Comprehensive Structured Abstraction of Pathology Reports Is Now Feasible Using Local Large Language Models

Digital Registrar: A Schema-First Framework for Multi-Cancer Privacy-Preserving Pathology Abstraction via Local LLMs | medRxiv /* */ /* */ <!-- <!-- /*! * yepnope1.5.4 * (c) WTFPL, GPLv2 */ (function(a,b,c){function d(a){return"[object Function]"==o.call(a)}function e(a){return"string"==typeof a}function f(){}function g(a){return!a||"loaded"==a||"complete"==a||"uninitialized"==a}function h(){var a=p.shift();q=1,a?a.t?m(function(){("c"==a.t?B.injectCss:B.injectJs)(a.s,0,a.a,a.x,a.e,1)},0):(a(),h()):q=0}function i(a,c,d,e,f,i,j){function k(b){if(!o&&g(l.readyState)&&(u.r=o=1,!q&&h(),l.onload=l.onreadystatechange=null,b)){"img"!=a&&m(function(){t.removeChild(l)},50);for(var d in y[c])y[c].hasOwnProperty(d)&&y[c][d].onload()}}var j=j||B.errorTimeout,l=b.createElement(a),o=0,r=0,u={t:d,s:c,e:f,a:i,x:j};1===y[c]&&(r=1,y[c]=[]),"object"==a?l.data=c:(l.src=c,l.type=a),l.width=l.height="0",l.onerror=l.onload=l.onreadystatechange=function(){k.call(this,r)},p.splice(e,0,u),"img"!=a&&(r||2===y[c]?(t.insertBefore(l,s?null:n),m(k,j)):y[c].push(l))}function j(a,b,c,d,f){return q=0,b=b||"j",e(a)?i("c"==b?v:u,a,b,this.i++,c,d,f):(p.splice(this.i++,0,a),1==p.length&&h()),this}function k(){var a=B;return a.loader={load:j,i:0},a}var l=b.documentElement,m=a.setTimeout,n=b.getElementsByTagName("script")[0],o={}.toString,p=[],q=0,r="MozAppearance"in l.style,s=r&&!!b.createRange().compareNode,t=s?l:n.parentNode,l=a.opera&&"[object Opera]"==o.call(a.opera),l=!!b.attachEvent&&!l,u=r?"object":l?"script":"img",v=l?"script":u,w=Array.isArray||function(a){return"[object Array]"==o.call(a)},x=[],y={},z={timeout:function(a,b){return b.length&&(a.timeout=b[0]),a}},A,B;B=function(a){function b(a){var a=a.split("!"),b=x.length,c=a.pop(),d=a.length,c={url:c,origUrl:c,prefixes:a},e,f,g;for(f=0;f<d;f++)g=a[f].split("="),(e=z[g.shift()])&&(c=e(c,g));for(f=0;f<b;f++)c=x[f](c);return c}function g(a,e,f,g,h){var i=b(a),j=i.autoCallback;i.url.split(".").pop().split("?").shift(),i.bypass||(e&&(e=d(e)?e:e[a]||e[g]||e[a.split("/").pop().split("?")[0]]),i.instead?i.instead(a,e,f,g,h):(y[i.url]?i.noexec=!0:y[i.url]=1,f.load(i.url,i.forceCSS||!i.forceJS&&"css"==i.url.split(".").pop().split("?").shift()?"c":c,i.noexec,i.attrs,i.timeout),(d(e)||d(j))&&f.load(function(){k(),e&&e(i.origUrl,h,g),j&&j(i.origUrl,h,g),y[i.url]=2})))}function h(a,b){function c(a,c){if(a){if(e(a))c||(j=function(){var a=[].slice.call(arguments);k.apply(this,a),l()}),g(a,j,b,0,h);else if(Object(a)===a)for(n in m=function(){var b=0,c;for(c in a)a.hasOwnProperty(c)&&b++;return b}(),a)a.hasOwnProperty(n)&&(!c&&!--m&&(d(j)?j=function(){var a=[].slice.call(arguments);k.apply(this,a),l()}:j[n]=function(a){return function(){var b=[].slice.call(arguments);a&&a.apply(this,b),l()}}(k[n])),g(a[n],j,b,n,h))}else!c&&l()}var h=!!a.test,i=a.load||a.both,j=a.callback||f,k=j,l=a.complete||f,m,n;c(h?a.yep:a.nope,!!i),i&&c(i)}var i,j,l=this.yepnope.loader;if(e(a))g(a,0,l,0);else if(w(a))for(i=0;i (function(w,d,s,l,i){w[l]=w[l]||[];w[l].push({'gtm.start':new Date().getTime(),event:'gtm.js'});var f=d.getElementsByTagName(s)[0];var j=d.createElement(s);var dl=l!='dataLayer'?'&l='+l:'';j.src='//www.googletagmanager.com/gtm.js?id='+i+dl;j.type='text/javascript';j.async=true;f.parentNode.insertBefore(j,f);})(window,document,'script','dataLayer','GTM-P4HH5NV'); Skip to main content Home About Submit ALERTS / RSS Search for this keyword Advanced Search Digital Registrar: A Schema-First Framework for Multi-Cancer Privacy-Preserving Pathology Abstraction via Local LLMs View ORCID Profile Nan-Haw Chow , View ORCID Profile Han Chang , Hung-Kai Chen , Chen-Yuan Lin , Ying-Lung Liu , Po-Yen Tseng , Li-Ju Shiu , View ORCID Profile Yen-Wei Chu , View ORCID Profile Pau-Choo Chung , View ORCID Profile Kai-Po Chang doi: