Retrospective analysis of COVID-19 clinical and laboratory data: Constructing a multivariable model across different comorbidities

Retrospective analysis of COVID-19 clinical and laboratory data: Constructing a multivariable model across different comorbidities

The clinical pathogenesis of COVID-19 necessitates a comprehensive and homogeneous study to understand the disease mechanisms. Identifying clinical symptoms and laboratory parameters as key predictors can guide prognosis and inform effective treatment strategies. This study analyzed comorbidities an...

Full description

Saved in:
Bibliographic Details
Published in:Journal of infection and public health Vol. 17; no. 12; p. 102566
Main Authors: Shokrollahi Barough, Mahdieh, Darzi, Mohammad, Yunesian, Masoud, Amini Panah, Danesh, Ghane, Yekta, Mottahedan, Sam, Sakinehpour, Sohrab, Kowsarirad, Tahereh, Hosseini-Farjam, Zahra, Amirzargar, Mohammad Reza, Dehghani, Samaneh, Shahriyary, Fahimeh, Kabiri, Mohammad Mahdi, Nojomi, Marzieh, Saraygord-Afshari, Neda, Mostofi, Seyedeh Ghazal, Yassin, Zeynab, Mojtabavi, Nazanin
Format: Journal Article
Language:English
Published: England Elsevier Ltd 01-12-2024
Subjects:
Comorbidity
COVID-19
Feature selection
Laboratory data
Machine learning
CRP
BB
MCV
P-LCR
Feature selection
BE
PT
ALP
ESR1h
Laboratory data
K
INR
SGPT ALT
Cr
COVID-19
PTT
LDH
BS
RBC
MPV
Na
FBS
WBC
O2-Sat
Hb
BUN
HCO3
SGOT AST
PDW
RDW
pCO2
Comorbidity
BEecf
CKP
D-Dimer
IL-6
pO2
MCHC
Machine learning
HCT
HbA1C
Ca
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:The clinical pathogenesis of COVID-19 necessitates a comprehensive and homogeneous study to understand the disease mechanisms. Identifying clinical symptoms and laboratory parameters as key predictors can guide prognosis and inform effective treatment strategies. This study analyzed comorbidities and laboratory metrics to predict COVID-19 mortality using a homogeneous model. A retrospective cohort study was conducted on 7500 COVID-19 patients admitted to Rasoul Akram Hospital between 2022 and 2022. Clinical and laboratory data, along with comorbidity information, were collected and analyzed using advanced coding, data alignment, and regression analyses. Machine learning algorithms were employed to identify relevant features and calculate predictive probability scores. The frequency and mortality rates of COVID-19 among males (19.3 %) were higher than those among females (17 %) (p = 0.01, OR = 0.85, 95 % CI = 0.76–0.96). Cancer (p < 0.05, OR = 1.9, 95 % CI = 1.48–2.4) and Alzheimer's (p < 0.05, OR = 2.36, 95 % CI = 1.89–2.9) were the two most common comorbidities associated with long-term hospitalization (LTH). Kidney disease (KD) was identified as the most lethal comorbidity (45 % of KD patients) (OR = 5.6, 95 % CI = 5.05–6.04, p < 0.001). Age > 55 was the most predictive parameter for mortality (p < 0.001, OR = 6.5, 95 % CI = 1.03–1.04), and the CT scan score showed no predictive value for death (p > 0.05). WBC, Cr, CRP, ALP, and VBG-HCO3 were the most significant critical data associated with death prediction across all comorbidities (p < 0.05). COVID-19 is particularly lethal for elderly adults; thus, age plays a crucial role in disease prognosis. Regarding death prediction, various comorbidities rank differently, with KD having a significant impact on mortality outcomes.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
ISSN:1876-0341
1876-035X
1876-035X
DOI:10.1016/j.jiph.2024.102566