Use of Noisy Labels as Weak Learners to Identify Incompletely Ascertainable Outcomes: A Feasibility Study with Opioid-Induced Respiratory Depression.

Alvin D JefferyDaniel FabbriRuth M ReevesMichael E Matheny

Published in: medRxiv : the preprint server for health sciences (2024)

Application of a data programming paradigm with expert-informed labeling functions might have utility for phenotyping clinical phenomena that are not easily ascertainable from highly-structured data.

Keyphrases

electronic health record
big data
chronic pain
depressive symptoms
high glucose
pain management
machine learning
adipose tissue
drug induced
physical activity
type diabetes
skeletal muscle
deep learning
insulin resistance
weight loss