期刊
GIGASCIENCE
卷 10, 期 9, 页码 -出版社
OXFORD UNIV PRESS
DOI: 10.1093/gigascience/giab055
关键词
biomarker; machine learning; generalization; dataset shift
资金
- National Institutes of Health (NIH) [NIH-NIBIB P41 EB019936, NIH-NIMH R01 MH083320, NIH RF1 MH120021]
- National Institute Of Mental Health [R01MH096906]
- Canada First Research Excellence Fund
- Brain Canada Foundation
- Montreal Neurological Institute
- Agence Nationale de la Recherche [ANR-17-CE23-0018]
- Agence Nationale de la Recherche (ANR) [ANR-17-CE23-0018] Funding Source: Agence Nationale de la Recherche (ANR)
Machine learning extracts new biomarkers from cohorts with rich biomedical measurements, but dataset shifts can lead to difficulties in applying these biomarkers to new individuals. Detection and correction strategies are crucial for addressing this issue in biomedical research.
Machine learning brings the hope of finding new biomarkers extracted from cohorts with rich biomedical measurements. A good biomarker is one that gives reliable detection of the corresponding condition. However, biomarkers are often extracted from a cohort that differs from the target population. Such a mismatch, known as a dataset shift, can undermine the application of the biomarker to new individuals. Dataset shifts are frequent in biomedical research, e.g., because of recruitment biases. When a dataset shift occurs, standard machine-learning techniques do not suffice to extract and validate biomarkers. This article provides an overview of when and how dataset shifts break machine-learning-extracted biomarkers, as well as detection and correction strategies.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据