考虑培训数据中的不确定性,以提高机器学习性能,预测早期多发性硬化症新疾病活动的预测
Maryam Tayyab1,2, Luanne M Metz3, David K B Li4,2
1School of Biomedical Engineering, University of British Columbia, Vancouver, BC, Canada.
Frontiers in neurology
|June 12, 2023
概括
在机器学习模型中考虑标签不确定性可以提高临床结果的预测准确性. 一个概率随机森林模型在处理缺失的结果数据时,在预测多发性硬化症转化方面表现出卓越的表现.
科学领域:
- 医疗信息学 医疗信息学
- 医疗保健中的机器学习
- 神经学 神经学
背景情况:
- 机器学习 (ML) 对使用健康数据预测个体患者的临床结果具有重大前景.
- 缺少的数据,特别是结果标签,在训练强大的ML算法方面是一个常见的挑战.
- 本研究涉及标签不确定性对临床试验环境中的ML模型性能的影响.
研究的目的:
- 在考虑标签不确定性时,比较三个ML模型的预测性能.
- 评估是否将不确定的结果纳入概率标签可以提高预测准确性.
- 评估ML模型在预测从临床隔离综合征转化为多发性硬化症 (MS) 的有效性.
主要方法:
- 使用了一项用于延迟MS转化中的米诺环素III期临床试验的数据集 (n=142).
- 使用MRI和临床数据训练了三个随机森林 (RF) 模型:RF排除 (删除不确定的标签),RF天真 (假设标签) 和概率RF (PRF) (概率标签).
- 用分层的7倍交叉验证来预测MS转化在2年内.
主要成果:
- 概率RF (PRF) 模型实现了0.76的最高曲线下面积 (AUC),超过了RF排除 (0.69) 和RF天真 (0.71).
- 与RF排除 (82.6%) 和RF天真 (76.8%) 相比,PRF还显示出更高的F1得分 (86.6%).
- 这些结果表明,建模标签不确定性显著提高了预测性能.
结论:
- 能够有效地模拟标签不确定性的机器学习算法可以提高预测性能.
- 这种方法对于数据集具有很大比例的未知结果的受试者特别有益.
- 在ML中使用概率方法可以在临床环境中带来更准确的预测,但数据有限.
更多相关视频
04:09Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma
Published on: October 10, 2018
8.3K
10:46A Method of Trigonometric Modelling of Seasonal Variation Demonstrated with Multiple Sclerosis Relapse Data
Published on: December 9, 2015
10.7K
相关概念视频
Improving Translational Accuracy
11.7K
Base complementarity between the three base pairs of mRNA codon and the tRNA anticodon is not a failsafe mechanism. Inaccuracies can range from a single mismatch to no correct base pairing at all. The free energy difference between the correct and nearly correct base pairs can be as small as 3 kcal/ mol. With complementarity being the only proofreading step, the estimated error frequency would be one wrong amino acid in every 100 amino acids incorporated. However, error frequencies observed in...
11.7K
Steps in Outbreak Investigation
155
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:
155
