Variation in monitoring: Glucose measurement in the ICU as a case study to preempt spurious correlations.
Khushboo TeotiaYueran JiaNaira Link WoiteLeo Anthony CeliJoão MatosTristan StrujaPublished in: medRxiv : the preprint server for health sciences (2023)
We found disparities in ICU glucose measurements among patients with sepsis, albeit the magnitude was small. Variation in disease monitoring is a source of data bias that may lead to spurious correlations when modeling health data.
Keyphrases
- intensive care unit
- electronic health record
- big data
- mechanical ventilation
- public health
- healthcare
- blood glucose
- mental health
- acute kidney injury
- health information
- machine learning
- metabolic syndrome
- risk assessment
- adipose tissue
- climate change
- artificial intelligence
- affordable care act
- extracorporeal membrane oxygenation