Identification of high-risk COVID-19 patients using machine learning
Fig 1
Normalized distributions for different central moments: (a) mean, (b) variance, (c) skewness, and (d) kurtosis, for class 1 (recovered patients), shown in blue and for class 2 (deceased patients), shown in red.
These central moments were computed from the 21 elements of the characteristics vector for each patient. These distributions were plotted using the entire dataset with 4, 700, 464 observations.