From: Adapting transformer-based language models for heart disease detection and risk factors extraction
Risk Factor | Indicator | Precision | Recall | F1-score | Support |
---|---|---|---|---|---|
CAD | Mention | 0.86 | 0.92 | 0.88 | 259 |
 | Event | 0.80 | 0.81 | 0.80 | 258 |
 | Test | 0.93 | 0.42 | 0.57 | 65 |
 | Symptom | 0.85 | 0.80 | 0.82 | 99 |
Diabetes | Mention | 0.99 | 0.99 | 0.99 | 601 |
 | A1c | 0.75 | 0.92 | 0.83 | 66 |
 | Glucose | 1.00 | 0.38 | 0.55 | 40 |
Hypertension | Mention | 1.00 | 0.99 | 1.00 | 602 |
 | High bp | 0.99 | 1.00 | 0.99 | 206 |
OBESE | Mention | 0.96 | 1.00 | 0.98 | 117 |
 | Obese_BMI | 0.00 | 0.00 | 0.00 | 5 |
Hyperlipidemia | Mention | 0.97 | 0.99 | 0.98 | 286 |
 | High chol. | 0.00 | 0.00 | 0.00 | 10 |
 | High LDL | 0.79 | 0.79 | 0.79 | 29 |
Smoker | Smoker_never | 0.94 | 0.95 | 0.94 | 114 |
 | Smoker_ever | 0.00 | 0.00 | 0.00 | 3 |
 | Smoker_current | 0.00 | 0.00 | 0.00 | 40 |
 | Smoker_past | 0.88 | 0.77 | 0.82 | 122 |
 | Smoker_unknown | 0.99 | 0.99 | 0.99 | 202 |
Medication | Â | 0.88 | 0.74 | 0.80 | 7253 |
Family history | Â | 0.0000 | 0.0000 | 0.0000 | 13 |
Weighted average | Â | 0.9338 | 0.9403 | 0.9357 | 42946 |
Macro average | Â | 0.3715 | 0.3614 | 0.3505 | 42946 |
Micro average | Â | Â | Â | 0.9403 | 42946 |
Accuracy | Â | Â | Â | 0.9403 | 42946 |