Minimal number of chicken daily growth velocities for artificial neural network detection of pulmonary hypertension syndrome (PHS)

Previously, evaluation of the first 2 wk of daily growth velocity with an a rtificial neural network (ANN provided an effective noninvasive approach fo r predicting the susceptibility of broilers to pulmonary hypertension syndr ome (PHS). This study was conducted to define the minimum number of days of growth data and the type of ANN required for the best prediction of PHS su sceptibility. Four experiments were conducted in which broilers were weighe d daily at 0800 h. in Experiment 1, Hubbard male broilers were reared to 50 d of age, with 13 developing PHS and 33 remaining normal (N), for a PHS:N ratio of 13:33. In Experiment 2, ANAK broilers were exposed to cool tempera tures (16 to 17 C) from 17 to 42 d of age, resulting in a PHS:N ratio of 16 :46 for males. in Experiments 3 and 4, Hubbard male and female chicks from a base population and a PHS-resistant line were exposed to cool temperature s from 17 to 42 d (Experiment 3) or 49 d of age (Experiment 4). The PHS:N r atios were 40:68 for males and 6:96 for females in Experiment 3 and 26:91 f or males and 10:58 for females in Experiment 4. Four ANN, back propagation (BP3), Ward back propagation (WardBP), probabilistic (PNN), and general reg ression (GRNN), were evaluated for their ability to predict PHS in the shor test number of days based on daily growth velocities (BWd+1-BWd). A 100% pr ediction of PHS and N birds was considered the criterion of success. Starti ng with 14 d of data, each ANN was trained on daily growth velocity, and th e number of predictive days was reduced with each run of the ANN. The best ANN was a GRNN, which correctly diagnosed PHS and N male broilers on 4 and 6 d of growth velocity data for Experiments 1 and 2, respectively. The resu lts were poorer with the BP3, WardBP, and PNN. The diagnostic ability of th e neural network was not consistent over all four experiments. In Experimen t 2, a minimum of 6 d was required for 100% PHS detection for males. In Exp eriment 3, the best diagnostic value for males was 93% PHS detection and 10 0% N detection at 15 d. For females, the 100% PHS detection occurred at a m inimum of 8 d. In Experiment 4, males had 100% PHS and N detection at a min imum of 11 d. Females had a 100% PHS and N detection at a minimum of 10 d. An attempt to build a single neural network that would detect PHS susceptib ility in Hubbard (Experiment 1) and ANAK (Experiment 2) broilers was unsucc essful. The application (validation) of neural networks between experiments also was not successful (data not presented). However, these studies demon strate that within a breed or line reared under similar selection pressures for ascites, a GRNN based on the first 14 d of growth velocity can detect, with at least 93% accuracy, broilers susceptible to PHS.