Software and Hardware Configuration for Hypothyroidism Prediction Model

3,772 records with 30 features were used to develop FusionNet-CXG, a hybrid deep-learning model for hypothyroidism prediction. The dataset, shared by Divya Kesavulu on figshare, was last updated in April 2026. Experiments used SMOTE-NC to mitigate class imbalance and 10 repetitions of 5-fold cross-validation for evaluation.

Use Cases

• Training hybrid deep-learning models for disease prediction based on the 30 clinical features.
• Benchmarking CNN, LSTM, and GRU architectures on a medical classification task.
• Applying SHAP analysis for model interpretability based on feature influence.
• Studying the effects of SMOTE-NC for handling class imbalance in clinical data.

Strengths

• Model performance is reported with specific metrics: 0.9394 mean accuracy, F1=0.906, and AUC-ROC=0.94.
• Evaluation protocol involved 50 fold-level evaluations from repeated cross-validation for stable results.
• Dataset is openly shared under a CC-BY-4.0 license, facilitating reuse.

Limitations

• Row count is unknown, which may limit suitability assessment.
• Column-level documentation is absent; field semantics must be inferred after download.
• The dataset is very small at 5.5 KB, indicating limited scope.

Provenance

Source

A public dataset referenced in the research description.

Collection Method

Likely collected for clinical research, as described in the model development paper.

Time Range

null

Freshness

Last updated 2026-04-21 17:48:58; freshness should be verified.

Geography

null