Turning chaotic sample group clusterization into organized ones by feature selection: Application on photodiagnosis...

Bovine brucellosis diagnosis is a major problem to be solved; the disease has a tremendous economic impact with significant losses in meat and dairy products, besides the fact that it can be transmitted to humans. The sanitary measures instituted in Brazil are based on disease control through diagnosis, animal sacrifice, and vaccination. Although the currently available diagnostic tests show suitable quality parameters, they are time-consuming, and the incidence of false-positive and/or false-negative results is still observed, hindering effective disease control. The development of a low-cost, fast, and accurate brucellosis diagnosis test remains a need for proper sanitary measures at a large-scale analysis. In this context, spectroscopy techniques associated with machine learning tools have shown great potential for use in diagnostic tests. In this study, bovine blood serum was investigated by UV-vis spectroscopy and machine learning algorithms to build a prediction model for Brucella abortus diagnosis. Here we first pre-treated the UV raw data by using Standard Normal Deviate method to remove baseline deviation, then apply principal component analysis - a clustering method - to observe the group formation tendency; the first results showed no clustering tendency with a messy sample score distribution, then we properly select the main principal components to improve clusterization. Finally, by using machine learning algorithms (SVM and KNN), the predicting models achieved a 92.5% overall accuracy. The present methodology provides a test result in an average time of 5 min, while the standard diagnosis, with the screening and confirmatory tests, can take up to 48 h. The present result demonstrates the method's viability for diagnosing bovine brucellosis, which can significantly contribute to disease control programs in Brazil and other countries.