US 7,321,881 B2
Methods and systems for predicting occurrence of an event
Olivier Saidi, Greenwich, Conn. (US); David A. Verbel, New York, N.Y. (US); and Lian Yan, Chester Springs, Pa. (US)
Assigned to Aureon Laboratories, Inc., Yonkers, N.Y. (US)
Filed on Feb. 25, 2005, as Appl. No. 11/67,066.
Claims priority of provisional application 60/577051, filed on Jun. 04, 2004.
Claims priority of provisional application 60/548322, filed on Feb. 27, 2004.
Prior Publication US 2005/0197982 A1, Sep. 08, 2005
Int. Cl. G06E 1/00 (2006.01); G06E 3/00 (2006.01); G06F 15/18 (2006.01); G06G 7/00 (2006.01); G01N 33/574 (2006.01)
U.S. Cl. 706—21  [706/15; 435/7.23] 14 Claims
OG exemplary drawing
 
1. A method for predicting recurrence of cancer in a patient comprising:
estimating the probability that cancer will recur within a shorter period of time in a patient with a higher prognostic score than a patient with a lower prognostic score, wherein estimating comprises conducting pair-wise comparisons between prognostic scores for patients i and j, using a neural network trained using an objective function comprising a function C substantially in accordance with an approximation of the concordance index.