Jove
Visualize
联系我们
JoVE
x logofacebook logolinkedin logoyoutube logo
关于 JoVE
概览领导团队博客JoVE 帮助中心
作者
出版流程编辑委员会范围与政策同行评审常见问题投稿
图书馆员
用户评价订阅访问资源图书馆顾问委员会常见问题
研究
JoVE JournalMethods CollectionsJoVE Encyclopedia of Experiments存档
教育
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab Manual教师资源中心教师网站
使用条款与条件
隐私政策
政策

相关概念视频

Receiver Operating Characteristic Plot01:15

Receiver Operating Characteristic Plot

82
A ROC (Receiver Operating Characteristic) plot is a graphical tool used to assess the performance of a binary classification model by illustrating the trade-off between sensitivity (true positive rate) and specificity (false positive rate). By plotting sensitivity against 1 - specificity across various threshold settings, the ROC curve shows how well the model distinguishes between classes, with a curve closer to the top-left corner indicating a more accurate model. The area under the ROC curve...
82

您也可能阅读

相关文章

通过共同作者、期刊和引用图与本文相关的文章。

排序
Same author

A quantum resistant chaos driven image encryption framework for secure visual data transmission in intelligent transportation systems.

Scientific reports·2026
Same author

Self-supervised cross frame-rate event-frame depth learning without ground truth.

Scientific reports·2026
Same author

Resource-efficient federated machine unlearning via evolutionary synaptic pruning for cloud-based distributed learning systems.

Scientific reports·2026
Same author

Geochemical and machine learning approaches to groundwater fluoride prediction in Karaga District, Northern Ghana.

Scientific reports·2026
Same author

An attention-based multimodal deep learning framework integrating EEG and ECG for enhanced stress detection.

Scientific reports·2026
Same author

A hybrid machine learning approach for detecting DDoS attacks in software-defined networks.

Scientific reports·2026

相关实验视频

Updated: Jun 6, 2025

Selecting Multiple Biomarker Subsets with Similarly Effective Binary Classification Performances
07:35

Selecting Multiple Biomarker Subsets with Similarly Effective Binary Classification Performances

Published on: October 11, 2018

7.4K

使用集体机器学习模型与合成少数人过量采样技术进行稳健的糖尿病预测.

Pradeepa Sampath1, Gurupriya Elangovan2, Kaaveya Ravichandran2

  • 1Department of Information Technology, School of Computing, SASTRA Deemed University, Thanjavur, 613401, Tamilnadu, India.

Scientific reports
|November 23, 2024
PubMed
概括

这项研究引入了一种先进的机器学习模型,用于准确预测糖尿病. 通过将AdaBoost和XGBoost与SMOTE平衡相结合,它可以显著改善早期检测和糖尿病管理结果.

关键词:
在 AdaBoost 中使用 AdaBoost.糖尿病患者 糖尿病患者机器学习 机器学习异常值检测异常值的检测在SMOTE中使用.在XGBoost中使用.

更多相关视频

Author Spotlight: Impact of Intergenic Interactions on Disease-Identifying Dark Biomarkers
03:37

Author Spotlight: Impact of Intergenic Interactions on Disease-Identifying Dark Biomarkers

Published on: March 1, 2024

641
A Machine Learning Approach to Design an Efficient Selective Screening of Mild Cognitive Impairment
12:18

A Machine Learning Approach to Design an Efficient Selective Screening of Mild Cognitive Impairment

Published on: January 11, 2020

7.5K

相关实验视频

Last Updated: Jun 6, 2025

Selecting Multiple Biomarker Subsets with Similarly Effective Binary Classification Performances
07:35

Selecting Multiple Biomarker Subsets with Similarly Effective Binary Classification Performances

Published on: October 11, 2018

7.4K
Author Spotlight: Impact of Intergenic Interactions on Disease-Identifying Dark Biomarkers
03:37

Author Spotlight: Impact of Intergenic Interactions on Disease-Identifying Dark Biomarkers

Published on: March 1, 2024

641
A Machine Learning Approach to Design an Efficient Selective Screening of Mild Cognitive Impairment
12:18

A Machine Learning Approach to Design an Efficient Selective Screening of Mild Cognitive Impairment

Published on: January 11, 2020

7.5K

科学领域:

  • 医疗信息学 医疗信息学
  • 机器学习 机器学习
  • 公共卫生 公共卫生

背景情况:

  • 糖尿病是一种全球性健康危机,其特点是胰岛素抵抗或缺乏,导致高血糖症.
  • 血糖水平升高可能导致严重并发症,包括脏疾病,视力丧失和心血管疾病.
  • 早期诊断对于管理糖尿病和预防其严重的健康后果至关重要.

研究的目的:

  • 开发和验证一个强大的机器学习框架,用于准确预测糖尿病.
  • 通过数据预处理和组合技术来提高预测模型的性能.
  • 提高早期检测率,以更好地管理糖尿病和改善患者的治疗结果.

主要方法:

  • 数据预处理包括缺失值的归算和异常值的拒绝.
  • 使用相关性分析进行了特征选择.
  • 通过使用合成少数人过量采样技术 (SMOTE) 来平衡类分布.
  • 整体机器学习模型,特别是AdaBoost和XGBoost,用于预测.

主要成果:

  • 拟议的AdaBoost和XGBoost组合模型实现了曲线下的面积 (AUC) 为0.968 +/- 0.015.
  • 这种性能超过了研究中评估的替代方法.
  • 该模型展示了糖尿病预测准确性的最新结果.

结论:

  • 开发的框架为早期糖尿病预测提供了一种高度有效的方法.
  • 将SMOTE与整体方法的整合显著提高了预测性能.
  • 这种模式有望促进糖尿病管理和改善医疗保健结果.