Table 3 Performance metrics for each disease category – Boosting model/RNN
From: Artificial intelligence to differentiate asthma from COPD in medico-administrative databases
Recall (= sensibility) (%) | Specificity (%) | Precision (= positive predictive value) (%) | Negative predictive value (%) | F1 score (%) | |
|---|---|---|---|---|---|
Boosting model | |||||
Asthma | 83 | 63 | 71 | 77 | 76 |
COPD | 65 | 90 | 61 | 90 | 63 |
Other | 54 | 76 | 66 | 65 | 60 |
RNN model | |||||
Asthma | 83 | 62 | 71 | 77 | 76 |
COPD | 65 | 91 | 66 | 92 | 65 |
Other | 64 | 84 | 53 | 77 | 58 |