T stage, recurrence and metastatic disease identified in the NIHR HIC colorectal cancer research database through NLP of imaging, endoscopy and/or histopathology reports for all patients who had surgical excision at one of the pilot sites
| Characteristic | Radical resection or local excision |
| Number of participants | 2124 (100%) |
| Maximum T stage | |
| 0 | 31 (1.5%) |
| is (in situ) | 0 (0%) |
| 1 | 195 (9.2%) |
| 2 | 369 (17.4%) |
| 3 | 954 (44.9%) |
| 4 | 460 (21.7%) |
| X | 2 (0.1%) |
| Not known | 113 (5.3%) |
| Recurrence or metastasis | |
| Recurrence or metastasis detected | 769 (36.2%) |
| Metastasis present around time of diagnosis | 286 (13.5%) |
| Not detected | 1355 (63.8%) |
HIC, Health Informatics Collaborative; NIHR, National Institute for Health Research; NLP, natural language processing.