HIV阴性神经梅毒机器学习诊断多中心研究数据集
包含1648例HIV阴性疑似神经梅毒患者的临床与CSF数据，用于开发多指南机器学习诊断模型，并提供在线工具。
基本信息
资源简介
HIV阴性神经梅毒机器学习诊断多中心研究数据集
【一句话概览】
本数据集是 figshare 公开的结构化表格数据集，收录 2 个文件、合计 1.14 MB，主题涵盖 Neurosyphilis、machine learning、diagnosis、cerebrospinal fluid、external validation，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《Optimizing machine learning-based diagnosis of neurosyphilis in HIV-negative patients: a multicenter, real-world comparison of international diagnostic criteria》。配套论文《Optimizing machine learning-based diagnosis of neurosyphilis in HIV-negative patients: a multicenter, real-world comparison of international diagnostic criteria》发表于 Emerging Microbes & Infections（2026），DOI：10.1080/22221751.2026.2648888。项目资助方：This work was financially supported by National Natural Science Foundation of China [82072321], Natural Science Foundation of Guangdong Province [2025A1515011165], Fujian Provincial Health Technology Project [2024ZD01008], CAMS Innovation Fund for Medical Sciences [2025-I2M-C&T-B-081], Fujian provincial health technology project [2024ZD01008], Dermatology Hospital of Southern Medical University Basic Research Nursery Program [BR202406, BR202409], European Research Council Consolidator Grant [Agreement Number 101171779, Horizon Europe Program, ERC-2024-COG funding scheme].。源站首次发布：2026-04-17。
【数据内容】
源站原始描述：Neurosyphilis continues to rise globally, yet diagnosis remains challenging, often requiring multidisciplinary expertise and multiple CSF assays that are difficult to access in resource-limited settings. We developed and compared machine-learning (ML) models tailored to six international diagnostic guidelines and built a free, web-based tool for guideline-adapted decision support. We assembled 1,648 suspected neurosyphilis cases from four centers, using Guangzhou as the training cohort and Beiji…
【数据结构与技术规格】
文件数 2 个，合计 1.14 MB。temi_a_2648888_sm4162.jpg：image/jpeg，396.27 KB。temi_a_2648888_sm4161.docx：application/vnd.openxmlformats-officedocument.wordprocessingml.document，748.24 KB。数据集 DOI：10.6084/m9.figshare.31900984.v2。
【主题与分类】
源站学科分类：Medicine、Cell Biology、Neuroscience、Sociology、Biological Sciences not elsewhere classified、Information Systems not elsewhere classified。主题标签：Neurosyphilis、machine learning、diagnosis、cerebrospinal fluid、external validation。
【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://tandf.figshare.com/articles/dataset/Optimizing_Machine_Learning_Based_Diagnosis_of_Neurosyphilis_in_HIV-Negative_Patients_A_Multicenter_Real-World_Comparison_of_International_Diagnostic_Criteria/31900984
使用许可：CC BY 4.0（https://creativecommons.org/licenses/by/4.0/）。
规范引用：Optimizing machine learning-based diagnosis of neurosyphilis in HIV-negative patients: a multicenter, real-world comparison of international diagnostic criteria. Taylor & Francis. Jiang, Yinbo; Deng, Xinlei; Zhang, Xiaohui; Xu, Wenqi; Weng, Wenjia; Zhang, Xiangcai; et al
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：Optimizing machine learning-based diagnosis of neurosyphilis in HIV-negative patients: a multicenter, real-world comparison of international diagnostic criteria
- DOI：10.6084/m9.figshare.31900984.v2
- 发布日期：2026-04-17
- 文件数：2 个
- 文件总体积：1.14 MB
- 源站页面：https://tandf.figshare.com/articles/dataset/Optimizing_Machine_Learning_Based_Diagnosis_of_Neurosyphilis_in_HIV-Negative_Patients_A_Multicenter_Real-World_Comparison_of_International_Diagnostic_Criteria/31900984
命令行下载
curl -L -o "temi_a_2648888_sm4162.jpg" "https://ndownloader.figshare.com/files/63343927"
curl -L -o "temi_a_2648888_sm4161.docx" "https://ndownloader.figshare.com/files/63343930"
文件清单
temi_a_2648888_sm4162.jpg（396.27 KB）temi_a_2648888_sm4161.docx（748.24 KB）
文件总体积 1.14 MB（源站 API 实测）。
数据说明
Neurosyphilis continues to rise globally, yet diagnosis remains challenging, often requiring multidisciplinary expertise and multiple CSF assays that are difficult to access in resource-limited settings. We developed and compared machine-learning (ML) models tailored to six international diagnostic guidelines and built a free, web-based tool for guideline-adapted decision support. We assembled 1,648 suspected neurosyphilis cases from four centers, using Guangzhou as the training cohort and Beijing, Xiamen (China) and Seattle (USA) as external validation cohorts. Five algorithms (Random Forest, AdaBoost, SVC, NuSVC, XGBoost) were trained with randomized search and three-fold cross-validation; performance was assessed by AUC, PRAUC, calibration, decision-curve net benefit, Brier score, and SHAP for model explainability. Across models and guidelines, neurological symptoms, CSF protein, and CSF white blood cell count consistently ranked as the strongest predictors. All models achieved excellent discrimination (AUC and PRAUC >0.90) with good calibration, reliability, and positive clinical utility, though performance varied modestly by guideline. These findings indicate that the optimal ML approach depends on the diagnostic definition applied. Our freely available online tool operationalizes these models to provide clinicians worldwide with context-adapted support aligned to local criteria.
许可
CC BY 4.0
引用
学术使用请引用 DOI 10.6084/m9.figshare.31900984.v2（source: https://tandf.figshare.com/articles/dataset/Optimizing_Machine_Learning_Based_Diagnosis_of_Neurosyphilis_in_HIV-Negative_Patients_A_Multicenter_Real-World_Comparison_of_International_Diagnostic_Criteria/31900984）。
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。
