International journal of medical informatics · 2026
Automated Flow and local LLM-Driven clinical Context Engineering: Precision colorectal cancer recurrence registry.
СтатьяНазвание и аннотация: Перевод пока не подготовлен
Обработка статьи · этапы, ошибки и управление
Загрузка состояния…
Ошибки и ограничения
История · было → стало
Состояние обновляется каждые 5 секунд, пока блок открыт. Процент показывается только там, где известен объём работы. Пауза останавливает продолжение этапа; текущий запрос к источнику может завершиться.
Yang Yi-Wen, Chang Che-Yuan, Lin Yu-Zu, Cheng Hou-Hsuan, Huang Sheng-Chieh, Lin Hung-Hsin, Lin Chun-Chi, Lan Yuan-Tzu, Wang Huann-Sheng, Chang Shih-Ching, Yang Shung-Haur, Chen Wei-Shone, Jiang Jeng-Kai
Аннотация
OBJECTIVE: This study develops and validates a deployable, privacy-preserving automated tool to address the labor-intensive nature of colorectal cancer (CRC) recurrence registration. Our tool utilizes a reproducible, two-stage 'Clinical Context Engineering' workflow to mimic expert clinical reasoning and overcome the limitations of handling longitudinal clinical data ambiguity.
METHODS: We retrospectively studied 3053 CRC patients (2010-2018). A local Large Language Model (LLM) (Qwen3:14B) analyzed ∼ 19,900 pathology and ∼ 43,900 imaging reports using iterative, patch-based analysis ("raw LLM"). Clinical validation rules were applied to generate "rule-based LLM" output, enhancing explainability and trustworthiness. Both automated methods and the manual Taiwan Cancer Registry (TCR) database were compared against a 20% manual reference standard (N = 602). Full prompts and validation code are provided for complete reproducibility.
RESULTS: Under a strict 60-day temporal tolerance, the Rule-Based LLM achieved 90.7% accuracy, comparable to standard TCR processes (92.0%), and 77.2% sensitivity. The application of clinical validation rules significantly improved specificity from 87.7% (Raw LLM) to 93.9% (Rule-Based LLM). In time window analysis, the Rule-Based LLM identified 87.1% of recurrences within 60 days of the reference date.
CONCLUSION: Our locally deployed, privacy-preserving, and explainable Clinical Context Engineering framework offers a viable, non-inferior alternative to standard TCR processes, reducing workload while maintaining data quality and fostering trust in AI-assisted cancer registry automation.
METHODS: We retrospectively studied 3053 CRC patients (2010-2018). A local Large Language Model (LLM) (Qwen3:14B) analyzed ∼ 19,900 pathology and ∼ 43,900 imaging reports using iterative, patch-based analysis ("raw LLM"). Clinical validation rules were applied to generate "rule-based LLM" output, enhancing explainability and trustworthiness. Both automated methods and the manual Taiwan Cancer Registry (TCR) database were compared against a 20% manual reference standard (N = 602). Full prompts and validation code are provided for complete reproducibility.
RESULTS: Under a strict 60-day temporal tolerance, the Rule-Based LLM achieved 90.7% accuracy, comparable to standard TCR processes (92.0%), and 77.2% sensitivity. The application of clinical validation rules significantly improved specificity from 87.7% (Raw LLM) to 93.9% (Rule-Based LLM). In time window analysis, the Rule-Based LLM identified 87.1% of recurrences within 60 days of the reference date.
CONCLUSION: Our locally deployed, privacy-preserving, and explainable Clinical Context Engineering framework offers a viable, non-inferior alternative to standard TCR processes, reducing workload while maintaining data quality and fostering trust in AI-assisted cancer registry automation.