paper-with-me

홈 › Papers

MedSyn: LLM-based Synthetic Medical Text Generation Framework

2024-08-04 · Gleb Kumichev, Pavel Blinov, Yulia Kuzkina, Vasily Goncharov, Galina Zubkova, Nikolai Zenovkin, Aleksei Goncharov, Andrey Savchenko

Generating synthetic text addresses the challenge of data availability in privacy-sensitive domains such as healthcare. This study explores the applicability of synthetic data in real-world medical settings. We introduce MedSyn, a novel medical text generation framework that integrates large language models with a Medical Knowledge Graph (MKG). We use MKG to sample prior medical information for the prompt and generate synthetic clinical notes with GPT-4 and fine-tuned LLaMA models. We assess the benefit of synthetic data through application in the ICD code prediction task. Our research indicates that synthetic data can increase the classification accuracy of vital and challenging codes by up to 17.8% compared to settings without synthetic data. Furthermore, to provide new data for further research in the healthcare domain, we present the largest open-source synthetic dataset of clinical notes for the Russian language, comprising over 41k samples covering 219 ICD-10 codes.

📄 PDF Abstract BibTeX arXiv:2408.02056

Code (1)

milteam/MedSyn 공식 구현

Tasks

Text Generation

Methods 이 논문이 사용한 방법론

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
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

MedSynth: Realistic, Synthetic Medical Dialogue-Note Pairs

2025-08-02 · Ahmad Rezaie Mianroodi, Amirali Rezaie, Niko Grisel Todorov, Nadine A. Friedrich 외 arxiv

Physicians spend significant time documenting clinical encounters, a burden that contributes to professional burnout. To address this, robust automation tools for medical documentation are crucial. We introduce MedSynth …

Utilizing Synthetic Data for Medical Vision-Language Pre-training: Bypassing the Need for Real Images

2023-10-10 · Che Liu, Anand Shah, Wenjia Bai, Rossella Arcucci

Medical Vision-Language Pre-training (VLP) learns representations jointly from medical images and paired radiology reports. It typically requires large-scale paired image-text datasets to achieve effective pre-training f…

image-classificationImage Classificationobject-detectionObject Detection+1

MEDSYN: Benchmarking Multi-EviDence SYNthesis in Complex Clinical Cases for Multimodal Large Language Models

2026-02-25 · Boqi Chen, Xudong Liu, Jiachuan Peng, Marianne Frey-Marti 외 arxiv

Multimodal large language models (MLLMs) have shown great potential in medical applications, yet existing benchmarks inadequately capture real-world clinical complexity. We introduce MEDSYN, a multilingual, multimodal be…

Synthesizing High-Quality Visual Question Answering from Medical Documents with Generator-Verifier LMMs

2025-10-29 · Xiaoke Huang, Ningsen Wang, Hui Liu, Xianfeng Tang 외 arxiv

Large Multimodal Models (LMMs) are increasingly capable of answering medical questions that require joint reasoning over images and text, yet training general medical VQA systems is impeded by the lack of large, openly u…

Visual Question AnsweringReinforcement Learning

MedSyn2: Flexible Control of 3D CT Generation via Text and Semantically-Defined Segmentation Prompts

2026-05-31 · Weicheng Dai, Chenyu Wang, Binxu Li, Shantanu Ghosh 외 arxiv

Generative models for volumetric medical images have found many applications in medical imaging, ranging from data augmentation to serving as priors for inverse problems. For these applications, generating high-resolutio…

Image SegmentationData AugmentationImage Generation