Digital Registrar: A Schema-First Framework for Multi-Cancer Privacy-Preserving Pathology Abstraction via Local LLMs

Chow, Nan-Haw; Chang, Han; Chen, Hung-Kai; Lin, Chen-Yuan; Liu, Ying-Lung; Tseng, Po-Yen; Shiu, Li-Ju; Chu, Yen-Wei; Chung, Pau-Choo; Chang, Kai-Po

doi:10.3390/diagnostics16111644

Open AccessArticle

Digital Registrar: A Schema-First Framework for Multi-Cancer Privacy-Preserving Pathology Abstraction via Local LLMs

by

Nan-Haw Chow

^1,2,3,†

,

Han Chang

^2,†

,

Hung-Kai Chen

²,

Chen-Yuan Lin

⁴,

Ying-Lung Liu

⁵,

Po-Yen Tseng

²,

Li-Ju Shiu

⁶,

Yen-Wei Chu

⁷

,

Pau-Choo Chung

⁸

and

Kai-Po Chang

^2,3,*

¹

Center for Precision Medicine, China Medical University Hospital, Taichung 404327, Taiwan

²

School of Medicine, China Medical University, Taichung 404333, Taiwan

³

Department of Pathology, China Medical University Hospital, Taichung 404327, Taiwan

⁴

Signal 1, Toronto, ON M5R 2E3, Canada

⁵

Department of Computer Science and Information Engineering, National Taiwan University of Science and Technology, Taipei 106990, Taiwan

⁶

Department of Foreign Languages and Literature, National Chi Nan University, Nantou 545301, Taiwan

⁷

Graduate Institute of Genomics and Bioinformatics, National Chung Hsing University, Taichung 402202, Taiwan

⁸

Department of Electrical Engineering, National Cheng Kung University, Tainan 701401, Taiwan

^*

Author to whom correspondence should be addressed.

^†

These authors contributed equally to this work.

Diagnostics 2026, 16(11), 1644; https://doi.org/10.3390/diagnostics16111644

Submission received: 5 April 2026 / Revised: 17 May 2026 / Accepted: 22 May 2026 / Published: 27 May 2026

(This article belongs to the Special Issue The Application of Large Language Models (LLMs) and Vision-Language Models (VLMs) in Healthcare)

Download

Browse Figures

Review Reports Versions Notes

Abstract

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 (>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 40–70 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.

Keywords: clinical ontology; cancer registry; CAP protocol; large language model; structured data extraction; DSPy; interoperability; privacy-preserving AI

Share and Cite

MDPI and ACS Style

Chow, N.-H.; Chang, H.; Chen, H.-K.; Lin, C.-Y.; Liu, Y.-L.; Tseng, P.-Y.; Shiu, L.-J.; Chu, Y.-W.; Chung, P.-C.; Chang, K.-P. Digital Registrar: A Schema-First Framework for Multi-Cancer Privacy-Preserving Pathology Abstraction via Local LLMs. Diagnostics 2026, 16, 1644. https://doi.org/10.3390/diagnostics16111644

AMA Style

Chow N-H, Chang H, Chen H-K, Lin C-Y, Liu Y-L, Tseng P-Y, Shiu L-J, Chu Y-W, Chung P-C, Chang K-P. Digital Registrar: A Schema-First Framework for Multi-Cancer Privacy-Preserving Pathology Abstraction via Local LLMs. Diagnostics. 2026; 16(11):1644. https://doi.org/10.3390/diagnostics16111644

Chicago/Turabian Style

Chow, Nan-Haw, Han Chang, Hung-Kai Chen, Chen-Yuan Lin, Ying-Lung Liu, Po-Yen Tseng, Li-Ju Shiu, Yen-Wei Chu, Pau-Choo Chung, and Kai-Po Chang. 2026. "Digital Registrar: A Schema-First Framework for Multi-Cancer Privacy-Preserving Pathology Abstraction via Local LLMs" Diagnostics 16, no. 11: 1644. https://doi.org/10.3390/diagnostics16111644

APA Style

Chow, N.-H., Chang, H., Chen, H.-K., Lin, C.-Y., Liu, Y.-L., Tseng, P.-Y., Shiu, L.-J., Chu, Y.-W., Chung, P.-C., & Chang, K.-P. (2026). Digital Registrar: A Schema-First Framework for Multi-Cancer Privacy-Preserving Pathology Abstraction via Local LLMs. Diagnostics, 16(11), 1644. https://doi.org/10.3390/diagnostics16111644

Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details here.

Article Menu

Digital Registrar: A Schema-First Framework for Multi-Cancer Privacy-Preserving Pathology Abstraction via Local LLMs

Abstract

Share and Cite

Article Metrics

Article Access Statistics

Further Information

Guidelines

MDPI Initiatives

Follow MDPI