Inferencing Strategies for Automated Alerts on Critically Abnormal Laboratory and Blood Gas Data

Abstract
A relatively insignificant amount of human thought is required to recognize critically abnormal events. After a few weeks of training on the ward, most medical students can recognize seriously abnormal results of common laboratory tests and take some definitive action, such as calling a supervising physician. The “gestalt” by which laboratory results are appreciated as clinically dangerous is complex and challenging to duplicate in a modern digital computer.

This publication has 1 reference indexed in Scilit: