ICD-AIS严重损伤映射数据集

数据集获取（Figshare）

• 源站标题：Development of an expert derived ICD-AIS map for serious AIS3+ injury identification
• DOI：10.6084/m9.figshare.11950392.v1
• 发布日期：2020-03-06
• 文件数：2 个
• 文件总体积：47.28 KB
• 源站页面：https://tandf.figshare.com/articles/dataset/Development_of_an_expert_derived_ICD-AIS_map_for_serious_AIS3_injury_identification/11950392

命令行下载

curl -L -o "Appendix table A2.docx" "https://ndownloader.figshare.com/files/21937713"
curl -L -o "Appendix_table_A1.docx" "https://ndownloader.figshare.com/files/21937716"

文件清单

• Appendix table A2.docx（21.71 KB）
• Appendix_table_A1.docx（25.57 KB）

文件总体积 47.28 KB（源站 API 实测）。

数据加载示例（图像类）

from PIL import Image
import glob, os

files = (glob.glob(os.path.join(path, "**", "*.png"), recursive=True)
       + glob.glob(os.path.join(path, "**", "*.jpg"), recursive=True)
       + glob.glob(os.path.join(path, "**", "*.tif"), recursive=True))
print("图像文件数:", len(files))
img = Image.open(files[0]); print("尺寸/模式:", img.size, img.mode)

# torchvision Dataset 方式:
# from torchvision import datasets
# ds = datasets.ImageFolder(path)  # 要求 子目录=类别

目录组织与标注格式以源站说明和下载后实际文件为准。

数据说明

Objective: The objective of the mapping project was to develop an expert derived map between the International Statistical Classification of Diseases and Related Health Problems (ICD) clinical modifications (CM) and the Abbreviated Injury Scale (AIS) to be able to relate AIS severity to ICD coded data road traffic collision data in EU datasets. The maps were developed to enable the identification of serious AIS3+ injury and provide details of the mapping process for assumptions to be made about injury severity from mass datasets. This article describes in detail the mapping process of the International Classification of Diseases Ninth Revision, Clinical Modification (ICD-9-CM) and the International Classification of Diseases Tenth Revision, Clinical Modification (ICD-10-CM) codes to the Abbreviated Injury Scale 2005, Update 2008 (AIS08) codes to identify injury with an AIS severity of 3 or more (AIS3+ severity) to determine ‘serious’ (MAIS3+) road traffic injuries.
Methods: Over 19,000 ICD codes were mapped from the following injury categories; injury ICD-9-CM (Chapter 17) codes between ‘800 and 999.9’ and injury ICD-10-CM (Chapter 19) ‘S’ and ‘T’ prefixed codes were reviewed and mapped to an AIS08 category and then relate the severity to three groups; AIS3+, AIS Results: In total 2,504 ICD-9-CM codes were mapped to the AIS, of which 780 (31%) were assigned an AIS3+ severity. For the16,508 ICD-10-CM mapped codes a total of 2,323 (14%) were assigned an AIS3+ severity. Some 17% (n = 426) and 27% (n = 4,485) of ICD-9-CM and ICD-10-CM codes respectively were assigned to AIS9 (no-map) following the mapping process. It was evident there were ‘problem’ codes that could not be easily mapped to an AIS code to reflect severity. Problem maps affect the specificity of the map and severity when used to translate historical data in large datasets.
Conclusions: The Association for the Advancement in Automotive Medicine, AAAM-endorsed expert-derived map offers a unique tool to road safety researchers to establish the number of MAIS3+ serious injuries occurring on the roads. The detailed process offered in this paper will enable researchers to understand the decision making an

许可

CC BY 4.0

引用

学术使用请引用 DOI 10.6084/m9.figshare.11950392.v1（source: https://tandf.figshare.com/articles/dataset/Development_of_an_expert_derived_ICD-AIS_map_for_serious_AIS3_injury_identification/11950392）。