An artificial neural network was trained to predict the presence or ab
sence of ascites in broiler chickens. The neural network was a three-l
ayer back-propagation neural network with an input layer of 15 neurons
(defining 15 physiological variables), a hidden layer of 16 neurons,
and an output layer of 2 neurons (the presence or absence of ascites).
Male by-products of a breeder pullet line were brooded at 32 and 30 C
during Weeks 1 and 2, respectively. The training set for the neural n
etwork consisted of data from birds subjected to cool temperatures (18
C) to induce ascites. After training, the predictive ability of the n
eural network was verified with two new data sets. The second data set
was from birds subjected to cool temperatures (18 C). The third data
set was from birds subjected to clamping of the pulmonary artery to si
mulate the physiological processes involved in ascites (the temperatur
e was 24 C). A comparison was made between laboratory diagnostic resul
ts and the neural network predicted ascites incidence. The neural netw
ork accurately identified the presence or absence of ascites in the fi
rst (training) set. Two false positives and one false positive were id
entified in the second and third verification sets, respectively. The
birds identified as false positives were determined to be in the devel
opmental stages of ascites before the occurrence of fluid accumulation
. Artificial neural networks were found to effectively identify broile
rs with and without ascites.