paper-with-me

Papers

DiReCT: Diagnostic Reasoning for Clinical Notes via Large Language Models

2024-08-04 · Bowen Wang, Jiuyang Chang, Yiming Qian, Guoxin Chen, JunHao Chen, Zhouqiang Jiang, Jiahao Zhang, Yuta Nakashima, Hajime Nagahara

Large language models (LLMs) have recently showcased remarkable capabilities, spanning a wide range of tasks and applications, including those in the medical domain. Models like GPT-4 excel in medical question answering but may face challenges in the lack of interpretability when handling complex tasks in real clinical settings. We thus introduce the diagnostic reasoning dataset for clinical notes (DiReCT), aiming at evaluating the reasoning ability and interpretability of LLMs compared to human doctors. It contains 511 clinical notes, each meticulously annotated by physicians, detailing the diagnostic reasoning process from observations in a clinical note to the final diagnosis. Additionally, a diagnostic knowledge graph is provided to offer essential knowledge for reasoning, which may not be covered in the training data of existing LLMs. Evaluations of leading LLMs on DiReCT bring out a significant gap between their reasoning ability and that of human doctors, highlighting the critical need for models that can reason effectively in real-world clinical scenarios.

📄 PDF Abstract BibTeX arXiv:2408.01933

Code (1)

wbw520/direct 공식 구현 pytorch

Tasks

DiagnosticMedical Question AnsweringQuestion Answering

Methods 이 논문이 사용한 방법론

Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
Multi-Head Attention 설명 없음
Position-Wise Feed-Forward Layer 설명 없음
Adam 설명 없음
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…

Similar Papers 제목 키워드 기반

Note2Chat: Improving LLMs for Multi-Turn Clinical History Taking Using Medical Notes

2026-01-29 · Yang Zhou, Zhenting Sheng, Mingrui Tan, Yuting Song 외 arxiv

Effective clinical history taking is a foundational yet underexplored component of clinical reasoning. While large language models (LLMs) have shown promise on static benchmarks, they often fall short in dynamic, multi-t…

Data Augmentation

Embeddings to Diagnosis: Latent Fragility under Agentic Perturbations in Clinical LLMs

2025-07-27 · Raj Krishnan Vijayaraj arxiv

LLMs for clinical decision support often fail under small but clinically meaningful input shifts such as masking a symptom or negating a finding, despite high performance on static benchmarks. These reasoning failures fr…

Automated Clinical Problem Detection from SOAP Notes using a Collaborative Multi-Agent LLM Architecture

2025-08-29 · Yeawon Lee, Xiaoyang Wang, Christopher C. Yang arxiv

Accurate interpretation of clinical narratives is critical for patient care, but the complexity of these notes makes automation challenging. While Large Language Models (LLMs) show promise, single-model approaches can la…

Uncertainty-Aware Large Language Models for Explainable Disease Diagnosis

2025-05-06 · Shuang Zhou, Jiashuo Wang, Zidu Xu, Song Wang 외

Explainable disease diagnosis, which leverages patient information (e.g., signs and symptoms) and computational models to generate probable diagnoses and reasonings, offers clear clinical values. However, when clinical n…

DiagnosticLanguage ModelingLanguage ModellingLarge Language Model

Teaching large language models to reason like expert diagnosticians

2025-09-15 · Thomas A. Buckley, Riccardo Conci, Peter G. Brodeur, Jason Gusdorf 외 arxiv

Differential diagnosis is an iterative process that integrates patient information with broader medical knowledge. Clinical case series such as the NEJM Clinicopathologic Conferences (CPCs), published continuously since …