Angioli et al reported a model for predicting endometrial cancer in a woman. The authors are from Campus Bio Medico University of Rome.
Patient selection: women from 45 to 80 years of age
Parameters:
(1) age in years
(2) serum HE4 (human epididymis protein 4) concentration in pmol/L
(3) endometrial thickness in mm
(4) presence of symptoms (abnormal bleeding, other)
Parameter
Finding
Points
age in years
0.062343 * (age)
serum HE4
0.039591 * (HE4)
endometrial thickness
0.25017 * (thickness)
symptoms
no
-2.66275
yes
0
value of X =
= SUM(points for all of the parameters) - 7.4545
probability of endometrial malignancy =
= 1 / (1 + EXP((-1) * X))
Performance:
• The area under the ROC curve is claimed to be 0.96 in the training set.
To read more or access our algorithms and calculators, please log in or register.
Specialty: Hematology Oncology
