Meta-Analysis
Copyright ©The Author(s) 2024.
World J Crit Care Med. Dec 9, 2024; 13(4): 99564
Published online Dec 9, 2024. doi: 10.5492/wjccm.v13.i4.99564
Table 1 Multivariate regression analysis for continuous and categorical variables
Covariate
Coefficients
Lower bound
Upper bound
Std. error
P value
Omnibus, P value
Model 1 for continuous variables
Intercept2.7740.9584.5910.9270.0030.034
Mean age-0.036-0.066-0.0060.0150.018
Female proportion0.000-0.0000.001< 0.0010.075
Hypertension proportion-0.003-0.0130.0070.0050.534
Follow-up period in years-0.028-0.0710.0150.0220.205
Model 2 for subgroup variables (categorical)
Intercept0.429-0.8201.6770.6370.5010.002
United States vs non-United States0.088-0.1880.3640.1410.534
Sample size < 200 vs sample size ≥ 2000.407-0.0970.9110.2570.113
Follow up < 5 years vs ≥ 5 years-0.541-1.2510.1690.3620.135
Mean age < 60 years vs ≥ 60 years-0.301-0.6370.0360.1720.080
Study quality score based on NIH risk of bias0.250-0.1010.6010.1790.162
Table 2 Subgroup analysis of studies based on country, sample size, follow-up period, mean age, or study quality
Group
Included studies
Odds ratio (95%CI)
P value
P-within subgroups heterogeneity
I2%
P-meta-regression
Overall risk of mortality141.40 (1.15-1.70)< 0.0010.00260NA
Subgroup analysis
Country United States vs non-United States
United States61.17 [0.89-1.53]0.260.2722< 0.001
Non-United States81.55 [1.25-1.92]< 0.0010.1436
Sample size < 200 vs ≥ 200
Sample size < 20071.22 [0.71-2.12]0.470.06500.340
Sample size ≥ 20071.46 [1.19-1.80]< 0.0010.00370
Follow up < 5 years vs ≥ 5 years
Follow up < 5 years51.52 [0.78-2.98]0.220.06560.640
Follow up ≥ 5 years91.37 [1.13-1.67]0.0010.00663
Overall mean age < 60 years vs ≥ 60 years
Mean age < 60 years71.61 [1.27-2.05]< 0.0010.4030.138
Mean age ≥ 60 years71.26 [0.99-1.61]0.060.00468
Study quality score based on NIH risk of bias
High32.52 [1.47-4.32]0.00080.9000.807
Moderate101.23 [1.05-1.43]0.0100.2026
Unclear11.78 [1.40-2.25]Not applicableNot applicableNot applicable