一个基于树的可解释的人工智能模型用于早期检测Covid-19使用生理数据
Manar Abu Talib1, Yaman Afadar2, Qassim Nasir2
1Department of Computer Science, College of Computing and Informatics, University of Sharjah, P.O. Box 27272, Sharjah, UAE. mtalib@sharjah.ac.ae.
BMC medical informatics and decision making
|June 24, 2024
概括
可穿戴设备可以在症状出现之前预测COVID-19. 机器学习模型分析了心率和步骤数据,在早期发现疾病方面达到85%的准确性.
科学领域:
- 人工智能的人工智能
- 数据科学数据科学数据科学
- 可穿戴技术可穿戴技术
背景情况:
- 随着COVID-19的爆发,人们越来越需要早期的疾病检测.
- 可穿戴设备提供有价值的生理数据 (如心率,睡眠质量) 来识别炎症性疾病.
- 早期发现COVID-19对于减轻其影响至关重要.
研究的目的:
- 使用可穿戴设备的生理数据,在症状出现之前预测COVID-19感染的概率.
- 为了比较渐变增强,CatBoost和TabNet分类器在COVID-19检测中的性能.
- 为了提高模型的解释性和验证私人数据集上的发现.
主要方法:
- 利用现有的数据集,包括步数和心率数据.
- 训练并比较了梯度提升,CatBoost和TabNet模型.
- 将可解释性层应用于表现最佳的模型.
- 创建并分析Fitbit设备的私人数据集.
主要成果:
- CatBoost 分类器在公开数据集上实现了85%的准确性,超过了之前的研究.
- 预训练的CatBoost模型在私人Fitbit数据集上实现了81%的准确性.
- 模型可解释性提供了对预测有效性的详细评估.
结论:
- 机器学习模型,特别是CatBoost,可以在症状出现之前使用可穿戴设备数据有效预测COVID-19.
- 该研究证明了模型在不同数据集中的可靠性和通用性.
- 这种方法为早期COVID-19检测和公共卫生管理提供了有希望的工具.
相关概念视频
Steps in Outbreak Investigation
122
In the ever-evolving field of public health, statistical analysis serves as a cornerstone for understanding and managing disease outbreaks. By leveraging various statistical tools, health professionals can predict potential outbreaks, analyze ongoing situations, and devise effective responses to mitigate impact. For that to happen, there are a few possible stages of the analysis:
122
Physical Assessment of the Respiratory Tract II: Inspection
272
Physical assessment of the respiratory tract through inspection is a crucial step in understanding the patient's respiratory health. It provides insights into the functioning of the respiratory system, the musculoskeletal structure, and even the patient's nutritional status. This comprehensive approach involves observing several vital aspects: chest configuration, breathing patterns, respiratory rates, skin color, and use of accessory muscles.
Chest Configuration
The chest configuration...
Chest Configuration
The chest configuration...
272


