From: Adapting transformer-based language models for heart disease detection and risk factors extraction
Risk Factor | Indicator | Precision | Recall | F1-score | Support |
---|---|---|---|---|---|
CAD | Mention | 0.93 | 0.92 | 0.92 | 301 |
 | Event | 0.69 | 0.78 | 0.73 | 241 |
 | Test | 0.00 | 0.00 | 0.00 | 63 |
 | Symptom | 0.94 | 0.49 | 0.64 | 94 |
Diabetes | Mention | 0.93 | 0.99 | 0.96 | 530 |
 | A1c | 0.91 | 0.81 | 0.86 | 75 |
 | Glucose | 0.00 | 0.00 | 0.00 | 40 |
Obese | Mention | 0.94 | 1.00 | 0.97 | 114 |
 | Obese_BMI | 0.00 | 0.00 | 0.00 | 7 |
Hypertension | Mention | 0.99 | 0.99 | 0.99 | 515 |
 | High bp | 0.97 | 0.98 | 0.97 | 205 |
Hyperlipidemia | Mention | 0.86 | 1.00 | 0.93 | 221 |
 | High chol. | 0.00 | 0.00 | 0.00 | 7 |
 | High LDL | 0.00 | 0.00 | 0.00 | 28 |
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_past | 0.85 | 0.59 | 0.69 | 121 |
 | Smoker_unknown | 0.93 | 0.90 | 0.91 | 202 |
Medication | Â | 0.87 | 0.76 | 0.81 | 7352 |
Family history | Â | 0.2000 | 0.0769 | 0.1111 | 13 |
Weighted average | Â | 0.9361 | 0.9397 | 0.9371 | 42946 |
Macro average | Â | 0.3988 | 0.3848 | 0.3772 | 42946 |
Micro average | Â | Â | Â | 0.9397 | 42946 |
Accuracy | Â | Â | Â | 0.9397 | 42946 |