructured":"Yin W, Hay J, Roth D: Benchmarking zero-shot text classification: Datasets, evaluation and entailment approach. arXiv 10.48550\/arXiv.1909.00161","journal-title":"arXiv"},{"key":"e_1_3_4_20_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.dajour.2023.100162"},{"key":"e_1_3_4_21_2","article-title":"BART: Denoising sequence-to-sequence pre-training for natural language generation, translation, and comprehension","author":"Lewis M","unstructured":"Lewis M, Liu Y, Goyal N, et al: BART: Denoising sequence-to-sequence pre-training for natural language generation, translation, and comprehension. arXiv http:\/\/arxiv.org\/abs\/1910.13461","journal-title":"arXiv"},{"key":"e_1_3_4_22_2","doi-asserted-by":"publisher","DOI":"10.1007\/s10579-023-09704-w"},{"key":"e_1_3_4_23_2","article-title":"A broad-coverage challenge corpus for sentence understanding through inference","author":"Williams A","unstructured":"Williams A, Nangia N, Bowman SR: A broad-coverage challenge corpus for sentence understanding through inference. arXiv 10.48550\/arXiv.1704.05426","journal-title":"arXiv"},{"key":"e_1_3_4_24_2","volume-title":"Hugging Face","unstructured":"Hugging Face. https:\/\/huggingface.co\/facebook\/bart-large-mnli\/"},{"key":"e_1_3_4_25_2","article-title":"On the computational complexity of self-attention","author":"Keles FD","unstructured":"Keles FD, Wijewardena PM, Hegde C: On the computational complexity of self-attention. arXiv 10.48550\/arXiv.2209.04881","journal-title":"arXiv"},{"key":"e_1_3_4_26_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41746-024-01079-8"},{"key":"e_1_3_4_27_2","doi-asserted-by":"publisher","DOI":"10.1016\/S2589-7500(24)00114-6"},{"key":"e_1_3_4_28_2","unstructured":"Yu H Yang Z Pelrine K et al: Open closed or small language models for text classification? 10.48550\/arXiv.2308.10092"},{"key":"e_1_3_4_29_2","article-title":"Extracting training data from large language models","author":"Carlini N","unstructured":"Carlini N, Tramer F, Wallace E, et al: Extracting training data from large language models. arXiv 10.48550\/arXiv.2012.07805","journal-title":"arXiv"},{"key":"e_1_3_4_30_2","article-title":"Systematic evaluation of privacy risks of machine learning models","author":"Song L","unstructured":"Song L, Mittal P: Systematic evaluation of privacy risks of machine learning models. arXiv 10.48550\/arXiv.2003.10595","journal-title":"arXiv"},{"key":"e_1_3_4_31_2","doi-asserted-by":"publisher","DOI":"10.1109\/SP.2017.41"},{"key":"e_1_3_4_32_2","doi-asserted-by":"publisher","DOI":"10.1186\/s13326-018-0179-8"}],"container-title":["JCO Clinical Cancer Informatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/ascopubs.org\/doi\/pdfdirect\/10.1200\/CCI-25-00130","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,22]],"date-time":"2025-09-22T20:00:18Z","timestamp":1758571218000},"score":1,"resource":{"primary":{"URL":"https:\/\/ascopubs.org\/doi\/10.1200\/CCI-25-00130"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9]]},"references-count":31,"journal-issue":{"issue":"9","published-print":{"date-parts":[[2025,9]]}},"alternative-id":["10.1200\/CCI-25-00130"],"URL":"https:\/\/doi.org\/10.1200\/cci-25-00130","relation":{},"ISSN":["2473-4276"],"issn-type":[{"value":"2473-4276","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,9]]},"assertion":[{"value":"2025-05-02","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-07-09","order":1,"name":"revised","label":"Revised","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-08-25","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-09-22","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"e2500130"}}