Table 4 MERP category prediction correlations using XGBoost.
From: A text mining approach to categorize patient safety event reports by medication error type
Predicted wrong drug | Predicted wrong time | Predicted wrong strength | Predicted wrong dosage form | Predicted improper dose | Predicted wrong rate | Predicted wrong patient | Predicted monitoring error | |
|---|---|---|---|---|---|---|---|---|
True wrong drug | 558 | 371 | 191 | 85 | 112 | 43 | 8 | 11 |
True wrong time | 353 | 374 | 145 | 85 | 191 | 45 | 5 | 9 |
True wrong strength | 200 | 157 | 293 | 159 | 94 | 36 | 1 | 7 |
True wrong dosage form | 162 | 113 | 176 | 276 | 79 | 12 | 0 | 8 |
True improper dose | 237 | 207 | 79 | 63 | 271 | 19 | 9 | 7 |
True wrong rate | 54 | 54 | 34 | 9 | 20 | 66 | 0 | 1 |
True wrong patient | 18 | 26 | 2 | 3 | 15 | 0 | 17 | 0 |
True monitoring error | 24 | 17 | 10 | 8 | 13 | 1 | 0 | 16 |
