Offline Surgical QA with Decomposed Retrieval and Synthesis for Resource-Constrained Settings

Kiran Bhattacharyya

Keywords: clinical AI, information retrieval system, medical education, offline AI systems

TL;DR: We present a compact, offline surgical information assistant using a novel RAG workflow (DeRetSyn) that outperforms larger models on domain-specific and general medical QA tasks, advancing accessible clinical AI for low-resource settings.

Track: Proceedings

Abstract: Digital access to critical medical knowledge in resource-limited settings is often hindered by a lack of internet connectivity and the computational demands of AI systems. This paper introduces the Surgical Information Assistant, a fully deployable, large language model (LLM) -driven multi-agent system designed to provide reliable surgical information in offline, resource-constrained environments. Our system is powered by a workflow that orchestrates question decomposition, information retrieval, grounded generation, and information synthesis to perform complex reasoning on consumer-grade hardware. Grounded in the Open Manual of Surgery for Resource-Limited Settings, we evaluated DeRetSyn on a new question-answer (QA) dataset of over 14,000 surgical question-answer pairs. We compare our system to other alternatives, perform ablation experiments on components of the agentic system, and interrogate sensitivity to retrieval parameters. The results show that our agentic orchestration enables a compact 3B Llama model to achieve 63\% top-1 accuracy, significantly outperforming both a baseline GPT-4o (42.5\%) and a larger 8B Llama model with conventional RAG (53\%). We further test whether this performance enhancement from agentic orchestration for information retrieval generalizes to the PubMedQA dataset. Additionally, the entire system consumes <3.5GB of RAM and generates responses within 8-15~seconds working on a consumer laptop. Our work serves as a practical blueprint for how agent-based systems can empower small, efficient models for medical domain information retrieval and synthesis, offering a tangible application of AI technology that could help advance health equity. We will release our dataset, code base, and prompts to foster further research in deployable and responsible clinical AI.

General Area: Applications and Practice

Specific Subject Areas: Deployment, Dataset Release & Characterization, Public & Social Health

Data And Code Availability: Yes

Ethics Board Approval: No

Entered Conflicts: I confirm the above

Anonymity: I confirm the above

Submission Number: 11