医疗保健数据集中的特征选择:走向可通用化解决方案
Ida Maruotto1, Federica Kiyomi Ciliberti1, Paolo Gargiulo2
1Institute of Biomedical and Neural Engineering, Reykjavik University, Reykjavik, Iceland.
Computers in biology and medicine
|July 30, 2025
概括
本研究引入了一个可扩展的整体特征选择 (FS) 策略,以减少医疗保健数据中的维度. 该方法有效地识别了关键特征,提高了机器学习模型的性能和临床可解释性.
科学领域:
- 生物医学信息学 生物医学信息学
- 医疗保健中的机器学习
- 数据科学数据科学数据科学
背景情况:
- 高维的医疗保健数据集对临床数据分析和解释提出了挑战.
- 减小尺寸对于有效和准确的临床见解至关重要.
- 当前的方法可能会与多生物识别和异质数据作斗争.
研究的目的:
- 为多生物识别医疗保健数据集开发一个可扩展的整体特征选择 (FS) 策略.
- 为了解决减小维度的需求,并确定显著的临床特征.
- 提高机器学习模型的性能和临床解释性.
主要方法:
- 一个新的布选择,整合了基于树的特征排名和贪的倒退消除.
- 一个合并策略,将特征子集结合为一个单一的,临床相关的集.
- 适用于不同的数据集:BioVRSea (生物信号) 和SinPain (医疗图像).
主要成果:
- 实现了显著的维度减少,在某些特征子集中超过50%.
- 减少的特征集保持或改进了分类指标 (支持向量机,随机森林).
- 在生物信号和基于图像的医疗保健数据上表现出有效性.
结论:
- 整体FS方法保留了临床结果歧视的基本特征.
- 结果的模型在计算上是高效的,在临床上是可解释的.
- 这种可扩展和可适应的方法显示出作为医疗保健研究的通用化工具的潜力.
相关概念视频
01:29Issues And Trends In Healthcare Delivery System
5.8K
The issues and trends in healthcare delivery are constantly changing. The COVID-19 pandemic is one recent issue that wreaked havoc on healthcare systems, causing a shortage of healthcare workers, high demand for medicines and supplies, and increased medical expenditure due to a lack of insurance. Other issues include rising healthcare costs and care fragmentation.
Cost Containment
Payment for healthcare services has historically promoted adoption of costly and often unnecessary or inefficient...
Cost Containment
Payment for healthcare services has historically promoted adoption of costly and often unnecessary or inefficient...
5.8K
01:30Health Information Technology and Healthcare Information System
923
Health Information Technology (HIT)
Health Information Technology, commonly called HIT, integrates advanced information systems and technology in healthcare settings. Its primary functions include:
Health Information Technology, commonly called HIT, integrates advanced information systems and technology in healthcare settings. Its primary functions include:
923