CLASSIF1 Data Pattern Classification


Patient Prognosis after Melanoma Surgery

Classification of Learning Set




< fig.5      fig.6: Unknown Test Patients

- Displayed are the first 10 survivor and non survivor patients of the test set which had remained unkown to the learning process.

- For this, the test set database records were labeled with: ? at the location for the classification truth to make them invisible to the learning process. This becomes evident from the learning set of fig.2 where the test set patient record numbers are missing.

- The unknown melanoma patients of the test classify similarly as those of the learning set (fig.1, fig.2) indicating robustness of the CLASSIF1 classifier for the prospective classification of unknown patients.



© 2026 G.Valet
1965-2006: Max-Planck-Institut für Biochemie, Am Klopferspitz 18a, D-82152 Martinsried, Germany
Last update: Apr 10,2004
First display: Mar 21,2002