https://doi.org/10.1101/2025.10.21.25338475 Nan-Haw Chow 1 Center for Precision Medicine, China Medical University Hospital, Taichung, Taiwan; Find this author on Google Scholar Find this author on PubMed Search for this author on this site ORCID record for Nan-Haw Chow Han Chang 2 School of Medicine, China Medical University, Taichung, Taiwan; Find this author on Google Scholar Find this author on PubMed Search for this author on this site ORCID record for Han Chang Hung-Kai Chen 2 School of Medicine, China Medical University, Taichung, Taiwan; Find this author on Google Scholar Find this author on PubMed Search for this author on this site Chen-Yuan Lin 3 Signal1, Toronto, Canada; Find this author on Google Scholar Find this author on PubMed Search for this author on this site Ying-Lung Liu 4 Department of Computer Science and Information Engineering, National Taiwan University of Science and Technology, Taipei, Taiwan; Find this author on Google Scholar Find this author on PubMed Search for this author on this site Po-Yen Tseng 2 School of Medicine, China Medical University, Taichung, Taiwan; Find this author on Google Scholar Find this author on PubMed Search for this author on this site Li-Ju Shiu 5 Department of Foreign Languages and Literature, National Chi Nan University, Nantou, Taiwan; Find this author on Google Scholar Find this author on PubMed Search for this author on this site Yen-Wei Chu 6 Graduate Institute of Genomics and Bioinformatics, National Chung Hsing University, Taichung, Taiwan; Find this author on Google Scholar Find this author on PubMed Search for this author on this site ORCID record for Yen-Wei Chu Pau-Choo Chung 7 Department of Electrical Engineering, National Cheng Kung University, Tainan, Taiwan Find this author on Google Scholar Find this author on PubMed Search for this author on this site ORCID record for Pau-Choo Chung Kai-Po Chang 2 School of Medicine, China Medical University, Taichung, Taiwan; Find this author on Google Scholar Find this author on PubMed Search for this author on this site ORCID record for Kai-Po Chang For correspondence: 017179{at}tool.caaumed.org.tw Abstract Info/History Metrics Supplementary material Data/Code Preview PDF Abstract Background/Objectives: Surgical pathology reports contain the most granular diagnostic data for cancer, yet their predominant free-text format creates a "translational gap" that hinders automated registry entry and secondary analytics. While current large language model (LLM) research often focuses on narrow extraction tasks, this study emphasizes the clinically governed schema layer as the more durable scientific contribution for long-term interoperability and reproducibility. Methods: We developed a College of American Pathologists (CAP)-aligned clinical ontology implemented as strictly typed, hierarchical schemas and encoded as DSPy signatures. The system covers 10 major cancer types across 193 registry fields, including complex variable-length structures such as lymph-node groups and surgical margins. An extraction pipeline was built using the DSPy framework, enabling a model-agnostic architecture in which LLMs serve as interchangeable inference engines. Performance was benchmarked on 893 internal pathology reports (2023-2024) and an external validation cohort of 150 TCGA reports. Hardware feasibility was tested on a single 48 GB GPU to ensure suitability for on-premise, privacy-preserving medical workstation deployment. Results: Using the gpt-oss:20b model, the framework achieved a mean exact-match accuracy of 94.3% across all internal registry fields. External validation accuracy remained high at 92.4% in the TCGA cohort, demonstrating robust generalizability across diverse institutional reporting styles. High fidelity was maintained for critical prognostic indicators, including breast cancer biomarkers (near-perfect accuracy) and surgical margin