远程眼科研究分析

基于UPMC远程眼科项目的糖尿病视网膜病变筛查分析,涵盖2008-2020年94家诊所、21,960次检查的定量与叙事数据。

NIAID Data Ecosystem
浏览 12
多模态within normal limitsprimary care clinicsnecessitating frequent examinationsminimal camera downtimemacular exudate )beyond technical contributionsbalanced gender distribution96 &# 177458 unique individuals25 &# 8211program conducted 21program &# 8217
Teleophthalmology studies analysis

基本信息

模态
多模态
大小
0.000068943 GB
许可
CC BY 4.0
创建/更新时间
2026-10-11
版本
v1

资源简介

远程眼科研究分析

【一句话概览】

本数据集是 figshare 公开的多模态数据集,收录 1 个文件、合计 68.94 KB,主题涵盖 within normal limits、primary care clinics、necessitating frequent examinations、minimal camera downtime、macular exudate ),,可用于跨模态对齐与融合建模研究,CC BY 4.0 许可开放获取。

【数据集背景】

本数据集源站标题为《Teleophthalmology studies analysis.》。源站首次发布:2024-07-12。

【数据内容】

源站原始描述:Diabetic Retinopathy stands as a leading cause of irreversible blindness, necessitating frequent examinations, especially in the early stages where effective treatments are available. However, current examination rates vary widely, ranging from 25–60%. This study scrutinizes the Point-of-Care Diabetic Retinopathy Examination Program at the University of Pittsburgh/UPMC, delving into its composition, evolution, challenges, solutions, and improvement opportunities. Employing a narrative approach,…

【数据结构与技术规格】

文件数 1 个,合计 68.94 KB。pone.0305586.s003.xlsx:application/vnd.openxmlformats-officedocument.spreadsheetml.sheet,68.94 KB。数据集 DOI:10.1371/journal.pone.0305586.s003。

【主题与分类】

源站学科分类:Medicine、Chemical Sciences not elsewhere classified、Biological Sciences not elsewhere classified、Science Policy、Infectious Diseases。主题标签:within normal limits、primary care clinics、necessitating frequent examinations、minimal camera downtime、macular exudate ),、beyond technical contributions、balanced gender distribution、96 &# 177、458 unique individuals、25 &# 8211。

【适用方向】

多模态数据适合跨模态对齐、融合建模与联合表征学习方向的研究。

【获取与许可】

源站页面:https://plos.figshare.com/articles/dataset/Teleophthalmology_studies_analysis_/26276584

使用许可:CC BY 4.0(https://creativecommons.org/licenses/by/4.0/)。

规范引用:Bonilla-Escobar, Francisco J.; Ghobrial, Anthony I.; Gallagher, Denise S.; Eller, Andrew; Waxman, Evan L. (2024). Teleophthalmology studies analysis.. PLOS ONE. Dataset

官方服务

专家保障全链路合规授权与标注交付

陕川双基地 × 超十家三甲医院直连

从合规授权、采集治理、专业标注到数据集交付,我们提供全链路闭环服务,让高质量临床数据即拿即用。

⚡️ 需要原始数据或标注支持?联系我们获取定制方案。

帮我联系

下载信息

注册下载

需要注册 Kaggle 账号并登录后下载,适合需要跟踪下载记录和使用 API 的用户。

暂未开放

公开下载

无需注册即可直接获取公开样本或文档,适合快速预览和评估数据集质量。

免登录

有偿下载

公开数据集受托下载与技术交付服务。

提供高速下载与技术交付服务(收技术服务费,非数据销售)

暂未开放

当前数据集主要来源为 Kaggle 公开托管,完整影像包建议通过原始链接或 Kaggle API 获取。

使用方式

数据集获取(Figshare)

命令行下载

curl -L -o "pone.0305586.s003.xlsx" "https://ndownloader.figshare.com/files/47639584"

文件清单

  • pone.0305586.s003.xlsx(68.94 KB)

文件总体积 68.94 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

Diabetic Retinopathy stands as a leading cause of irreversible blindness, necessitating frequent examinations, especially in the early stages where effective treatments are available. However, current examination rates vary widely, ranging from 25–60%. This study scrutinizes the Point-of-Care Diabetic Retinopathy Examination Program at the University of Pittsburgh/UPMC, delving into its composition, evolution, challenges, solutions, and improvement opportunities. Employing a narrative approach, insights are gathered from key stakeholders, including ophthalmologists and staff from primary care clinics. A quantitative analysis from 2008 to 2020 provides a comprehensive overview of program outcomes, covering 94 primary care offices with 51 retinal cameras. Program components feature automated non-mydriatic 45° retinal cameras, a dedicated coordinator, rigorous training, and standardized workflows. Over this period, the program conducted 21,960 exams in 16,458 unique individuals, revealing a diverse population with an average age of 58.5 and a balanced gender distribution. Average body mass index (33.96±8.02 kg/m2) and hemoglobin A1c (7.58%±1.88%) surpassed normal ranges, indicating prevalent risk factors for diabetes-related complications. Notably, 24.2% of patients underwent more than one exam, emphasizing program engagement. Findings indicated that 86.3% of exams were gradable, with 59.0% within normal limits, 12.1% showing some evidence of diabetic retinopathy, and 6.4% exhibiting vision-threatening diabetic retinopathy. Follow-up appointments with ophthalmologists were recommended in 31.5% of exams due to indeterminate results, positive diabetic retinopathy (≥moderate or macular exudate), or other findings like age-related macular degeneration or suspected glaucoma. The program demonstrated high reproducibility across diverse healthcare settings, featuring a sustainable model with minimal camera downtime, standardized workflows, and financial support from grants, health systems, and clinical revenues. Despite COVID-19 pandemic challenges, this research emphasizes the program’s reproducibility, user-friendly evolution, and promising outcomes. Beyond technical co

许可

CC BY 4.0

引用

学术使用请引用 DOI 10.1371/journal.pone.0305586.s003(source: https://plos.figshare.com/articles/dataset/Teleophthalmology_studies_analysis_/26276584)。

数据缺失?

依托陕西、四川两大基地,我们与超过十家三甲医院建立直接合作关系,覆盖合规授权、采集治理、专业标注、数据交付的全流程,为AI医疗团队提供即拿即用的高质量临床数据。

⚡️ 需要数据支持或标注服务?立即联系我们获取专业方案。

获取专属数据定制方案