{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,7]],"date-time":"2026-08-07T16:57:50Z","timestamp":1786121870445,"version":"build-2736575974"},"reference-count":20,"publisher":"Scientific Scholar","content-domain":{"domain":["cytojournal.com"],"crossmark-restriction":true},"short-container-title":["Cytojournal"],"abstract":"\n Objectives:<\/jats:title>\n Cytopathology laboratories are required to track diagnostic category distributions as part of quality control (QC) under Clinical Laboratory Improvement Amendments regulations. This process is typically manual, time-consuming, and prone to inconsistency. We evaluated whether a large language model (LLM) could accurately and efficiently categorize cytopathology reports to support regulatory QC processes.<\/jats:p>\n <\/jats:sec>\n \n Material and Methods:<\/jats:title>\n A total of 472 fine needle aspiration and non-gynecologic (NG) cytology reports from 1\u201331 January 2024 were processed using DeepSeek-R1:32B, a locally deployed open-source LLM. GYN cytology reports were excluded because their diagnostic categories are already captured as discrete data in our laboratory information system, eliminating the need for natural language processing. The model extracted the final diagnosis, diagnostic category, and confidence score from each report. A board-certified cytopathologist independently reviewed all cases to serve as the ground truth. Cases were categorized as correct or incorrect. Time required for manual versus artificial intelligence (AI)-assisted review was also measured.<\/jats:p>\n <\/jats:sec>\n \n Results:<\/jats:title>\n The model achieved 98.5% categorization agreement (95% confidence interval: 97.0\u201399.3%; Cohen\u2019s Kappa = 0.973) with expert review (465\/472 cases were classified as correct), with only 1.5% (7\/472) raw misclassifications. Most misclassifications were due to semantic ambiguity, missing context, or institutional interpretation conventions. The pipeline implemented a human-in-the-loop mechanism by flagging low-confidence or non-standard outputs for manual review, enhancing safety. The AI-assisted workflow reduced total review time by 98.5%, from 279 to 4.15 min.<\/jats:p>\n <\/jats:sec>\n \n Conclusion:<\/jats:title>\n This study demonstrates that LLMs can accurately and safely support cytopathology QC tasks, significantly reducing workload while maintaining reporting consistency. With further development and validation, LLM-powered tools may become integral to pathology workflows across specialties.<\/jats:p>\n <\/jats:sec>","DOI":"10.25259\/cytojournal_192_2025","type":"journal-article","created":{"date-parts":[[2026,8,4]],"date-time":"2026-08-04T12:20:18Z","timestamp":1785846018000},"page":"47","update-policy":"https:\/\/doi.org\/10.25259\/crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Automating fine needle aspiration and non-gynecologic quality control using a large language model: A real-world evaluation of diagnostic accuracy and efficiency"],"prefix":"10.25259","volume":"23","author":[{"given":"Sanskriti","family":"Naik","sequence":"first","affiliation":[{"name":"Department of Pathology and Laboratory Medicine, Penn State Health Milton S. Hershey Medical Center, Hershey, United States,"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Vikas","family":"Nishadham","sequence":"additional","affiliation":[{"name":"Department of Pathology and Laboratory Medicine, Penn State Health Milton S. Hershey Medical Center, Hershey, United States,"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Christopher","family":"Jackson","sequence":"additional","affiliation":[{"name":"Department of Pathology and Laboratory Medicine, Penn State Health Milton S. Hershey Medical Center, Hershey, United States,"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"10894","published-online":{"date-parts":[[2026,8,4]]},"reference":[{"key":"10.25259\/Cytojournal_192_2025\/ref-1","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1159\/000502373","article-title":"Cytopathology comes of age","volume":"64","author":"Baloch","year":"2020","journal-title":"Acta Cytol"},{"key":"10.25259\/Cytojournal_192_2025\/ref-2","doi-asserted-by":"publisher","first-page":"707","DOI":"10.1016\/S0272-2712(18)30779-0","article-title":"Quality control in cytopathology","volume":"6","author":"Erozan","year":"1986","journal-title":"Clin Lab Med"},{"key":"10.25259\/Cytojournal_192_2025\/ref-3","doi-asserted-by":"publisher","first-page":"163","DOI":"10.1186\/s13000-024-01590-2","article-title":"The current troubled state of the global pathology workforce: A concise review","volume":"19","author":"Walsh","year":"2024","journal-title":"Diagn Pathol"},{"key":"10.25259\/Cytojournal_192_2025\/ref-4","doi-asserted-by":"publisher","first-page":"407","DOI":"10.1002\/dc.25281","article-title":"Cytotechnology schools: Future outlook","volume":"52","author":"Rockson","year":"2024","journal-title":"Diagn Cytopathol"},{"key":"10.25259\/Cytojournal_192_2025\/ref-5","doi-asserted-by":"publisher","first-page":"598","DOI":"10.1016\/j.jpurol.2023.07.007","article-title":"ChatGPT and large language model (LLM) chatbots: The current state of acceptability and a proposal for guidelines on utilization in academic medicine","volume":"19","author":"Kim","year":"2023","journal-title":"J Pediatr Urol"},{"key":"10.25259\/Cytojournal_192_2025\/ref-6","doi-asserted-by":"publisher","first-page":"887","DOI":"10.3390\/healthcare11060887","article-title":"ChatGPT utility in healthcare education, research, and practice: Systematic review on the promising perspectives and valid