共 50 条
Ten quick tips for ensuring machine learning model validity
被引:0
|作者:
Goh, Wilson Wen Bin
[1
,2
,3
,4
,5
]
Kabir, Mohammad Neamul
[1
,3
]
Yoo, Sehwan
[1
,3
]
Wong, Limsoon
[6
,7
]
机构:
[1] Nanyang Technol Univ, Lee Kong Chian Sch Med, Singapore, Singapore
[2] Nanyang Technol Univ, Sch Biol Sci, Singapore, Singapore
[3] Nanyang Technol Univ, Ctr Biomed Informat, Singapore, Singapore
[4] Nanyang Technol Univ, Ctr AI Med, Singapore, Singapore
[5] Imperial Coll London, Fac Med, Dept Brain Sci, Div Neurol, London, England
[6] Natl Univ Singapore, Sch Comp, Singapore, Singapore
[7] Natl Univ Singapore, Yong Loo Lin Sch Med, Singapore, Singapore
基金:
新加坡国家研究基金会;
关键词:
SEQUENCE;
D O I:
10.1371/journal.pcbi.1012402
中图分类号:
Q5 [生物化学];
学科分类号:
071010 ;
081704 ;
摘要:
Artificial Intelligence (AI) and Machine Learning (ML) models are increasingly deployed on biomedical and health data to shed insights on biological mechanism, predict disease outcomes, and support clinical decision-making. However, ensuring model validity is challenging. The 10 quick tips described here discuss useful practices on how to check AI/ML models from 2 perspectives-the user and the developer.
引用
收藏
页数:12
相关论文