Table 3.
Feature description for each clinical dataset, where numerical covariates are indicated with “*” and categorical covariates are converted into binary covariates through dummy coding.
Dataset 7 | Dataset 8 | Dataset 9 | Dataset 10 | Dataset 11 | |
---|---|---|---|---|---|
x1 | CA19* | Birth number* | Age* | Symptoms
|
Pain in right arm |
x2 | CA125* | Smoking status | Beck Depression Score* | Nausea | |
x3 | - | Race
|
Drug use history
|
Hypo perfusion | |
x4 | - | Perceived benefit* | ST elevation | ||
x5 | - | Age of mother* | Prior drug treatments* | Family history | New Q waves |
x6 | - | Weight at last menstrual period* | Race | Self examination | ST depression |
x7 | - | - | Treatment assignment | Detection probability
|
T wave inversion |
x8 | - | - | Treatment site | Sweating | |
x9 | - | - | - | - | Pain in left arm |
y | Presence of cancer | Low birth weight | Remained drug free | Mammograph experience | Presence of disease |