CDSS数据集

“CDSS数据集”是由福建大数据一级开发有限公司依托福建省公共数据汇聚共享平台及“三医”数据资源中心构建的高质量医疗专识数据集 。该数据集规模为200kb，共包含1358条结构化文本数据 。其原始数据源自福建省200余家二级及以上定点医疗机构真实的医保结算单 。数据集的核心内容为医生专业画像，涵盖了医生的基本身份信息、执业机构，以及基于国际标准编码（ICD-10与ICD-9-CM-3）统计的疾病诊疗与手术操作经验频次 。全部数据均经过严格的过滤与脱敏处理，彻底剔除了患者个人隐私信息，在坚守“原始数据不出域、数据可用不可见”的安全红线下开展授权使用 。

The CDSS Dataset is a high-quality medical expertise dataset constructed by Fujian Big Data First-level Development Co., Ltd. based on the Fujian Provincial Public Data Aggregation and Sharing Platform and the "Three Medical" Data Resource Center. It has a total size of 200 KB and contains 1,358 structured text data entries. The raw data of the dataset is sourced from real medical insurance settlement statements from over 200 designated medical institutions at or above the secondary level in Fujian Province. The core of the dataset comprises professional profiles of medical practitioners, covering their basic personal information, practicing institutions, as well as frequency statistics of disease diagnosis, treatment and surgical operations calculated in accordance with international standard coding systems (ICD-10 and ICD-9-CM-3). All data has undergone strict filtering and de-identification processing, with all personal privacy information of patients thoroughly removed. Authorized utilization is conducted under the security red line that adheres to the principles of "raw data shall not leave the domain, and data is accessible but not visible".

搜集汇总

背景与挑战

背景概述

CDSS数据集是一个由福建大数据一级开发有限公司构建的医疗专识数据集，包含1358条结构化文本数据，源自福建省200余家定点医疗机构的医保结算单。该数据集以医生专业画像为核心，涵盖医生基本信息和基于ICD编码的疾病诊疗与手术操作经验频次，经过严格脱敏处理，在保障数据安全的前提下支持临床决策和医疗资源调度。