False positives/negatives calibration

The table reports the experiment number Exp, capacity parameter C, kernel type K (linear L polynomial P radial basis function R neural N anova A), and corresponding parameters, calibration results (TP,., true positive in calibration FN, false negative in calibration TN,-, true negative in calibration FP, false positive in calibration SV number of support vectors in calibration AC calibration accuracy), and L20%O prediction results (TPp, true positive in prediction FNp, false negative in prediction TNp, true negative in prediction FPp, false positive in prediction SVp, average number of support vectors in prediction ACp, prediction accuracy). 

Test kit producer-generated data to verify performance claims are required according to an AOAC-approved protocol, to generally include ruggedness tests, calibration curves, accuracy, precision, cross reactivity, test kit component stability, detection limit, limit of quantification and rates of false positives and false negatives. 

False negative alarms occur when instruments fail to respond to targeted chemicals that are present in a sample. These responses are viewed as more problematic than false positive alarms, because failure to produce a necessary alarm may lead to dangerous/disastrous situations. Causes of false negative alarms include changing environmental conditions humidity effects presence of interfering chemicals that mask normal detection capabilities and detector malfunction, such as improper calibration and detection algorithm deviations. 

Results of qualitative SIMCA classification of milk samples based on their NIR spectra after they were divided into healthy or mastitic according to their AEG are presented in Table 9.3.7. Incorrect classification was obtained for five samples from the calibration set (1 false negative and 4 false positive) and for four samples from the test set (2 false negative and 2 false positive). The false negative samples from the calibration set and the test set had SCC< 160,000 cell/ml, which showed that according to their SCC content they were healthy, but their AEC reference value was higher than the threshold set up for AEC. 

---