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 literature on disease prediction models.

More »

Table 1 Expand

Fig 1.

Multi-model disease prediction framework.

More »

Fig 1 Expand

Fig 2.

Abstract representation of the model families considered in this study.

More »

Fig 2 Expand

Table 2.

Model configuration for heart disease dataset.

More »

Table 2 Expand

Table 3.

Model configuration for diabetes disease dataset.

More »

Table 3 Expand

Table 4.

Model configuration for Parkinson’s disease dataset.

More »

Table 4 Expand

Table 5.

(a) Standalone model training configuration (MLP, CNN, FT-transformer). (b) Ensemble model training configuration (MLP + AE, CNN + AE, FT + AE).

More »

Table 5 Expand

Table 6.

Standalone model search spaces.

More »

Table 6 Expand

Table 7.

Ensemble model hyperparameter grid.

More »

Table 7 Expand

Table 8.

Autoencoder architecture configuration.

More »

Table 8 Expand

Table 9.

Cross-validation configuration per dataset.

More »

Table 9 Expand

Table 10.

Summary of proposed instantiations.

More »

Table 10 Expand

Table 11.

Baseline model configurations.

More »

Table 11 Expand

Table 12.

The different evaluation metrics.

More »

Table 12 Expand

Table 13.

Heart disease classification performance.

More »

Table 13 Expand

Fig 3.

All models comparison.

More »

Fig 3 Expand

Table 14.

Diabetes classification performance.

More »

Table 14 Expand

Fig 4.

The shows grouped performance metrics for diabetes classification.

More »

Fig 4 Expand

Table 15.

Parkinson’s disease classification performance.

More »

Table 15 Expand

Fig 5.

The presents grouped performance metrics for Parkinson’s disease classification.

More »

Fig 5 Expand

Table 16.

Classical ML baseline performance.

More »

Table 16 Expand

Table 17.

DL vs. classical ML – Best model comparison.

More »

Table 17 Expand

Fig 6.

Confusion matrix for FT + AE on heart disease.

More »

Fig 6 Expand

Fig 7.

Confusion matrix for CNN + AE on diabetes.

More »

Fig 7 Expand

Fig 8.

Confusion matrix for MLP on Parkinsons disease.

More »

Fig 8 Expand

Fig 9.

ROC curve for CNN on heart disease.

More »

Fig 9 Expand

Fig 10.

ROC curve for CNN on diabetes.

More »

Fig 10 Expand

Fig 11.

ROC curve for MLP on Parkinson’s disease.

More »

Fig 11 Expand

Fig 12.

Precision-recall curve for CNN on heart disease.

More »

Fig 12 Expand

Fig 13.

Precision-recall curve for CNN on diabetes.

More »

Fig 13 Expand

Fig 14.

Precision-recall curve for MLP on Parkinson’s disease.

More »

Fig 14 Expand

Table 18.

The accuracy comparison with literature benchmarks.

More »

Table 18 Expand

Fig 15.

The compares reported accuracy of the proposed models with benchmark results from prior studies.

More »

Fig 15 Expand

Table 19.

Selected Wilcoxon signed-rank test results (AUC).

More »

Table 19 Expand

Table 20.

Model efficiency comparison.

More »

Table 20 Expand

Table 21.

Parameter scaling across datasets.

More »

Table 21 Expand

Fig 16.

SHAP summary plot for FT on heart disease (best fold).

More »

Fig 16 Expand

Fig 17.

FT-Transformer CLS attention to features: Heart disease.

More »

Fig 17 Expand

Fig 18.

Feature cross-attention heat map: Heart disease.

More »

Fig 18 Expand

Fig 19.

Mean grad-CAM activation map for CNN on diabetes.

More »

Fig 19 Expand

Fig 20.

Decision curve analysis for FT + AE on heart disease.

More »

Fig 20 Expand

Fig 21.

Decision curve analysis for CNN on diabetes.

More »

Fig 21 Expand

Fig 22.

Decision curve analysis for MLP on Parkinson’s disease.

More »

Fig 22 Expand

Table 22.

PPV/NPV across prevalence rates (Best standalone model per dataset by AUC, best fold).

More »

Table 22 Expand

Table 23.

Ablation study: Incremental impact on mean AUC.

More »

Table 23 Expand

Table 24.

Error distribution summary (Best model per dataset by AUC, best fold).

More »

Table 24 Expand

More »

Expand