It has recently been established that 40% of farmed flocks face a lameness problem at a rate greater than 5%. For herds with 10% or more lameness-affected animals, losses are estimated at around €10 per animal per year. This cost includes the required medication, labor costs for podiatry, milk loss and vet fees. All this can be avoided by implementing the proposed system for the early diagnosis of lameness. The farmer will now have in his hands a reliable tool with which he can improve the efficiency of the herd by taking advantage of the full life cycle of his livestock by avoiding the premature slaughter of animals with lameness.

It will also increase the milk production capacity of the animals significantly through the quick diagnosis of the symptoms of diseases in the latent state as well as the disorders of the nutrition of the animals. Finally, there will be positive effects on the operational costs of the unit through the reduction of expenses for pharmaceutical treatments and veterinary services. As a consequence, there will be an upgrade of local products, strengthening of human resources at the local level, upgrade and expansion of the company’s operations as well as partnership with research bodies benefiting from the adoption of new technologies.

The system is applied for the first time in Greece, since it is the product of original laboratory research. Given that the detection of lameness today is mainly carried out by visual subjective assessment of the animal, initially by the breeder himself and then by the veterinarian, the proposed system will be a reliable and affordable solution to the issue of early diagnosis of lameness.

It has been proven that the use of the 5-point grading scale does not provide particular reliability in the diagnosis of lameness, while other modern methods of diagnosing lameness are mainly based on the use of visual media where they try to diagnose animals with lameness using images and videos. The disadvantage of these methods lies in their difficulty to monitor the animal continuously in its natural habitat. Therefore, the need to establish a new method of detecting lameness with continuous recording of the kinesiological characteristics of the animal in its natural space using new machine learning algorithms will provide a clear solution to the problem of timely diagnosis of lameness at an early stage.