positivity (91.2% mean accuracy). Operationally, gpt-oss:20b provided the best balance of speed (40-70 s/report) and accuracy compared with denser or more complex architectures. Conclusions: The primary contribution is a schema-first abstraction layer that decouples clinical logic from specific AI models. By transforming narrative reports into machine-readable structures with registry-grade reliability, this framework provides a portable foundation for automated cancer surveillance, privacy-preserving institutional data reuse, and future multimodal clinical systems. Competing Interest Statement The authors have declared no competing interest. Funding Statement This work was supported by the National Science and Technology Council (NSTC) of Taiwan, under grant number NSTC 113-2221-E-039-017, and 114-2813-C-039-132-E, and China Medical University Hospital, under grant number DMR-115-078. The funder played no role in study design, data collection, analysis and interpretation of data, or the writing of this manuscript. Author Declarations I confirm all relevant ethical guidelines have been followed, and any necessary IRB and/or ethics committee approvals have been obtained. Yes The details of the IRB/oversight body that provided approval or exemption for the research described are given below: Research ethics committee of China Medical University & Hospital gave ethical approval for this work, under REC number of CMUH114-REC2-037 I confirm that all necessary patient/participant consent has been obtained and the appropriate institutional forms have been archived, and that any patient/participant/sample identifiers included were not known to anyone (e.g., hospital staff, patients or participants themselves) outside the research group so cannot be used to identify individuals. Yes I understand that all clinical trials and any other prospective interventional studies must be registered with an ICMJE-approved registry, such as ClinicalTrials.gov. I confirm that any such study reported in the manuscript has been registered and the trial registration ID is provided (note: if posting a prospective study registered retrospectively, please provide a statement in the trial ID field explaining why the study was not registered in advance). Yes I have followed all appropriate research reporting guidelines, such as any relevant EQUATOR Network research reporting checklist(s) and other pertinent material, if applicable. Yes Footnotes This is the version accepted to diagnostics, which includes major revision including inter-observer variability and baseline benchmark. The article is still processing. Data Availability Internal Development Cohort The primary dataset consists of de-identified surgical pathology reports from China Medical University Hospital. Due to patient privacy protections, these data are not publicly available but may be accessed by qualified researchers upon reasonable request to the corresponding author, subject to a Data Use Agreement (DUA). External Validation Cohort (TCGA Benchmark) To facilitate reproducibility and benchmarking, the complete external validation dataset including the 150 selected TCGA pathology reports, the expert-annotated ground truth labels, and the model outputs has been deposited in Zenodo and is publicly available at https://doi.org/10.5281/zenodo.20263897 . The original source data remains accessible via the NCI Genomic Data Commons (GDC) Data Portal. https://doi.org/10.5281/zenodo.20263897 https://github.com/kblab2024/digitalregistrar Copyright The copyright holder for this preprint is the author/funder, who has granted medRxiv a license to display the preprint in perpetuity. It is made available under a CC-BY-NC-ND 4.0 International license . View the discussion thread. Back to top Previous Next Posted May 23, 2026. Download PDF Supplementary Material Data/Code Email Thank you for your interest