Skip to main content
Advertisement
Browse Subject Areas
?

Click through the PLOS taxonomy to find articles in your field.

For more information about PLOS Subject Areas, click here.

< Back to Article

Table 1.

Summary of current literature works for preterm birth prediction using AI.

More »

Table 1 Expand

Fig 1.

Preprocessing steps performed to build the final dataset.

More »

Fig 1 Expand

Table 2.

Age group distribution according to the literature.

More »

Table 2 Expand

Table 3.

Selected attributes.

More »

Table 3 Expand

Table 4.

Attributes removed after preprocessing.

More »

Table 4 Expand

Fig 2.

Sampling scenarios used in our experiments.

More »

Fig 2 Expand

Table 5.

Grid search hyperparameters.

More »

Table 5 Expand

Fig 3.

Overview for handling imbalanced data and training machine learning models.

More »

Fig 3 Expand

Table 6.

Best hyperparameters when using undersampling.

More »

Table 6 Expand

Fig 4.

Models’ performance when using Undersampling to balance the training dataset.

More »

Fig 4 Expand

Table 7.

Best hyperparameters when using oversampling.

More »

Table 7 Expand

Fig 5.

Models’ performance when using oversampling to balance the training dataset.

More »

Fig 5 Expand

Table 8.

Best hyperparameters when using Hybridsampling double size.

More »

Table 8 Expand

Fig 6.

Models’ performance when using Hybridsampling double size to balance the training dataset.

More »

Fig 6 Expand

Table 9.

Best hyperparameters when using Hybridsampling triple size.

More »

Table 9 Expand

Fig 7.

Hybridsampling triple size models performance.

More »

Fig 7 Expand

Table 10.

Best hyperparameters when using Hybridsampling quadruple size.

More »

Table 10 Expand

Fig 8.

Models’ performance when using Hybridsampling quadruple size to balance the training dataset.

More »

Fig 8 Expand