按年龄-性别亚组的差结果率
包含按年龄和性别分层的牙科治疗差结果率，来源自回顾性队列研究，用于分析摄入表格视觉复杂性与预后的关联。
基本信息
资源简介
按年龄-性别亚组的差结果率
【一句话概览】
本数据集是 figshare 公开的结构化表格数据集，收录 1 个文件、合计 5.63 KB，主题涵盖 support risk stratification、significantly higher risk、senior attending dentist、remain largely unexplored、processed using python，可用于统计建模、特征工程与队列分析，CC BY 4.0 许可开放获取。
【数据集背景】
本数据集源站标题为《Poor outcome rate by age-sex subgroup.》。源站首次发布：2025-09-04。
【数据内容】
源站原始描述：Background While many factors influence dental treatment outcomes, the visual characteristics of intake forms—such as the amount of handwriting—remain largely unexplored. Clinical impressions suggest that minimal or excessive form completion may reflect patient engagement or psychological disposition. To examine whether the visual complexity of intake forms, quantified as a “writing ratio,” is associated with treatment prognosis in dental settings. Methods This retrospective cohort study include…
中文译文（机器翻译，仅供快速理解，请以原文为准）：背景 尽管多种因素会影响牙科治疗结局，但接诊表格的视觉特征——例如手写内容的多少——在很大程度上仍未被探索。临床印象提示，表格填写过少或过多可能反映患者的参与度或心理倾向。本研究旨在探讨接诊表格的视觉复杂度（以“书写比率”量化）是否与牙科治疗预后相关。 方法 这项回顾性队列研究纳入了2016年在福冈齿科大学医院接受综合牙科咨询的813例患者。对接诊表格进行扫描，并使用Python和OpenCV进行处理，以计算书写比率，即图像中黑色像素的百分比。根据该比率将患者分为三分位组（低、中、高）。采用多变量logistic回归评估其与不良治疗结局（定义为失访或由临床医生发起的终止治疗）之间的关联，并校正年龄、性别、诊断以及最高年资主治牙医的经验。利用关键预测因素构建了一个探索性评分系统，并通过ROC分析进行评估。 结果 与中书写比率组相比，低书写比率组患者发生不良结局的风险显著更高（校正OR = 1.53，95% CI：1.07–2.18，p = 0.019）。中组与高组之间未观察到显著差异。中年女性亚组表现出最高的失访率。探索性评分系统显示出中等程度的区分能力（AUC = 0.544）。 结论 接诊表格视觉复杂度较低可能反映患者参与度不足或沟通不清，并与较差的治疗结局相关。接诊表格的外观可能作为早期行为指标，并支持牙科诊疗中的风险分层。重新设计接诊表格以同时捕捉结构和行为线索，可能有助于加强早期临床评估和照护计划。
【数据结构与技术规格】
文件数 1 个，合计 5.63 KB。Table 3.xls：application/vnd.ms-excel，5.63 KB。数据集 DOI：10.1371/journal.pone.0331615.t003。
【主题与分类】
源站学科分类：Cell Biology、Neuroscience、Pharmacology、Biotechnology、Cancer、Mental Health。主题标签：support risk stratification、significantly higher risk、senior attending dentist、remain largely unexplored、processed using python、poor outcomes compared、multivariable logistic regression、exploratory scoring system、early behavioral indicator、clinical impressions suggest。
【适用方向】
结构化表格数据可直接用于统计建模、特征工程与队列分析。
【获取与许可】
源站页面：https://plos.figshare.com/articles/dataset/Poor_outcome_rate_by_age-sex_subgroup_/30055544
使用许可：CC BY 4.0（https://creativecommons.org/licenses/by/4.0/）。
规范引用：Umezaki, Yojiro; Sudo, Takeaki; Motomura, Haruhiko; Morita, Hiromitsu; Naito, Toru (2025). Poor outcome rate by age-sex subgroup.. PLOS ONE. Dataset
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）
- 源站标题：Poor outcome rate by age-sex subgroup.
- DOI：10.1371/journal.pone.0331615.t003
- 发布日期：2025-09-04
- 文件数：1 个
- 文件总体积：5.63 KB
- 源站页面：https://plos.figshare.com/articles/dataset/Poor_outcome_rate_by_age-sex_subgroup_/30055544
命令行下载
curl -L -o "Table 3.xls" "https://ndownloader.figshare.com/files/57675797"
文件清单
Table 3.xls（5.63 KB）
文件总体积 5.63 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
Background
While many factors influence dental treatment outcomes, the visual characteristics of intake forms—such as the amount of handwriting—remain largely unexplored. Clinical impressions suggest that minimal or excessive form completion may reflect patient engagement or psychological disposition. To examine whether the visual complexity of intake forms, quantified as a “writing ratio,” is associated with treatment prognosis in dental settings.
Methods
This retrospective cohort study included 813 patients who received a comprehensive dental consultation at Fukuoka Dental College Hospital in 2016. Intake forms were scanned and processed using Python and OpenCV to calculate the writing ratio, defined as the percentage of black pixels in the image. Patients were categorized into tertiles (Low, Mid, High) based on this ratio. Multivariable logistic regression was used to assess associations with poor treatment outcomes (defined as dropout or clinician-initiated discontinuation), adjusting for age, sex, diagnosis, and the experience of the most senior attending dentist. An exploratory scoring system was constructed using key predictors and evaluated via ROC analysis.
Results
Patients in the Low writing ratio group had a significantly higher risk of poor outcomes compared to the Mid group (adjusted OR = 1.53, 95% CI: 1.07–2.18, p = 0.019). No significant difference was observed between the Mid and High groups. A subgroup of middle-aged females exhibited the highest dropout rate. The exploratory scoring system showed modest discriminative performance (AUC = 0.544).
Conclusions
Lower visual complexity of intake forms may reflect disengagement or unclear communication and is associated with poorer treatment outcomes. Intake form appearance may serve as an early behavioral indicator and support risk stratification in dental care. Redesigning intake forms to capture both structural and behavioral cues may enhance early clinical assessment and care planning.
许可
CC BY 4.0
引用
学术使用请引用 DOI 10.1371/journal.pone.0331615.t003（source: https://plos.figshare.com/articles/dataset/Poor_outcome_rate_by_age-sex_subgroup_/30055544）。
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。
