Transformer models trained on MIMIC-III to generate synthetic patient notes

PhysioNet2026-06-27 收录

医疗文本生成

临床文档合成

数据链接：

https://physionet.org/content/transformer-synthetic-note/1.0.0/数据链接链接失效反馈

官方服务：

资源简介：

Machine learning models that have been trained using MIMIC-III to enable the creation of synthetic discharge summaries.

ChuGyouk/KoMedInstruct-52k

医疗文本生成

跨语言翻译

Ko-AlpaCare数据集是MedInstruct-52k的韩语翻译版本，MedInstruct-52k是一个用于医疗领域的合成生成的指令数据集。该数据集主要用于文本生成任务，涵盖了医疗相关的指令和回答。翻译过程中使用了DeepL Pro应用，并且提到了一些翻译过程中遇到的问题，如重复数据、幻觉风险以及输入输出中包含相同数据的情况。

Hugging Face2024-06-29 更新230

AdapterOcean/med_alpaca_standardized_cluster_36_alpaca

指令微调

医疗文本生成

--- dataset_info: features: - name: input dtype: string - name: output dtype: string splits: - name: train num_bytes: 141351 num_examples: 129 download_size: 71946 datase

Hugging Face2023-10-23 更新80

AdapterOcean/med_alpaca_standardized_cluster_95_alpaca

医疗文本生成

指令微调

--- dataset_info: features: - name: input dtype: string - name: output dtype: string splits: - name: train num_bytes: 15784496 num_examples: 9641 download_size: 8061413 d

Hugging Face2023-10-24 更新60

MIMIC-IV-Ext-GPT-3_5-Generated-Discharge-Summaries-for-Low-Resource-Codes

医疗文本生成

ICD国际疾病分类

This dataset comprises 9,606 Synthetic Discharge Summaries generated by GPT-3.5 based on combinations of ICD-10-code descriptions associated with real discharge summaries in MIMIC-IV. As part of the g

DataCite Commons2024-12-16 更新90

AdapterOcean/med_alpaca_standardized_cluster_88_alpaca

指令微调

医疗文本生成

--- dataset_info: features: - name: input dtype: string - name: output dtype: string splits: - name: train num_bytes: 8123207 num_examples: 5946 download_size: 4196884 da

Hugging Face2023-10-24 更新80

Transformer models trained on MIMIC-III to generate synthetic patient notes

资源简介：

相关数据集