Finding H. pylori in the Fine Print: Evidence-Linked Multi-Agent Case Finding from Gastric Biopsy Reports

Jul 16, 2026

Evidence for Helicobacter pylori infection and H. pylori–associated gastritis can be scattered across heterogeneous coded and free-text fields in gastric biopsy pathology reports, making keyword search and manual review hard to scale. This study retrospectively evaluated the Nimblemind Multi-Agent System (nMAS) using 54 de-identified Singapore gastric biopsy reports. Four clinician-scoped binary fields were tested, achieving 98.61% overall accuracy (213/216 decisions). Outputs preserved report-level, source-sentence traceability. An illustrative scenario suggests large reductions in clinician review time by leveraging evidence-linked verification. Larger studies should validate evidence-span correctness, clinician verification time, and generalizability.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages10

Reading Time25 min

Introduction

Related Work

Finding H. pylori in the Fine Print: Evidence-Linked Multi-Agent Case Finding from Gastric Biopsy Reports Yufan Wang∗ , Anit Kumar Sahu¶ , Yan Fei Ng†, Daniel Kang∗ , Shayan Vassef∗ , Soorya Ram Shimgekar∗ , Koustuv Saha§ , Piyum Zonooz∗ , Navin Kumar∗ , Chee Leong Cheng†‡, and Li Yan Khor†‡ ∗[Nimblemind.ai](Nimblemind.ai), USA †Department of Anatomical Pathology, Singapore General Hospital, Singapore ‡Duke–NUS Medical School, Singapore § University of Illinois Urbana-Champaign ¶ Independent Researcher arXiv :2607 .06435v 1 [ cs .AI ] 7 Jul 2026 Abstract—Data from Singapore indicated that about 31% of the population had evidence of Helicobacter pylori infection. Persistent H. pylori infection is associated with chronic active gastritis and peptic ulcer disease, and its eradication is key to gastric cancer prevention. However, evidence supporting H. pylori positivity and H. pylori-associated gastritis may be distributed across heterogeneous coded and free-text report fields and may require contextual interpretation of assertion and negation, limiting keyword search, and making manual review difficult to scale. We conducted a retrospective pilot evaluation of the Nimblemind Multi-Agent System (nMAS), a field-name-driven, evidence-linked extraction workflow, using 54 de-identified gastric biopsy pathology reports from a large healthcare system in Singapore. Four clinician-scoped binary fields were evaluated: gastric/stomach biopsy, biopsy status, H. pylori positivity, and H. pylori-associated gastritis. Across 216 feature-case decisions, nMAS correctly classified 213, corresponding to 98.61% overall accuracy. A separately implemented UMA-style MiniMax M2.5 comparator produced similar aggregate and per-field classification metrics. Although predictive performance was similar, nMAS maintained unified report-level outputs with supporting source sentences; the demonstrated contribution is therefore workflow integration and traceability rather than predictive superiority. Under an illustrative, unmeasured scenario, reviewing 1,000 reports at five minutes per manual review versus five seconds per evidence-linked verification would reduce review time from 83.3 to 1.4 staff-hours, corresponding to 81.9 staff-hours and about USD 6,100 in potential staff-time value. Larger multiinstitutional studies should evaluate evidence-span correctness, clinician verification time, and generalizability. Index Terms—clinical NLP, pathology reports, large language models, multi-agent systems, information extraction, Helicobacter pylori, gastric biopsy, H. pylori-associated gastritis I. INTRODUCTION About 31% of the Singapore population was estimated to have evidence of Helicobacter pylori infection, with prevalence increasing with age and varying across ethnic groups [1] . Persistent H. pylori infection is associated with chronic active gastritis and peptic ulcer disease, while eradication is central to gastric cancer prevention [2]–[4] . Reliable identification of biopsy-confirmed H. pylori-positive reports is therefore important for treatment review, eradication follow-up, clini- cal audit, research cohort assembly, and quality-improvement workflows. Pathology-based case finding is not a simple keywordsearch task. Identical organism terms may appear in affirmative, negated, historical, or ancillary-stain contexts; for example, “Helicobacter organisms are identified” and “No Helicobacter organisms are identified” contain the same target terms but require opposite labels. Relevant evidence may also be distributed across coded specimen fields, specimen labels, diagnoses, microscopic descriptions, and ancillary-test comments, making manual review difficult to scale. Slow manual review can delay treatment review, eradication followup, and quality-improvement action, which may limit timely patient care [5]–[7] . At five minutes per report, screening 1,000 candidate pathology reports would require about 83 staff-hours before downstr

FAQs

What were the main performance and practical implications of nMAS?

nMAS correctly classified 213 of 216 feature-case decisions, yielding 98.61% overall accuracy. While predictive performance was similar to a comparator, nMAS emphasized unified, traceable report-level outputs that can reduce clinician review time in an illustrative scenario.

Jul 16, 2026

Upload by River Wang