Performance metrics (compared with DXA-based measurement) for different prediction algorithms using all predictors in test data, based on 25 datasets where the DXA-based outcomes were randomly permuted (to provide a null or baseline scenario to compare against performance on the real data).

<p>Performance metrics (compared with DXA-based measurement) for different prediction algorithms using all predictors in test data, based on 25 datasets where the DXA-based outcomes were randomly permuted (to provide a null or baseline scenario to compare against performance on the real data)....

Full description

Saved in:

Bibliographic Details
Main Author:	Nick Birk (15444728) (author)
Other Authors:	Bharati Kulkarni (111619) (author), Santhi Bhogadi (5915165) (author), Aastha Aggarwal (533042) (author), Gagandeep Kaur Walia (8374872) (author), Vipin Gupta (102192) (author), Usha Rani (18301879) (author), Hemant Mahajan (16378728) (author), Sanjay Kinra (102266) (author), Poppy A. C. Mallinson (21587244) (author)
Published:	2025
Subjects:	Physiology Pharmacology Ecology Developmental Biology Statistics Science Policy Plant Biology Cardiology Environmental Sciences not elsewhere classified Biological Sciences not elsewhere classified simple anthropometric measures scale epidemiological studies mean absolute error 995 &# 8201 976 &# 8201 935 &# 8201 808 &# 8201 105 &# 8201 054 &# 8201 tanita &# 8217 measured body composition body composition parameters combined bia measurements bia measures may predict six dxa kg ), separately body composition based females using durnin body composition body circumferences tanita bc females using based equations bia devices south asians skinfold thickness ray absorptiometry made available machine learning grip strength generalize well findings demonstrate estimation algorithm energy x cost measurement commonly used approach could 289 females 1133 females
Tags:	Add Tag No Tags, Be the first to tag this record!

Performance metrics (compared with DXA-based measurement) for different prediction algorithms using all predictors in test data, based on 25 datasets where the DXA-based outcomes were randomly permuted (to provide a null or baseline scenario to compare against performance on the real data).

Similar Items