早期帕金森病识别混合特征选择数据集

数据集获取（Figshare）

• 源站标题：Early Parkinson’s disease identification via hybrid feature selection from multi-feature subsets and optimized CatBoost with SMOTE
• DOI：10.6084/m9.figshare.28924061.v1
• 发布日期：2025-05-02
• 文件数：41 个
• 文件总体积：11.49 MB
• 源站页面：https://tandf.figshare.com/articles/dataset/Early_Parkinson_s_disease_identification_via_hybrid_feature_selection_from_multi-feature_subsets_and_optimized_CatBoost_with_SMOTE/28924061

命令行下载

curl -L -o "tssc_a_2498909_sm0521.docx" "https://ndownloader.figshare.com/files/54154634"
curl -L -o "Figure 1.jpg" "https://ndownloader.figshare.com/files/54154637"
curl -L -o "Figure 10a.jpg" "https://ndownloader.figshare.com/files/54154640"
curl -L -o "Figure 10b.jpg" "https://ndownloader.figshare.com/files/54154643"
curl -L -o "Figure 11a.jpg" "https://ndownloader.figshare.com/files/54154646"
curl -L -o "Figure 11b.jpg" "https://ndownloader.figshare.com/files/54154649"
curl -L -o "Figure 12.jpg" "https://ndownloader.figshare.com/files/54154652"
curl -L -o "Figure 13a.jpg" "https://ndownloader.figshare.com/files/54154655"

文件清单

• tssc_a_2498909_sm0521.docx（16.81 KB）
• Figure 1.jpg（82.65 KB）
• Figure 10a.jpg（331.53 KB）
• Figure 10b.jpg（310.71 KB）
• Figure 11a.jpg（559.62 KB）
• Figure 11b.jpg（678.55 KB）
• Figure 12.jpg（698.29 KB）
• Figure 13a.jpg（250.46 KB）
• Figure 13b.jpg（270.99 KB）
• Figure 13c.jpg（595.77 KB）
• Figure 14.jpg（1.03 MB）
• Figure 2.jpg（341.06 KB）
• Figure 3a.jpg（719.84 KB）
• Figure 3b.jpg（218.27 KB）
• Figure 4.jpg（716.15 KB）
• Figure 5.jpg（722.14 KB）
• Figure 6.jpg（267.52 KB）
• Figure 7a.jpeg（147.82 KB）
• Figure 7b.jpeg（149.54 KB）
• Figure 7c.jpeg（149.46 KB）

文件总体积 11.49 MB（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

Achieving high accuracy, efficiency and robustness remains a primary challenge in Parkinson’'s disease (PD) detection, as existing methods often struggle with these aspects. Additionally, data imbalance in medical datasets further limits the reliability of current models. Given the critical role of precise PD classification in medical diagnostics, this study proposes a novel framework to enhance detection accuracy. The proposed framework leverages a strong categorical boosting (CatBoost) algorithm optimized using Grid Search Optimization (GSO). The analysis was conducted on a PD dataset derived from speech recording signals. To address the data imbalance, the synthetic minority oversampling technique (SMOTE) is applied as a pre-processing step to improve the robustness and reliability of the model. The framework is tested with several feature subsets, as well as their combined set. In addition, RReliefF feature selection was also applied to identify the optimal subset of features. For the selected feature subset, the proposed approach achieved an accuracy of 0.9261, precision of 0.9633, sensitivity of 0.9375, F1-score of 0.9502, specificity of 0.8947, AUC of 0.9549 and a testing time of 0.012s. These results underscore the effectiveness of the proposed framework in accurately diagnosing PD, thereby providing a reliable and efficient tool for future medical diagnostics.

许可

CC BY 4.0

引用

学术使用请引用 DOI 10.6084/m9.figshare.28924061.v1（source: https://tandf.figshare.com/articles/dataset/Early_Parkinson_s_disease_identification_via_hybrid_feature_selection_from_multi-feature_subsets_and_optimized_CatBoost_with_SMOTE/28924061）。