concerns","volume":"11","author":"Sallam","year":"2023","journal-title":"Healthcare (Basel)"},{"key":"10.25259\/Cytojournal_192_2025\/ref-7","doi-asserted-by":"publisher","first-page":"106","DOI":"10.1038\/s41746-024-01079-8","article-title":"A critical assessment of using ChatGPT for extracting structured data from clinical notes","volume":"7","author":"Huang","year":"2024","journal-title":"NPJ Digit Med"},{"key":"10.25259\/Cytojournal_192_2025\/ref-8","doi-asserted-by":"publisher","DOI":"10.1101\/2024.09.02.24312917","article-title":"LLM-AIx: An Open Source Pipeline for Information Extraction from Unstructured Medical Text Based on Privacy Preserving Large Language Models","author":"Wiest","year":"2024","journal-title":"medRxiv [Preprint];"},{"key":"10.25259\/Cytojournal_192_2025\/ref-9","doi-asserted-by":"publisher","first-page":"e64544","DOI":"10.2196\/64544","article-title":"Using large language models to automate data extraction from surgical pathology reports: Retrospective cohort study","volume":"9","author":"Lee","year":"2025","journal-title":"JMIR Form Res"},{"key":"10.25259\/Cytojournal_192_2025\/ref-10","doi-asserted-by":"publisher","first-page":"633","DOI":"10.1038\/s41586-025-09422-z","article-title":"DeepSeek-R1 incentivizes reasoning in LLMs through reinforcement learning","volume":"645","author":"Guo","year":"2025","journal-title":"Nature"},{"key":"10.25259\/Cytojournal_192_2025\/ref-11","article-title":"On Verbalized Confidence Scores for llms","author":"Yang","year":"2024","journal-title":"arXiv [Preprint]"},{"key":"10.25259\/Cytojournal_192_2025\/ref-12","doi-asserted-by":"publisher","first-page":"444","DOI":"10.1111\/cyt.13378","article-title":"Interobserver variability in cytopathology: How much do we agree?","volume":"35","author":"Acanfora","year":"2024","journal-title":"Cytopathology"},{"key":"10.25259\/Cytojournal_192_2025\/ref-13","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1002\/dc.24900","article-title":"The international system for serous fluid cytopathology: Interobserver agreement","volume":"50","author":"Layfield","year":"2021","journal-title":"Diagn Cytopathol"},{"key":"10.25259\/Cytojournal_192_2025\/ref-14","doi-asserted-by":"publisher","first-page":"17","DOI":"10.4103\/cytojournal.cytojournal_12_17","article-title":"Interobserver reproducibility of the paris system for reporting urinary cytology","volume":"14","author":"Long","year":"2017","journal-title":"Cytojournal"},{"key":"10.25259\/Cytojournal_192_2025\/ref-15","doi-asserted-by":"publisher","first-page":"74","DOI":"10.1007\/s10916-024-02098-4","article-title":"Effectiveness of artificial intelligence (AI) in clinical decision support systems and care delivery","volume":"48","author":"Ouanes","year":"2024","journal-title":"J Med Syst"},{"key":"10.25259\/Cytojournal_192_2025\/ref-16","doi-asserted-by":"publisher","first-page":"209","DOI":"10.3857\/roj.2023.00633","article-title":"Developing prompts from large language model for extracting clinical information from pathology and ultrasound reports in breast cancer","volume":"41","author":"Choi","year":"2023","journal-title":"Radiat Oncol J"},{"key":"10.25259\/Cytojournal_192_2025\/ref-17","doi-asserted-by":"publisher","first-page":"AIcs2400943","DOI":"10.1056\/AIcs2400943","article-title":"LLM-mediated data extraction from patient records after radical prostatectomy","volume":"2","author":"Azar","year":"2025","journal-title":"NEJM AI"},{"key":"10.25259\/Cytojournal_192_2025\/ref-18","doi-asserted-by":"publisher","first-page":"100521","DOI":"10.1016\/j.jpi.2025.100521","article-title":"Leveraging large language models for structured information extraction from pathology reports","volume":"19","author":"Balasubramanian","year":"2025","journal-title":"J Pathol Inform"},{"key":"10.25259\/Cytojournal_192_2025\/ref-19","doi-asserted-by":"publisher","first-page":"128","DOI":"10.1055\/s-0038-1638592","article-title":"Extracting information from textual documents in the electronic health record: A review of recent research","volume":"17","author":"Savova","year":"2008","journal-title":"Yearb Med Inform"},{"key":"10.25259\/Cytojournal_192_2025\/ref-20","doi-asserted-by":"publisher","first-page":"31","DOI":"10.1038\/s41591-021-01614-0","article-title":"AI in health and medicine","volume":"28","author":"Rajpurkar","year":"2022","journal-title":"Nat Med"}],"container-title":["Cytojournal"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/cytojournal.com\/automating-fine-needle-aspiration-and-non-gynecologic-quality-control-using-a-large-language-model-a-real-world-evaluation-of-diagnostic-accuracy-and-efficiency\/","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/cytojournal.com\/automating-fine-needle-aspiration-and-non-gynecologic-quality-control-using-a-large-language-model-a-real-world-evaluation-of-diagnostic-accuracy-and-efficiency\/","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,7]],"date-time":"2026-08-07T07:21:22Z","timestamp":1786087282000},"score":1,"resource":{"primary":{"URL":"https:\/\/cytojournal.com\/automating-fine-needle-aspiration-and-non-gynecologic-quality-control-using-a-large-language-model-a-real-world-evaluation-of-diagnostic-accuracy-and-efficiency\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,4]]},"references-count":20,"alternative-id":["10.25259\/Cytojournal_192_2025"],"URL":"https:\/\/doi.org\/10.25259\/cytojournal_192_2025","relation":{},"ISSN":["1742-6413","0974-5963"],"issn-type":[{"value":"1742-6413","type":"electronic"},{"value":"0974-5963","type":"print"}],"subject":[],"published":{"date-parts":[[2026,8,4]]},"article-number":"47"}}