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

Source

• Source name: arXiv
• Source kind: paper
• Authors / organization: Yufan Wang, Anit Kumar Sahu, Yan Fei Ng, Daniel Kang, Shayan Vassef, Soorya Ram Shimgekar, Koustuv Saha, Piyum Zonooz, Navin Kumar, Chee Leong Cheng, Li Yan Khor
• Venue: arXiv: cs.AI
• Published: 2026-07-07
• Collected: 2026-07-08
• URL: http://arxiv.org/abs/2607.06435v1
• PDF: https://arxiv.org/pdf/2607.06435v1
• DOI: UNKNOWN

Plain-Language Brief

Researchers evaluated a system called nMAS for extracting information from gastric biopsy reports to identify Helicobacter pylori infection. The system achieved high accuracy in classifying samples, and could potentially save significant time compared to manual review.

What the Document Says

• A study was conducted on the Nimblemind Multi-Agent System (nMAS) for analyzing gastric biopsy reports. The system is designed to find evidence of Helicobacter pylori infection.
• The study used 54 de-identified gastric biopsy pathology reports from a healthcare system in Singapore.
• Four binary fields were evaluated: gastric/stomach biopsy, biopsy status, H. pylori positivity, and H. pylori-associated gastritis.
• nMAS correctly classified 213 out of 216 feature-case decisions, achieving an overall accuracy of 98.61%.
• A separate comparator produced similar classification metrics.
• The system's contribution is in workflow integration and traceability rather than predictive superiority.
• Under a hypothetical scenario, reviewing 1000 reports could save about 81.9 staff-hours and approximately USD~6,100 in potential staff-time.

Key Concepts Mentioned

• Helicobacter pylori
• gastric biopsy reports
• Nimblemind Multi-Agent System (nMAS)
• classification metrics
• staff time

Claims Made by the Document

• nMAS can accurately classify gastric biopsy samples for Helicobacter pylori infection.
• nMAS could potentially save significant time in manual review compared to a hypothetical scenario.

Evidence Used

• Overall accuracy of 98.61% was achieved by nMAS in the study

Methods / Approach

• Retrospective pilot evaluation
• Evaluation of four binary fields
• Comparison with a separate comparator

Limitations Stated by the Authors

The authors mention that larger multi-institutional studies should be conducted to evaluate evidence-span correctness, clinician verification time, and generalizability.

Limitations Noted by the Agent

Agent interpretation — not from the source.

The study only evaluated a hypothetical scenario for time savings, not actual implementation.

Open Questions

• What is the actual time savings in real-world implementation?
• How accurate is nMAS in differentiating between various stages of Helicobacter pylori infection?

Notes for Future Q&A

May include interpretation. Labeled where it does.

• The study only evaluates the accuracy and potential time savings of the system, not its effectiveness in real-world use.
• It's unclear if the system can accurately differentiate between various stages or severities of Helicobacter pylori infection.

Raw Abstract / Excerpt

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 \textit{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 multi-institutional studies should evaluate evidence-span correctness, clinician verification time, and generalizability.