From: Adapting transformer-based language models for heart disease detection and risk factors extraction
Risk factor | Indicator | Precision | Recall | F1-score | Support |
---|---|---|---|---|---|
CAD | Mention | 0.82 | 0.79 | 0.81 | 228 |
 | Event | 0.72 | 0.70 | 0.71 | 278 |
 | Test | 0.00 | 0.00 | 0.00 | 70 |
 | Symptom | 0.90 | 0.39 | 0.54 | 95 |
Diabetes | Mention | 0.92 | 0.99 | 0.95 | 549 |
 | A1c | 0.89 | 0.79 | 0.84 | 71 |
 | Glucose | 0.00 | 0.00 | 0.00 | 40 |
Hypertension | Mention | 0.99 | 0.97 | 0.98 | 525 |
 | High bp | 0.93 | 0.99 | 0.96 | 210 |
OBESE | Mention | 0.95 | 1.00 | 0.97 | 115 |
 | Obese_BMI | 0.00 | 0.00 | 0.00 | 6 |
Hyperlipidemia | Mention | 0.87 | 0.99 | 0.93 | 232 |
 | High chol. | 0.00 | 0.00 | 0.00 | 7 |
 | High LDL | 0.50 | 0.10 | 0.17 | 30 |
Smoker | Smoker_never | 0.80 | 0.72 | 0.76 | 114 |
 | Smoker_ever | 0.00 | 0.00 | 0.00 | 3 |
 | Smoker_current | 0.00 | 0.00 | 0.00 | 37 |
 | Smoker_unknown | 0.93 | 0.90 | 0.91 | 202 |
 | Smoker_past | 0.85 | 0.59 | 0.69 | 121 |
Medication | Â | 0.87 | 0.74 | 0.80 | 7329 |
Family history | Â | 0.2000 | 0.0769 | 0.1111 | 13 |
Weighted average | Â | 0.9390 | 0.9427 | 0.9394 | 42946 |
Macro average | Â | 0.4195 | 0.4037 | 0.3915 | 42946 |
Micro average | Â | Â | Â | 0.9427 | 42946 |
Accuracy | Â | Â | Â | 0.9427 | 42946 |