Research Article

Machine Learning Readmission Risk Modeling: A Pediatric Case Study

Table 5

Average standard deviation f-score (F) performance [%] of SVM, MLP1, MLP2, and NB for decreasing number of folders in the RCV process. no SMOTE = no oversampling correction of class imbalance is done.

nfolds SMOTE
SVMMLP2MLP1NB

109.85 0.637.54 0.1610.23 0.89.83 0.3
59.67 0.497.65 0.199.67 0.269.83 0.53
49.6 0.177.65 0.029.71 0.239.83 0.13
39.73 0.187.57 0.069.69 0.079.98 0.17

ā€‰no SMOTE
ā€‰SVMMLP2MLP1NB

101.86 0.009.70 1.45NA11.23 1.37
52.04 0.009.16 0.82NA11.20 1.14
41.95 0.409.62 0.75NA11.29 1.32
32.22 0.459.60 0.52NA11.08 1.23