# Trust but Verify:Evidence-Linked Multi-Agent Clinical Information Extraction in Pathology

arXiv: https://arxiv.org/abs/2607.06435 · HTML: https://mlsanity.com/paper/2607.06435/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 3 of its 39 references that are in the map.
- First posted on arXiv 7 Jul 2026.

## Builds on (most cited first, 3 of 3)

- [BioBERT: a pre-trained biomedical language representation model for biomedical text mining](https://mlsanity.com/paper/1901.08746/) (2019)
- [DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence](https://mlsanity.com/paper/2606.19348/) (2026)
- [Universal Abstraction: Harnessing Frontier Models to Structure Real-World Data at Scale](https://mlsanity.com/paper/2502.00943/) (2025)

## Built on by (most cited first, 1 of 1)

- [From Analytics to Tumor Boards: An Evidence-Linked Multi-Agent Workflow for Oncology Feature Extraction](https://mlsanity.com/paper/2608.28974/) (2026)

## Abstract (arXiv)

Clinical feature extraction from pathology reports is challenging because relevant evidence may be distributed across coded and narrative fields and depend on specimen attribution, negation, ancillary findings, and diagnostic context. We retrospectively evaluated the NimbleMind Multi-Agent System (nMAS), a configurable workflow that separates clinician-defined field specifications from extraction models and returns report-level predictions with source-linked evidence. The study included 54 dummy gastric biopsy pathology reports from Singapore and four binary target fields, yielding 216 feature-case decisions. nMAS correctly classified 213 of 216 decisions (98.61%), and all evidence spans associated with correct predictions occurred verbatim in the corresponding source reports. All three errors occurred in the two context-dependent textitH. pylori-related fields requiring negation handling or diagnostic attribution. A single-model UMA-style comparator produced the similar label-level performance and error pattern. These findings do not demonstrate predictive superiority for the multi-agent architecture.Rather, the contribution of nMAS lies in workflow integration and traceability through configurable field specifications, complexity-based routing, report-level aggregation, and source-text validation within a clinician-reviewable workflow. Larger multi-institutional studies should assess generalizability, semantic evidence quality, adaptation effort, and clinician verification time.