2026/01/01 by 谭少听, Shaoting Tan, Ning Liu +8
Computer Science · #Advanced Graph Neural Networks #Bayesian Modeling and Causal Inference #Feature (linguistics) #Focus (optics) #Identification (biology) #Key (lock) #Machine Learning in Healthcare #Set (abstract data type) #cs.AI
paper · pdf · doi:10.18653/v1/2026.findings-acl.1092
openalex publication_date 2026/01/01 · openalex created_date 2026/07/02 · openalex updated_date 2026/08/05
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 costaware 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.