An assessment of the value of deep neural networks in genetic risk prediction for surgically relevant outcomes.

Mathias Aagaard ChristensenArnór SigurdssonAlexander BondeSimon RasmussenSisse Rye OstrowskiMads NielsenMartin Sillesen

Published in: PloS one (2024)

In this report we presented linear and deep learning predictive models for surgery relevant outcomes. Overall, predictability was similar between linear and deep learning models and inclusion of genetics seemed to improve accuracy.

Keyphrases

deep learning
neural network
minimally invasive
convolutional neural network
artificial intelligence
machine learning
coronary artery bypass
genome wide
gene expression
metabolic syndrome
type diabetes
copy number
atrial fibrillation
weight loss