{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,30]],"date-time":"2026-07-30T14:19:34Z","timestamp":1785421174407,"version":"3.56.0"},"reference-count":39,"publisher":"MDPI AG","issue":"11","license":[{"start":{"date-parts":[[2026,5,27]],"date-time":"2026-05-27T00:00:00Z","timestamp":1779840000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100020595","name":"National Science and Technology Council of Taiwan","doi-asserted-by":"crossref","award":["NSTC 113-2221-E-039-017"],"award-info":[{"award-number":["NSTC 113-2221-E-039-017"]}],"id":[{"id":"10.13039\/100020595","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/100020595","name":"National Science and Technology Council of Taiwan","doi-asserted-by":"crossref","award":["NSTC 114-2813-C-039-132-E"],"award-info":[{"award-number":["NSTC 114-2813-C-039-132-E"]}],"id":[{"id":"10.13039\/100020595","id-type":"DOI","asserted-by":"crossref"}]},{"award":["NSTC 113-2221-E-039-017"],"award-info":[{"award-number":["NSTC 113-2221-E-039-017"]}],"id":[{"id":"https:\/\/ror.org\/02kv4zf79","id-type":"ROR","asserted-by":"publisher"}]},{"award":["NSTC 114-2813-C-039-132-E"],"award-info":[{"award-number":["NSTC 114-2813-C-039-132-E"]}],"id":[{"id":"https:\/\/ror.org\/02kv4zf79","id-type":"ROR","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004391","name":"China Medical University Hospital","doi-asserted-by":"publisher","award":["DMR-115-078"],"award-info":[{"award-number":["DMR-115-078"]}],"id":[{"id":"10.13039\/501100004391","id-type":"DOI","asserted-by":"publisher"}]},{"award":["DMR-115-078"],"award-info":[{"award-number":["DMR-115-078"]}],"id":[{"id":"https:\/\/ror.org\/0368s4g32","id-type":"ROR","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Diagnostics"],"abstract":"<jats:p>Background\/Objectives: Free-text surgical pathology reports hinder automated cancer registry entry and secondary analytics. This study introduces a clinically governed schema layer for interoperability, testing whether a locally-deployable Large Language Model (LLM) pipeline can deliver robust registry-grade extraction across institutions. Methods: We developed a College of American Pathologists (CAP)-aligned clinical ontology encompassing 10 cancer types, 192 per-organ scalar fields, key biomarkers, and nested structures for lymph nodes and margins. Encoded via Declarative Self-improving Python (DSPy) signatures with grammar-constrained decoding using DSPy v3.2.1, this model-agnostic pipeline was benchmarked on 893 internal reports against a pathologist-adjudicated gold standard. External validation utilized 242 The Cancer Genome Atlas (TCGA) reports. Hardware feasibility was confirmed on a single 48-gigabyte (GB) Graphics Processing Unit (GPU), ensuring suitability for privacy-preserving on-premises deployment. Results: Using the gpt-oss-20b model, the framework achieved 92.0% macro-mean exact-match accuracy on internal data, demonstrating near-perfect run-to-run reliability. Critical prognostic indicators, including breast estrogen receptor\/progesterone receptor (ER\/PR) (98.7%) and margin positivity (&gt;93%), maintained high fidelity. On the external TCGA cohort, accuracy was 77.5%, rising to 88.0% after excluding structurally silent fields absent in older narratives. Operationally, the model processed reports in 40\u201370 s, optimally balancing speed and accuracy. Conclusions: This schema-first abstraction layer successfully decouples clinical logic from specific Artificial Intelligence (AI) models. By reliably transforming narrative reports into machine-readable structures, it establishes a portable privacy-preserving foundation for automated cancer surveillance, institutional data reuse, and future multimodal clinical systems.