Author(s)
Jiandong Zhou
Published 16 Projects
Infectious Diseases Heart Failure Cardiovascular Medicine Risk Stratification Frailty Score
Sharen Lee
Published 16 Projects
Infectious Diseases Heart Failure Cardiovascular Medicine Risk Stratification Frailty Score
Tong Liu
Published 16 Projects
Infectious Diseases Heart Failure Cardiovascular Medicine Risk Stratification Frailty Score
William KK Wu
Published 6 Projects
COVID-19 Infectious Diseases Key Words Cardiovascular Medicine Angiotensin Receptor Blockers
Zhidong Cao
Published 3 Projects
COVID-19 Infectious Diseases Key Words Angiotensin Receptor Blockers Mortality
Dajun Zeng
Published 3 Projects
COVID-19 Infectious Diseases Key Words Angiotensin Receptor Blockers Mortality
Ian CK Wong
Published 2 Projects
Infectious Diseases Key Words Cardiovascular Medicine All Cause Mortality Factorization Machine
Bernard Man Yung Cheung
Published 23 Projects
Infectious Diseases Heart Failure Cardiovascular Medicine Frailty Score COVID-19
Content
Background: The coronavirus disease 2019 (COVID-19) has become a pandemic, placing significant burdens on the healthcare systems. In this study, we tested the hypothesis that a machine learning approach incorporating hidden nonlinear interactions can improve prediction for Intensive care unit (ICU) admission. Methods: Consecutive patients admitted to public hospitals between 1st January and 24th May 2020 in Hong Kong with COVID-19 diagnosed by RT-PCR were included. The primary endpoint was ICU admission. Results: This study included 1043 patients (median age 35 (IQR: 32-37; 54% male). Nineteen patients were admitted to ICU (median hospital length of stay (LOS): 30 days, median ICU LOS: 16 days). ICU patients were more likely to be prescribed angiotensin converting enzyme inhibitors/angiotensin receptor blockers, anti-retroviral drugs lopinavir/ritonavir and remdesivir, ribavirin, steroids, interferon-beta and hydroxychloroquine. Significant predictors of ICU admission were older age, male sex, prior coronary artery disease, respiratory diseases, diabetes, hypertension and chronic kidney disease, and activated partial thromboplastin time, red cell count, white cell count, albumin and serum sodium. A tree-based machine learning model identified most informative characteristics and hidden interactions that can predict ICU admission. These were: low red cells with 1) male, 2) older age, 3) low albumin, 4) low sodium or 5) prolonged APTT. A five-fold cross validation confirms superior performance of this model over baseline models including XGBoost, LightGBM, random forests, and multivariate logistic regression. Conclusions: A machine learning model including baseline risk factors and their hidden interactions can accurately predict ICU admission in COVID-19.
More Projects
Loren Frank
13 views • 2 years ago
Global Immunotalks
390 views • 2 years ago
Laurel Yohe
2 views • 2 years ago
Global Immunotalks
130 views • 2 years ago
Jignesh H. Parmar
0 views • 1 year ago
Winston A. Haynes
0 views • 1 year ago
Noam Mazor
0 views • 1 year ago
Global Immunotalks
182 views • 2 years ago
Cem Yuksel
345 views • 2 years ago
Oscar Gonzalez-Recio
3 views • 2 years ago
Please pick a style:
Gary Tse. (2021, Nov 8).Identifying main and interaction effects of risk factors to predict intensive care admission in patients hospitalized with COVID-19: a retrospective cohort study in Hong Kong[Video]. Scitok. https://scitok.com/project/p/2fbd9af5
Zhou Jiandong. "Identifying main and interaction effects of risk factors to predict intensive care admission in patients hospitalized with COVID-19: a retrospective cohort study in Hong Kong" Scitok, uploaded by Tse Gary, 8 Nov, 2021, https://scitok.com/project/p2fbd9af5
Gary Tse. "Identifying main and interaction effects of risk factors to predict intensive care admission in patients hospitalized with COVID-19: a retrospective cohort study in Hong Kong" Scitok. (Nov 8, 2021). https://scitok.com/project/p/2fbd9af5
Gary Tse (Nov 8, 2021). Identifying main and interaction effects of risk factors to predict intensive care admission in patients hospitalized with COVID-19: a retrospective cohort study in Hong Kong Scitok. https://scitok.com/project/p/2fbd9af5
Gary Tse. Identifying main and interaction effects of risk factors to predict intensive care admission in patients hospitalized with COVID-19: a retrospective cohort study in Hong Kong[video]. 2021 Nov 8. https://scitok.com/project/p/2fbd9af5
@online{al2006link, title={ Identifying main and interaction effects of risk factors to predict intensive care admission in patients hospitalized with COVID-19: a retrospective cohort study in Hong Kong }, author={ Tse, Gary }, organization={Scitok}, month={ Nov }, day={ 8 }, year={ 2021 }, url = {https://scitok.com/project/p/2fbd9af5}, }