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

Fig 1.

Workflow of the proposed FusionNet-CXG framework for hypothyroidism prediction.

The pipeline integrates preprocessing, class balancing, feature extraction, and a hybrid CNN–XLSTM–GRU classifier.

More »

Fig 1 Expand

Fig 2.

Distribution of thyroid-related hormones (TSH, TT4, T3, and FTI) in the dataset.

More »

Fig 2 Expand

Fig 3.

Gender distribution of patients in the dataset.

More »

Fig 3 Expand

Fig 4.

Comparison of class balancing techniques.

More »

Fig 4 Expand

Fig 5.

Relative contribution of key features.

More »

Fig 5 Expand

Table 1.

Optimal Hyperparameter Settings for the Proposed Model.

More »

Table 1 Expand

Table 2.

FusionNet-CXG layer architecture.

More »

Table 2 Expand

Table 3.

Proposed FusionNet-CXG model architecture and parameters.

More »

Table 3 Expand

Table 4.

Experimental Configuration and Pipeline Summary (Hypothyroid Binary Classification).

More »

Table 4 Expand

Table 5.

Software and hardware configuration.

More »

Table 5 Expand

Table 6.

Experimental pipeline and methods (FusionNet-CXG).

More »

Table 6 Expand

Fig 6.

Heatmap of pairwise feature correlations.

More »

Fig 6 Expand

Fig 7.

Autoencoder training and validation loss curves for different class balancing approaches: (a) Random Oversampling (b) Random Under sampling (c) ADASYN (d) Borderline-SMOTE (e) SMOTE-NC.

More »

Fig 7 Expand

Fig 8.

Correlation between original features and encoded features.

More »

Fig 8 Expand

Fig 9.

Illustrates the test Accuracy across hyperparameter tuning results of CNN-LSTM.

More »

Fig 9 Expand

Fig 10.

(a) Training and validation loss of CNN-LSTM classifier over epochs. (b) accuracy score between training and validating data over epochs of CNN-LSTM classifier.

More »

Fig 10 Expand

Fig 11.

Depicts the test Accuracy across Hyperparameter Configurations for CNN + BiLSTM.

More »

Fig 11 Expand

Fig 12.

(a) Training and validation loss of the CNN + BiLSTM classifier. Fig12 (b) training and validation accuracy over epochs of the CNN + BiLSTM classifier.

More »

Fig 12 Expand

Fig 13.

Test accuracy across different hyperparameter configurations for the FusionNet-CXG model.

More »

Fig 13 Expand

Fig 14.

(a) Training and validation loss of the FusionNet-CXG model. Fig 14 (b) validation and training accuracy of the FusionNet-CXG model.

More »

Fig 14 Expand

Fig 15.

Model accuracy among different genders (with 95% Wilson CI).

More »

Fig 15 Expand

Table 7.

Overall performance of FusionNet-CXG across 50 runs (mean ± SD; 95% CI).

More »

Table 7 Expand

Table 8.

Overall Performance of FusionNet-CXG (Mean ± SD; 95% CI).

More »

Table 8 Expand

Table 9.

Comparative Performance of CNN+LSTM, CNN + BiLSTM, and Proposed Model with Mean ± SD and 95% Confidence Intervals.

More »

Table 9 Expand

Table 10.

Statistical comparison based on 10 repetition-wise mean accuracies obtained from 10 × 5 repeated stratified cross-validation.

More »

Table 10 Expand

Table 11.

Verification of Assumptions for Paired t-Test.

More »

Table 11 Expand

Fig 16.

Mean performance comparison of the deep learning models on cross-validation test folds under 5-fold stratified cross-validation repeated 10 times.

More »

Fig 16 Expand

Fig 17.

SHAP-Based Explainability of the Proposed Hypothyroid Diagnostic Model.

More »

Fig 17 Expand

Table 12.

Performance comparison of the Proposed model with state-of-the-art models.

More »

Table 12 Expand