Table 14 Ensembles
From: Adapting transformer-based language models for heart disease detection and risk factors extraction
All Ensembles (BERT+BioBERT+BioClinicalBERT+RoBERTa+XLNet) | Precision | Recall | F1-score | Support |
|---|---|---|---|---|
Macro average | 0.3218 | 0.3330 | 0.3129 | 42946 |
Weighted average | 0.9337 | 0.9426 | 0.9366 | 42946 |
Accuracy | Â | Â | 0.9426 | 42946 |