Sub-clinical mastitis (SM) is the most economically damaging yet often visually undetectable disease of dairy cows. Early detection and treatment can reduce the loss caused by the disease, thus, the continuous improvement of SM diagnostic methods is necessary. Albeit, the somatic cell count (SCC) of milk is commonly measured for diagnostic purposes, its direct determination is not widely used in everyday practice. The primary objective of our work was to investigate whether the predictive value of SM diagnostics can be improved by training artificial neural networks (ANNs) on data generated using common milking machines. The best ANN classifier had a sensitivity of 0.54 and a specificity of 0.77, which is comparable to the performance of several California Mastitis Tests (CMT) in the literature. Combining two diagnostic tests, ANN and CMT, we concluded that the positive predictive value could be up to 50% higher than the value provided by the individual CMT. While the implementation of CMT is a labor-intensive process, in milking parlors where milk or milk yield data can be measured automatically, similar to our work, SCC-gain predictions for all individuals could be obtained on a daily basis.