<\/jats:p>","DOI":"10.3390\/diagnostics16111644","type":"journal-article","created":{"date-parts":[[2026,5,27]],"date-time":"2026-05-27T11:03:27Z","timestamp":1779879807000},"page":"1644","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Digital Registrar: A Schema-First Framework for Multi-Cancer Privacy-Preserving Pathology Abstraction via Local LLMs"],"prefix":"10.3390","volume":"16","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0277-1947","authenticated-orcid":false,"given":"Nan-Haw","family":"Chow","sequence":"first","affiliation":[{"name":"Center for Precision Medicine, China Medical University Hospital, Taichung 404327, Taiwan"},{"name":"School of Medicine, China Medical University, Taichung 404333, Taiwan"},{"name":"Department of Pathology, China Medical University Hospital, Taichung 404327, Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1664-5770","authenticated-orcid":false,"given":"Han","family":"Chang","sequence":"additional","affiliation":[{"name":"School of Medicine, China Medical University, Taichung 404333, Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hung-Kai","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Medicine, China Medical University, Taichung 404333, Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chen-Yuan","family":"Lin","sequence":"additional","affiliation":[{"name":"Signal 1, Toronto, ON M5R 2E3, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ying-Lung","family":"Liu","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Information Engineering, National Taiwan University of Science and Technology, Taipei 106990, Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Po-Yen","family":"Tseng","sequence":"additional","affiliation":[{"name":"School of Medicine, China Medical University, Taichung 404333, Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Li-Ju","family":"Shiu","sequence":"additional","affiliation":[{"name":"Department of Foreign Languages and Literature, National Chi Nan University, Nantou 545301, Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5525-4011","authenticated-orcid":false,"given":"Yen-Wei","family":"Chu","sequence":"additional","affiliation":[{"name":"Graduate Institute of Genomics and Bioinformatics, National Chung Hsing University, Taichung 402202, Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8660-570X","authenticated-orcid":false,"given":"Pau-Choo","family":"Chung","sequence":"additional","affiliation":[{"name":"Department of Electrical Engineering, National Cheng Kung University, Tainan 701401, Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1730-9728","authenticated-orcid":false,"given":"Kai-Po","family":"Chang","sequence":"additional","affiliation":[{"name":"School of Medicine, China Medical University, Taichung 404333, Taiwan"},{"name":"Department of Pathology, China Medical University Hospital, Taichung 404327, Taiwan"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,5,27]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"106237","DOI":"10.1016\/j.ypmed.2020.106237","article-title":"The role and utility of population-based cancer registries in cervical cancer surveillance and control","volume":"144","author":"Saraiya","year":"2021","journal-title":"Prev. Med."},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"The Lancet (2025). Cancer registries: The bedrock of global cancer care. Lancet, 405, 353.","DOI":"10.1016\/S0140-6736(25)00189-8"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"20","DOI":"10.21037\/tbcr-24-60","article-title":"The role of a national cancer registry in effective implementation and monitoring of the Global Breast Cancer Initiative (GBCI) framework in Ghana: A narrative review","volume":"6","author":"Nair","year":"2025","journal-title":"Transl. Breast Cancer Res."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"e2400110","DOI":"10.1200\/CCI.24.00110","article-title":"Classifying tumor reportability status from unstructured electronic pathology reports using language models in a population-based cancer registry setting","volume":"8","author":"Gondara","year":"2024","journal-title":"JCO Clin. Cancer Inform."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"314","DOI":"10.1007\/s10462-025-11316-5","article-title":"A survey of NLP methods for oncology in the past decade with a focus on cancer registry applications","volume":"58","author":"Hands","year":"2025","journal-title":"Artif. Intell. Rev."},{"key":"ref_6","first-page":"175","article-title":"Cancer Registrar Workload and Staffing Study: Guidelines for Hospital Cancer Registry Programs","volume":"51","author":"Hailer","year":"2024","journal-title":"J. Regist. Manag."},{"key":"ref_7","first-page":"287","article-title":"An overview of real-world data sources for oncology and considerations for research","volume":"72","author":"Penberthy","year":"2022","journal-title":"CA Cancer J. Clin."