Mathematical algorithm
A
list of differential diagnoses is provided by the database with each set of
input data. The differential diagnoses
have an assigned value of profile factor (PF).
The PF value for a neoplasm reflects how well its immunophenotyping
pattern matches that of a given case. In
this project, accumulated data from published literature are utilized to
enhance the sensitivity and specificity of the differential diagnosis. The formula for calculating PF is as
following:
Where
PF : profile factor for a particular neoplasm
Cn :
profile coefficient for an input data (0 ≤ Cn ≤
1)
n = 1 to N
N :
the number of (not-NULL) attributes of a neoplasm that have input data
The profile coefficient is calculated as:
Cn = PosRatio(i,j) if input data is positive (+), and Cn =NegRatio(i,j) if input data is negative (-)
The
ratio of cases that are positive for a certain marker for a disorder, PosRatio(i,j), is defined as:
Where
i: the i th disorder
j: the j th marker
: number of cases that are positive for the j th marker for the ith disorder
: number of cases under study for the j th
marker for the ith disorder
The
ratio of cases that are negative for a certain marker for a disorder, NegRatio(i,j), is calculated as:
= 1 - 
with **tag in
database indicates that the marker is very critical, its contribution will be
twice as that of other markers (the increment will be 2x in calculationg PF).
The normalized profile factor (nPF) is calculated to convert PF to a value between
0 and 1, ie. (0 ≤ nPF
≤ 1) using a sigmoid function:
