Deep reflective reasoning in interdependence constrained structured data extraction from clinical notes for digital health

TL;DR

This paper introduces deep reflective reasoning, a novel LLM framework that iteratively checks and revises structured data extraction from clinical notes, significantly improving accuracy and consistency across multiple oncology applications.

Contribution

It presents a new LLM-based method that enforces interdependence constraints through iterative self-critique, enhancing reliability of clinical data extraction.

Findings

F1 score for categorical variables increased from 0.828 to 0.911.

Accuracy for immunostaining pattern improved from 0.870 to 0.927.

Tumor staging accuracy increased from 0.680 to 0.833.

Abstract

Extracting structured information from clinical notes requires navigating a dense web of interdependent variables where the value of one attribute logically constrains others. Existing Large Language Model (LLM)-based extraction pipelines often struggle to capture these dependencies, leading to clinically inconsistent outputs. We propose deep reflective reasoning, a large language model agent framework that iteratively self-critiques and revises structured outputs by checking consistency among variables, the input text, and retrieved domain knowledge, stopping when outputs converge. We extensively evaluate the proposed method in three diverse oncology applications: (1) On colorectal cancer synoptic reporting from gross descriptions (n=217), reflective reasoning improved average F1 across eight categorical synoptic variables from 0.828 to 0.911 and increased mean correct rate across four numeric variables from 0.806 to 0.895; (2) On Ewing sarcoma CD99 immunostaining pattern identification (n=200), the accuracy improved from 0.870 to 0.927; (3) On lung cancer tumor staging (n=100), tumor stage accuracy improved from 0.680 to 0.833 (pT: 0.842 -> 0.884; pN: 0.885 -> 0.948). The results demonstrate that deep reflective reasoning can systematically improve the reliability of LLM-based structured data extraction under interdependence constraints, enabling more consistent machine-operable clinical datasets and facilitating knowledge discovery with machine learning and data science towards digital health.