Search Articles

View query in Help articles search

Search Results (1 to 10 of 27 Results)

Download search results: CSV END BibTex RIS


Predicting Abnormal Laboratory Blood Test Results in the Intensive Care Unit Using Novel Features Based on Information Theory and Historical Conditional Probability: Observational Study

Predicting Abnormal Laboratory Blood Test Results in the Intensive Care Unit Using Novel Features Based on Information Theory and Historical Conditional Probability: Observational Study

A study by Lee and Maslove [16] used entropy, conditional entropy, and mutual information to measure redundancy in 11 blood tests performed during the first 3 days in the ICU. They found a decreasing trend in the novelty of information throughout the ICU stay, showing that performing additional laboratory tests does not necessarily result in the gain of information.

Camilo E Valderrama, Daniel J Niven, Henry T Stelfox, Joon Lee

JMIR Med Inform 2022;10(6):e35250