CLASSIF1 Data Pattern Classificaition
- The print output of the CLASSIF1 learning procedure LRNLYMPH comprises the confusion matrix for the classification of the learning set and the unknown test set patients, (fig.1), the reclassification of the learning set (fig.2), the disease classification masks (fig.3), the parameter list of the database (fig.4), the means, SEMs and percentiles of the discriminatory parameters of the disease classification masks (fig.5) and the prospective classification of unknown test set patients (fig.6).
- The normal and overtrained cyclists are well recognised mainly from the CD45RO and CD3 antigen expression of blood lymphocytes (fig.3).
- The reclassification list of the learning set (fig.2) shows that the sample classification masks do not exhibit systematic data pattern differences with the increasing number of patients i.e. the immunophenotype measurements were of stable quality over the collection period of the samples which was about one year.
- The reclassification list shows furthermore that correct classification may be obtained despite non total positional coincidence of the: +, - and 0 characters between the patient classification masks and the disease classification masks as evidenced by classification coincidence factors < 1.00 (fig.2).
- The unknown test set persons (fig.6) classify similarly (fig.1) as the learning set persons (fig.2) showing robustness of the classification process towards the prospective classification of unknown persons.
- The selected parameters of the disease classification masks (fig.3) differ in most instances statistically significantly between normal and overtrained cylcists (fig.5). The 11 selected parameters constitut only a small fraction (6.5%) of the totally available information of 170 parameters (fig.4).
|© 2023 G.Valet|