NeFut Logo NeFut
Admin Login

[CS.AI] GraphDx: A Cost-Aware Knowledge-Enhanced Framework for Sequential Diagnosis

Published at: 2026-07-20 22:00 Last updated: 2026-07-22 01:02
#AI #Machine Learning #Open Source

Abstract

Sequential diagnosis requires balancing diagnostic accuracy against resource costs through iterative information gathering. Existing Large Language Model (LLM) approaches exhibit a critical knowledge-reasoning gap: despite encoding extensive medical knowledge, they struggle to reason systematically under cost constraints, often resorting to excessive testing. We propose GraphDx, a knowledge-enhanced framework with two core innovations.

First, we design an automated pipeline that leverages LLMs to construct Medical Diagnosis Knowledge Graphs (MDKGs) with quantized typicality, action-centric topology, and dual-objective attributes for both diagnostic relevance and cost-sensitivity.

Second, we introduce three collaborative agents (Perception, Reasoning, and Decision) where the Perception and Decision Agents handle language understanding and generation, while the Reasoning Agent performs deterministic evidence scoring and cost-aware planning on the MDKG.

Experiments on MedQA and MIMIC-IV across three LLM backbones (DeepSeek-V3, Kimi-k2, Llama-3.3) show that GraphDx improves diagnostic success rates from 50--68% to 79--93% while reducing test costs by 20--54%, providing a robust, economical, and interpretable solution for automated clinical diagnosis.

Blogger's Review: The design of GraphDx focuses on enhancing diagnostic efficiency through knowledge graphs and multi-agent collaboration while considering cost factors, which is particularly crucial in the context of limited medical resources. Its innovative dual-objective attributes and automated pipeline deserve attention as they could guide future research in medical AI.

Original Source: https://arxiv.org/abs/2607.15280

[h] Back to Home