Table 4.
Predictive performance of the selected binary logistic regression model for detecting woody breast (WB) condition in broiler carcasses by sex using image measurements.
| Sex | Data set1 | Fit details2 |
Parameter estimates and odds ratio (OR) |
||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Gen. R2 | RMSE | MAD | MR (%) | TPR (%) | FPR (%) | AUC | Parameter | Estimate | Std. Error | Pr > χ2 | OR | ||
| Female | Training | 0.69 | 0.18 | 0.07 | 4.44 | 68.97 | 1.75 | 0.97 | M1 | 2.07 | 0.58 | 0.0003 | 7.94 |
| Validation | 0.65 | 0.18 | 0.07 | 4.44 | 60.00 | 1.60 | 0.98 | M2 | −9.91 | 2.14 | <0.0001 | 4.99 × 10−5 | |
| M3 | 2.30 | 0.64 | 0.0003 | 10.02 | |||||||||
| Male | Training | 0.64 | 0.30 | 0.18 | 13.65 | 71.43 | 8.82 | 0.93 | M1 | 1.47 | 0.37 | <0.0001 | 4.37 |
| Validation | 0.63 | 0.31 | 0.17 | 14.81 | 74.29 | 11.00 | 0.93 | M2 | −8.03 | 1.21 | <0.0001 | 3.25 × 10−4 | |
| M3 | 1.36 | 0.28 | <0.0001 | 3.90 | |||||||||
| As-hatched | Training | 0.65 | 0.26 | 0.13 | 9.05 | 63.21 | 3.44 | 0.95 | M1 | 1.39 | 0.30 | <0.0001 | 4.03 |
| Validation | 0.61 | 0.26 | 0.13 | 8.52 | 71.11 | 4.44 | 0.94 | M2 | −7.55 | 1.00 | <0.0001 | 5.24 × 10−4 | |
| M3 | 1.83 | 0.28 | <0.0001 | 6.23 | |||||||||
Abbreviations: AUC, area under the ROC (receiver operating characteristic) curve; FPR, false positive rate; MR, misclassification rate; MAD, mean absolute deviation; RMSE, root mean square error; TPR, true positive rate (sensitivity, ST).
1
Training (n = 315) and validation (n = 135). As-hatched group included all data set (n = 900) divided into 2 sets of training (n = 630) and validation (n = 270).
2
The model used for WB prediction (model 1): Logit (p) = α + β1 M1 + β2 M2 + β3 M3.