The page for
"Oculomics for sarcopenia prediction: a machine learning approach towards predictive, preventive, and personalized medicine"
The research manuscript was submitted to the EPMA Journal (the Forum for Predictive, Preventive, and Personalised Medicine).
Sex:
Male
Female
Age:
years old
Body Mass Indes (BMI):
kg/m^2
Region of residence:
Rural
Urban
Current smoker:
Yes
No
Alcohol consumption:
1 drink/week or more
less than 1 drink/week
Diabete mellitus (DM):
Yes
No
Hypertension (HTN):
Yes
No
Eye examinations
Blepharoptosis:
Yes
No
Decreased levator function:
Yes
No
Pterygium:
Yes
No
Cataract:
Yes
No
Glaucoma:
Yes
No
Age-related macular degeneration:
Yes
No
Diabetic retinopathy:
Yes
No
Results
Skeletal muscle index (SMI) prediction: (A low index means less muscle mass.)
Sarcopenia index (SI) prediction: (A low index means less muscle mass.)
Sarcopenia (SI-based) risk prediction score (%): (A high score means more sarcopenia risk.)
Sarcopenia risk estimated by a logistic regression (sigmoid prediction) model based on the KNHANES 2008-2011
powered by VISUWORKS Inc.
