Skip to main content

Table 3 Comparison of ANN model with decision tree model of the hospital charge on gastric cancer patients

From: Comparison of hospital charge prediction models for gastric cancer patients: neural network vs. decision tree models

Indexes

ANN

Decision tree

 

Training dataset

test dataset

Training dataset

test dataset

Minimum error

-10878.152

-6048.823

-12680.355

-11754.598

Maximum error

15072.62

5971.064

36086.455

50410.532

Mean error

81.358

-2.027

0.0

0.0

Mean absolute error

1819.197

1162.279

2782.423

3424.608

Standard deviation

2765.489

1646.117

4689.292

6102.192

Linear correlation coefficient

0.955

0.987

0.866

0.806

Accuracy

97.418%

98.35%

----

----