Feature importance in predicting subsequent occurrence of IHCA.

figure

posted on 2020-07-13, 17:29 authored by Ryo Ueno, Liyuan Xu, Wataru Uegami, Hiroki Matsui, Jun Okui, Hiroshi Hayashi, Toru Miyajima, Yoshiro Hayashi, David Pilcher, Daryl Jones

Importance of each predictor in the 2 different random forest models: Vitals-Only model and Vitals+Labs model. 20 most important variables were summarized. Abbreviations: APTT, activated partial thromboplastin time; BUN, blood urea nitrogen; CRP, C-reactive protein; LD, lactate dehydrogenase; PT, prothrombin time.

History

Usage metrics

Keywords

models use patient demographics care unit patients Vitals-Only model machine learning-based prediction m...laboratory results Random forest models AUC 24 hours CI single-center retrospective cohort ...IHCA training data ward patient data

Licence

CC BY 4.0

Feature importance in predicting subsequent occurrence of IHCA.

History

Usage metrics

Categories

Keywords

Licence

Exports