Agent-based large language model system for extracting structured data from breast cancer synoptic reports: a dual-validation study.

Objectives: To develop and validate an agent-based Large Language Model (LLM) system for extracting structured data from breast cancer synoptic pathology reports and assess the performance gap between synthetic and real-world validation. Materials and Methods: We developed a modular artificial intelligence (AI) agent-based framework employing sequential specialized LLMs for parsing pathology reports and extracting structured data. We normalized College of American Pathologists (CAP) cancer protocols into 8 sections, 86 subsections, and 229 discrete fields. Seven leading LLMs (gemini-2.5-pro, llama3.3-70b, phi4-14b, deepseek-r1 14B/70B, gemma3-27b, gemini-2.0-flash-lite) were validated using dual evaluation: synthetic validation (864 controlled test cases) and real-world ground truth (6651 annotated fields from 90 pathology reports). Results: Synthetic validation demonstrated strong performance (accuracy: 93.8%-99.0%). Real-world evaluation revealed field extraction recall ranging from 61.8% to 87.7%, demonstrating a substantial "reality gap" with performance drops of 11-32 percentage points. The gemini-2.5-pro model achieved the highest real-world recall (87.7%). Model size did not predict performance: the 14B-parameter deepseek-r1 (77.6%) outperformed its 70B-parameter counterpart (70.4%). Discussion: The substantial performance degradation from synthetic to real-world data underscores the complexity of authentic clinical documentation. Smaller models can achieve competitive or superior recall, reducing computational costs. With even the best models missing 12%-38% of annotated fields, mandatory human verification is essential for clinical deployment. Conclusion: While LLM-based extraction systems show promise for pathology data extraction, synthetic validation alone provides false confidence. Rigorous real-world ground truth evaluation with expert annotation is essential before clinical deployment. These systems are best positioned as screening tools with mandatory human oversight rather than autonomous decision-making systems.