Large-Scale Deep Learning for Metastasis Detection in Pathology Reports

No existing algorithm can reliably identify metastasis from pathology reports across multiple cancer types and the entire US population. In this study, we develop a deep learning model that automatically detects patients with metastatic cancer by using pathology reports from many laboratories and of multiple cancer types. We trained and validated our model on a cohort of 29,632 patients from four Surveillance, Epidemiology, and End Results (SEER) registries linked to 60,471 unstructured pathology reports. Our deep learning architecture trained on task-specific data outperforms a general-purpose LLM, with a recall of 0.894 compared to 0.824. We quantified model uncertainty and used it to defer reports for human review. We found that retaining 72.9% of reports increased recall from 0.894 to 0.969. This approach could streamline population-based cancer surveillance to help address the unmet need to capture recurrence or progression.