|
CLASSIF1 Data Pattern Analysis
|
Myocardial Infarction Risk Assessment
(Thrombocyte Activation Antigens)
< fig.1
fig.2: Reclassification of the Learning Set
> fig.3
- The disease mask for the reference group of
patients (normals) contains typically a sequence of (0)
characters because the majority (80%) of the parameter values are
located between the two percentiles thresholds
10% and 90%, 10% below (-) the lower percentile and 10% above (+) the
upper percentile.
- Unknown
patients are classified according to the highest positional
coincidence of the patient classification mask with any of the
disease classification masks.
- The degree of coincidence between the patient mask
and the best fitting disease mask is expressed by
the mask coincidence factor. The coincidence factor
is 1.00 for patients #10/14/16/17/18/19/23 but also for non risk
(normal) patients #1/6/7 (arrows <= ) despite the fact that not all
triple matrix characters are (0). Infarct risk patients
have all discriminatory parameters of the disease mask
increased (+), patients with normal (0) or diminished (-) discriminatory
parameter values belong to the non risk (normal) patients.
Parameter values (-) are therefore counted as hit for non risk
(normal) patients, thus explaining the coincidence factor of 1.00 for
patients #6/7.
- Displayed are the triple matrix patterns of the first 10 patients of
the normals and the myocardial risk patients. The patients missing
in the patient number sequence like #101, #105, #110, #136, #140,
#145 have been included into the
unknown
test (validation) set of patients prior to learning as
the 1st, 5th, 10th etc patient of either patient group.
INTERNET:
https://www.classimed.de
last update: Jun 03,2022
first display: Oct 10,1995