在医学光谱学中,疾病亚型的分类用于基于分组和层次学习的多类样本失衡
Rui Gao1, Zishuo Chen1, Zilong Shao2
1College of Software, Xinjiang University, Urumqi, Xinjiang, China, China.
Lasers in medical science
|May 19, 2025
概括
这项研究引入了一种新的分层增量学习方法,使用血清拉曼光谱来改善疾病亚型,有效地解决不平衡数据的挑战,并提高类似疾病的诊断准确性.
科学领域:
- 医学诊断 医学诊断 医学诊断
- 生物医学数据分析
- 机器学习在医疗保健中的应用
背景情况:
- 医疗数据集经常存在类不平衡,阻碍了准确的多类分类模型的开发.
- 疾病亚型的分化尤其具有挑战性,因为样本大小不平衡,影响诊断可靠性.
- 血清拉曼光谱为疾病检测提供了一个有希望的,非侵入性的方法,但需要强大的分析模型.
研究的目的:
- 开发一种新的方法来解决血清拉曼光谱数据中的多类不平衡,用于疾病亚型.
- 提高模型在区分类似疾病亚型时的准确性,即使样本大小有限.
- 通过与已建立的机器学习模型对拟议方法的性能进行验证.
主要方法:
- 采用分层增量学习方法,按噪声水平分组样本,以平衡训练数据.
- 该方法减轻了通过数据增强引入的噪声,提高了模型稳定性.
- 卷积神经网络 (CNN) 和随机森林 (RF) 模型使用原始和增强的血清拉曼光谱数据进行了比较.
主要成果:
- 拟议的方法实现了高精度和F1得分,超过95%,在不平衡数据的肝炎亚型.
- 该方法在区分类似疾病亚型方面表现出有效性,特别是那些样本规模有限的亚型.
- 与标准CNN和RF模型相比,在不平衡的数据集上观察到性能改善.
结论:
- 层次增量学习方法为血清拉曼光谱中的多类不平衡提供了强大的解决方案,用于疾病亚型.
- 该方法显示出在具有挑战性的医学分类任务中提高诊断准确性的巨大潜力.
- 需要进一步验证,以确认拟议方法在各种疾病中具有更广泛的适用性和通用性.
相关概念视频
How Data are Classified: Categorical Data
31.3K
A variable, usually notated by capital letters such as X and Y, is a characteristic or measurement that can be determined for each member of a population. Data are the actual values of variables. They may be numbers, or they may be words. Datum is a single value.
Data are classified based on whether they are measurable or not. Categorical data cannot be measured; instead, it can be divided into categories. For example, if Y denotes a person's party affiliation, some examples of Y include...
Data are classified based on whether they are measurable or not. Categorical data cannot be measured; instead, it can be divided into categories. For example, if Y denotes a person's party affiliation, some examples of Y include...
31.3K
Stratified Sampling Method
11.7K
Sampling is a technique to select a portion (or subset) of the larger population and study that portion (the sample) to gain information about the population. The sampling method ensures that samples are drawn without bias and accurately represent the population. Because measuring the entire population in a study is not practical, researchers use samples to represent the population of interest.
To choose a stratified sample, divide the population into groups called strata and then take a...
To choose a stratified sample, divide the population into groups called strata and then take a...
11.7K


