Deterioration Phenotypes Through Clustering Analysis of Provider Actions

Poster Number: P31
Presentation Time: 05:00 PM - 06:30 PM

Abstract Keywords: Clinical Decision Support, Machine Learning, Evaluation, Critical Care, Usability
Primary Track: Applications
Programmatic Theme: Clinical Informatics

This study examines patient deterioration phenotypes by analyzing healthcare provider actions in relation to high Deterioration Index (DTI) scores and then using martingale residuals to perform hierarchical clustering to identify seven distinct deterioration phenotypes. The results demonstrate the potential for more accurate identification of true deterioration, which suggests that recognizing these phenotypes could improve patient outcomes through tailored interventions.

Speaker(s):
Abhinab Kc, B.A.
University of Minnesota Medical School Twin Cities

Author(s):
Abhinab Kc, B.A. - University of Minnesota Medical School Twin Cities; Benjamin Langworthy, PhD - University of Minnesota School of Public Health; Thomas Byrd, MD, MS - University of Minnesota - MHealth Fairview;