in spreading the word about medRxiv. NOTE: Your email address is requested solely to identify you as the sender of this article. Your Email * Your Name * Send To * Enter multiple addresses on separate lines or separate them with commas. You are going to email the following Digital Registrar: A Schema-First Framework for Multi-Cancer Privacy-Preserving Pathology Abstraction via Local LLMs Message Subject (Your Name) has forwarded a page to you from medRxiv Message Body (Your Name) thought you would like to see this page from the medRxiv website. Your Personal Message CAPTCHA This question is for testing whether or not you are a human visitor and to prevent automated spam submissions. Share Digital Registrar: A Schema-First Framework for Multi-Cancer Privacy-Preserving Pathology Abstraction via Local LLMs Nan-Haw Chow , Han Chang , Hung-Kai Chen , Chen-Yuan Lin , Ying-Lung Liu , Po-Yen Tseng , Li-Ju Shiu , Yen-Wei Chu , Pau-Choo Chung , Kai-Po Chang medRxiv 2025.10.21.25338475; doi: https://doi.org/10.1101/2025.10.21.25338475 Share This Article: Copy Citation Tools Digital Registrar: A Schema-First Framework for Multi-Cancer Privacy-Preserving Pathology Abstraction via Local LLMs Nan-Haw Chow , Han Chang , Hung-Kai Chen , Chen-Yuan Lin , Ying-Lung Liu , Po-Yen Tseng , Li-Ju Shiu , Yen-Wei Chu , Pau-Choo Chung , Kai-Po Chang medRxiv 2025.10.21.25338475; doi: https://doi.org/10.1101/2025.10.21.25338475 Citation Manager Formats BibTeX Bookends EasyBib EndNote (tagged) EndNote 8 (xml) Medlars Mendeley Papers RefWorks Tagged Ref Manager RIS Zotero Tweet Widget Facebook Like Google Plus One Subject Areas All Articles Addiction Medicine (568) Allergy and Immunology (863) Anesthesia (300) Cardiovascular Medicine (4435) Dentistry and Oral Medicine (444) Dermatology (382) Emergency Medicine (608) Endocrinology (including Diabetes Mellitus and Metabolic Disease) (1509) Epidemiology (15229) Forensic Medicine (30) Gastroenterology (1124) Genetic and Genomic Medicine (6600) Geriatric Medicine (668) Health Economics (997) Health Informatics (4536) Health Policy (1368) Health Systems and Quality Improvement (1613) Hematology (541) HIV/AIDS (1264) Infectious Diseases (except HIV/AIDS) (15916) Intensive Care and Critical Care Medicine (1103) Medical Education (623) Medical Ethics (146) Nephrology (667) Neurology (6599) Nursing (346) Nutrition (998) Obstetrics and Gynecology (1144) Occupational and Environmental Health (957) Oncology (3332) Ophthalmology (974) Orthopedics (369) Otolaryngology (420) Pain Medicine (436) Palliative Medicine (130) Pathology (663) Pediatrics (1693) Pharmacology and Therapeutics (691) Primary Care Research (711) Psychiatry and Clinical Psychology (5447) Public and Global Health (9232) Radiology and Imaging (2198) Rehabilitation Medicine and Physical Therapy (1370) Respiratory Medicine (1196) Rheumatology (593) Sexual and Reproductive Health (712) Sports Medicine (530) Surgery (712) Toxicology (99) Transplantation (289) Urology (265) (function(){function c(){var b=a.contentDocument||a.contentWindow.document;if(b){var d=b.createElement('script');d.innerHTML="window.__CF$cv$params={r:'a00c7b54d8849c08',t:'MTc3OTYyNzYxMA=='};var a=document.createElement('script');a.src='/cdn-cgi/challenge-platform/scripts/jsd/main.js';document.getElementsByTagName('head')[0].appendChild(a);";b.getElementsByTagName('head')[0].appendChild(d)}}if(document.body){var a=document.createElement('iframe');a.height=1;a.width=1;a.style.position='absolute';a.style.top=0;a.style.left=0;a.style.border='none';a.style.visibility='hidden';document.body.appendChild(a);if('loading'!==document.readyState)c();else if(window.addEventListener)document.addEventListener('DOMContentLoaded',c);else{var e=document.onreadystatechange||function(){};document.onreadystatechange=function(b){e(b);'loading'!==document.readyState&&(document.onreadystatechange=e,c())}}}})();