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"259","DOI":"10.1038\/s41586-023-05881-4","article-title":"Foundation models for generalist medical artificial intelligence","volume":"616","author":"Moor","year":"2023","journal-title":"Nature"},{"key":"ref_9","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":"ref_10","doi-asserted-by":"crossref","first-page":"435","DOI":"10.1007\/s10389-022-01795-z","article-title":"Privacy in electronic health records: A systematic mapping study","volume":"32","author":"Tertulino","year":"2024","journal-title":"J. Public Health"},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"816","DOI":"10.1158\/1055-9965.EPI-19-0873","article-title":"Leveraging digital data to inform and improve quality cancer care","volume":"29","author":"Blayney","year":"2020","journal-title":"Cancer Epidemiol. Biomark. Prev."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"40","DOI":"10.1038\/s41698-025-00824-w","article-title":"An automatic pipeline for temporal monitoring of radiotherapy-induced toxicities in head and neck cancer patients","volume":"9","author":"Bagherzadeh","year":"2025","journal-title":"npj Precis. Oncol."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"e54246","DOI":"10.2196\/54246","article-title":"A new natural language processing-inspired methodology to investigate temporal shifts (drifts) in health care data","volume":"12","author":"Paiva","year":"2024","journal-title":"JMIR Med. Inform."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"27300","DOI":"10.1038\/s41598-025-10709-4","article-title":"Cancer type, stage and prognosis assessment from pathology reports using LLMs","volume":"15","author":"Saluja","year":"2025","journal-title":"Sci. Rep."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"e65984","DOI":"10.2196\/65984","article-title":"Large language model applications for health information extraction in oncology: Scoping review","volume":"11","author":"Chen","year":"2025","journal-title":"JMIR Cancer"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"e13605","DOI":"10.1200\/JCO.2025.43.16_suppl.e13605","article-title":"Human vs. AI: A comparative effectiveness study of large language models for automated biomarker extraction","volume":"43","author":"Hung","year":"2025","journal-title":"J. Clin. Oncol."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"313","DOI":"10.1038\/s41698-025-01103-4","article-title":"A software pipeline for medical information extraction with large language models","volume":"9","author":"Wiest","year":"2025","journal-title":"npj Precis. Oncol."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"106022","DOI":"10.1016\/j.ijmedinf.2025.106022","article-title":"From text to data: Open-source large language models in extracting cancer related medical attributes from German pathology reports","volume":"203","author":"Bartels","year":"2025","journal-title":"Int. J. Med. Inform."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"257","DOI":"10.1038\/s41746-024-01233-2","article-title":"Privacy-preserving large language models for structured medical information retrieval","volume":"7","author":"Wiest","year":"2024","journal-title":"npj Digit. Med."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"e68998","DOI":"10.2196\/68998","article-title":"Scientific evidence for clinical text summarization using large language models","volume":"27","author":"Bednarczyk","year":"2025","journal-title":"J. Med. Internet Res."},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Tripathi, A., Waqas, A., Venkatesan, K., Ullah, E., Khan, A., Khalil, F., Chen, W.S., Ozturk, Z.G., Saeed-Vafa, D., and Bui, M.M. (2025). Employing consensus-based reasoning with locally deployed LLMs for enabling structured data extraction from surgical pathology reports. medRxiv.","DOI":"10.1101\/2025.04.22.25326217"},{"key":"ref_22","unstructured":"Bumgardner, V.K.C., Mullen, A., Armstrong, S., Hickey, C., and Talbert, J. (2023). Local large language models for complex structured medical tasks. arXiv."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"e64544","DOI":"10.2196\/64544","article-title":"Using large language models to automate data extraction from surgical pathology reports","volume":"9","author":"Lee","year":"2025","journal-title":"JMIR Form. Res."