Health problems in dairy cows are detrimental to animal welfare, cause production losses and lead to treatment costs. Early detection of health disorders can have cow welfare as well as economic benefits. For disorders that affect short-term feeding behaviour, the automatic monitoring of such behaviour by electronic tagging of cows could assist in early detection. The first objective of the study was to describe and quantify changes in short-term feeding behaviour of dairy cows that occur with the onset of the health disorders ketosis, mastitis, acute locomotory problems and chronic lameness. The evaluation of the suitability of an algorithm based on those changes as a diagnostic tool for the early identification of health problems in group-housed dairy cows was our second objective.