Table 2.
Spherical feature annotation and increase in topic share (n=52,222)a.
| Clinical topic NLPb | Records tagged initially, n (%) | Records tagged NLP-augmented, n (%) | Increase in tagged patient records, n (%)c |
| COVID-19 | 375 (0.72) | 405 (0.78) | 30 (8) |
| General symptom | 6401 (12.26) | 6867 (13.15) | 466 (7.28) |
| General administration | 315 (0.6) | 1217 (2.33) | 902 (286.35) |
| Systemic clinical | 3219 (6.16) | 3519 (6.74) | 300 (9.32) |
| Gastrointestinal | 3421 (6.55) | 4159 (7.96) | 738 (21.57) |
| Respiratory | 4040 (6.55) | 4159 (7.96) | 738 (21.57) |
| Cardiovascular | 2683 (5.14) | 5219 (9.99) | 2536 (94.52) |
| Neurological | 414 (7.93) | 4485 (8.59) | 345 (8.33) |
| Eye; ear, nose, and throat; and derma | 1818 (3.48) | 2061 (3.95) | 243 (13.37) |
| Gynecology and urology | 2712 (5.19) | 3004 (5.75) | 292 (10.77) |
| Trauma | 16,516 (31.63) | 17,389 (33.3) | 873 (5.29) |
| General psychiatric | 1989 (3.81) | 2627 (5.03) | 638 (32.08) |
| No tag | 14,141 (27.08) | 10,569 (20.24) | –3572 (–25.26) |
aThis table presents the distribution of the diagnosis topics obtained with the NLP-based text annotation before and after the spherical feature annotation.
bNLP: natural language processing.
cPercent of initially recorded tags.