Abstract
Bladder cancer is associated with a recurrence rate of 30 to 90% depending on a variety of prognostic factors. A large portion of a urologist's workload is devoted to diagnosing and treating bladder cancer recurrence. The purpose of this study is to retrospectively evaluate the ability of an artificial neural network (ANN) to predict bladder cancer recurrence from clinical and pathological information based on the initial primary tumour. Data relating to various prognostic markers was collected from an initial cohort of 432 patients. Of the 200 patients within the test set, 72% were classified correctly, with a sensitivity and specificity of 76% and 55%, respectively in relation to the prediction of future tumour recurrence.
| Original language | English |
|---|---|
| Pages (from-to) | 1007-1009 |
| Number of pages | 3 |
| Journal | Annual International Conference of the IEEE Engineering in Medicine and Biology - Proceedings |
| Volume | 3 |
| State | Published - 1997 |
| Externally published | Yes |
| Event | Proceedings of the 1997 19th Annual International Conference of the IEEE Engineering in Medicine and Biology Society - Chicago, IL, USA Duration: Oct 30 1997 → Nov 2 1997 |