},{"key":"ref_24","doi-asserted-by":"crossref","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":"ref_25","doi-asserted-by":"crossref","first-page":"96","DOI":"10.1038\/s43856-025-00808-8","article-title":"Comprehensive testing of large language models for extraction of structured data in pathology","volume":"5","author":"Grothey","year":"2025","journal-title":"Commun. Med."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"11","DOI":"10.1038\/s44401-025-00013-8","article-title":"Synoptic reporting by summarizing cancer pathology reports using large language models","volume":"2","author":"Rajaganapathy","year":"2025","journal-title":"npj Health Syst."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"450","DOI":"10.1038\/s41746-025-01824-7","article-title":"Large language model integrations in cancer decision-making: A systematic review and meta-analysis","volume":"8","author":"Hao","year":"2025","journal-title":"npj Digit. Med."},{"key":"ref_28","unstructured":"Atil, B., Aykent, S., Chittams, A., Fu, L., Passonneau, R.J., Radcliffe, E., Rajagopal, G.R., Sloan, A., Tudrej, T., and Ture, F. (2024). Non-determinism of \u201cdeterministic\u201d LLM settings. arXiv."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"47","DOI":"10.1200\/CCI.20.00104","article-title":"College of American Pathologists Cancer Protocols","volume":"5","author":"Torous","year":"2021","journal-title":"JCO Clin. Cancer Inform."},{"key":"ref_30","unstructured":"Khattab, O., Singhvi, A., Maheshwari, P., Zhang, Z., Santhanam, K., Haq, S., Sharma, A., Joshi, T., Moazam, H., and Miller, H. (2024, January 7\u201311). DSPy: Compiling declarative language model calls into state-of-the-art pipelines. Proceedings of the International Conference on Learning Representations 2024 (ICLR 2024), Vienna, Austria."},{"key":"ref_31","unstructured":"Kumar, D., Yadav, D., and Patel, Y. (2025). GPT-OSS-20B: A comprehensive deployment-centric analysis. arXiv."},{"key":"ref_32","unstructured":"Qwen Team (2025). Qwen3 technical report. arXiv."},{"key":"ref_33","unstructured":"Gemma Team (2025). Gemma 3 technical report. arXiv."},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"100933","DOI":"10.1016\/j.patter.2024.100933","article-title":"TCGA-Reports: A machine-readable pathology report resource for benchmarking text-based AI models","volume":"5","author":"Kefeli","year":"2024","journal-title":"Patterns"},{"key":"ref_35","first-page":"229","article-title":"Global cancer statistics 2022: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries","volume":"74","author":"Bray","year":"2024","journal-title":"CA Cancer J. Clin."},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"143","DOI":"10.1038\/s41746-025-01476-7","article-title":"Implementing large language models in healthcare while balancing control, collaboration, costs and security","volume":"8","author":"Hastings","year":"2025","journal-title":"npj Digit. Med."},{"key":"ref_37","doi-asserted-by":"crossref","unstructured":"Waqas, A., Tripathi, A., Ramachandran, R.P., Stewart, P.A., and Rasool, G. (2024). Multimodal data integration for oncology in the era of deep neural networks: A review. Front. Artif. Intell., 7.","DOI":"10.3389\/frai.2024.1408843"},{"key":"ref_38","unstructured":"Chen, C., Weishaupt, L., Williamson, D.F.K., Chen, R.J., Ding, T., Chen, B., Vaidya, A., Le, L.P., Jaume, G., and Lu, M.Y. (2025). Evidence-based diagnostic reasoning with multi-agent copilot for human pathology. arXiv."},{"key":"ref_39","unstructured":"Witowski, J., Zeng, K.G., Cappadona, J., Elayoubi, J., Choucair, K., Chiru, E.D., Chan, N., Kang, Y.J., Howard, F., and Ostrovnaya, I. (2024). Multi-modal AI for comprehensive breast cancer prognostication. arXiv."}],"container-title":["Diagnostics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2075-4418\/16\/11\/1644\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,29]],"date-time":"2026-05-29T04:19:19Z","timestamp":1780028359000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2075-4418\/16\/11\/1644"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,27]]},"references-count":39,"journal-issue":{"issue":"11","published-online":{"date-parts":[[2026,6]]}},"alternative-id":["diagnostics16111644"],"URL":"https:\/\/doi.org\/10.3390\/diagnostics16111644","relation":{},"ISSN":["2075-4418"],"issn-type":[{"value":"2075-4418","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5,27]]}}}