Table 8 Effects of baseline incidence, proportions diseased, risk ratios, and baseline symptom correlations on the maximal area under the receiver operating characteristic curve using at most 40 symptoms for disease diagnosis.
From: Diagnostic accuracy of symptoms for an underlying disease: a simulation study
Coefficients | (95% CIs) | p | |
|---|---|---|---|
Incidence not reaching 1 among those diseased | |||
(Intercept) | 0.58 | (0.569 to 0.591) | < 0.0001 |
Correlation between diseases | − 0.001 | (− 0.012 to 0.01) | 0.807 |
Proportions diseased | 0.006 | (− 0.006 to 0.018) | 0.322 |
Baseline incidence | − 0.763 | (− 0.781 to − 0.745) | < 0.0001 |
Risk ratio | − 0.013 | (− 0.014 to − 0.012) | < 0.0001 |
At-risk incidence | 0.775 | (0.762 to 0.788) | < 0.0001 |
Baseline symptom correlation | − 0.104 | (− 0.114 to − 0.094) | < 0.0001 |
Dependent variable mean = 0.7; SD = 0.29; median = 0.76; min = 0; max = 1 | |||
Adjusted R-square = 0.79 | |||
Incidence reaching 1 among those diseased | |||
(Intercept) | 1.125 | (1.116 to 1.134) | < 0.0001 |
Correlation between diseases | 0.004 | (− 0.004 to 0.012) | 0.303 |
Proportions diseased | − 0.007 | (− 0.015 to 0.001) | 0.088 |
Baseline incidence | − 0.256 | (− 0.268 to − 0.244) | < 0.0001 |
Risk ratio | − 0.003 | (− 0.004 to − 0.002) | < 0.0001 |
Baseline symptom correlation | − 0.177 | (− 0.184 to − 0.17) | < 0.0001 |
Dependent variable mean = 0.94; SD = 0.1; median = 0.99; min = 0.66; max = 1 | |||
Adjusted R-square = 0.71 | |||
