Explore the evidence.
Understand the reach.

This study focused on improving the diagnosis of African swine fever (ASF) by improving accuracy, reliability and precision using various machine learning algorithms. Data from the European Union Reference Laboratory for ASF and the EU Animal Disease Information System (ADIS) containing clinical information on wild and domestic pigs were processed and converted into numerical and categorical formats for analysis. Various machine learning models were tested as part of the study, including linear regression, Bayesian regression, support vector machines (SVM), decision trees, random forest classifiers, artificial neural networks (ANNs) and logistic regression. The models were evaluated using metrics such as accuracy, precision, recall, F1-score and root mean square error (RMSE). The results showed that the SVM achieved the lowest performance with 44.4% accuracy, followed by the logistic regression model with 61.5%. The neural network model achieved 69% accuracy, closely followed by the decision tree model with 70%. The linear regression model performed slightly better with 74% accuracy. Bayesian regression achieved a higher accuracy of 80%, while the Random Forest model outperformed all others, achieving the highest accuracy of 88.9%. These results make an important contribution to economic efficiency and innovative applications in veterinary medicine and improve disease management through advanced machine learning techniques.

This review emphasizes the urgent need for effective diagnostic strategies for African swine fever (ASF), a serious disease affecting pig populations worldwide. The aim of the review is to analyze the existing research on ASF diagnostics through a comprehensive literature review, focusing on different diagnostic approaches, including clinical assessments, PCR tests, ELISA, rapid tests and epidemiological models. It examines their sensitivity, specificity and overall performance, addressing challenges such as the varying sensitivity of tests and cross-reactivity. The review highlights both the strengths and limitations of current methods and suggests areas for improvement and standardization. Recommendations are made for future research and the development of innovative diagnostic tools to improve ASF surveillance and control. This study makes a practical contribution by providing a detailed assessment of ASF diagnostic methods from which veterinary scientists and practitioners can benefit. Theoretical contributions include the identification of gaps in ASF diagnostics and the refinement of discussions on diagnostic accuracy and reliability. These findings are consistent with the journal’s focus on infectious diseases and veterinary research and support progress in veterinary medicine and animal welfare.

This paper presents the practical application of a novel approach, the so-called "Lububu method", to develop a causal machine learning model (CML) for the diagnosis of African swine fever (ASF). The Lububu method was developed to build causal machine learning models by focusing on the contextual understanding of a particular phenomenon and using technological tools to improve accuracy. Its main goal is to identify cause-and-effect relationships that can lead to better outcomes in various fields, including manufacturing, energy production, agriculture, transportation, data management, medicine and computer science. In this study, the Lububu method serves as an experimental framework for the construction of a CML model tailored to ASF diagnosis. This involves gathering comprehensive knowledge about ASF, covering aspects such as the causes, symptoms, transmission patterns and diagnostic procedures. This detailed contextual understanding supports the development of a model that can accurately identify ASF-related factors, ultimately increasing diagnostic effectiveness. By combining AI innovation and epidemiological expertise, this approach redefines ASF diagnostics and paves the way for data-driven, ethical and globally applicable solutions for veterinary medicine.

This paper presents the practical application of a novel approach, the so-called "Lububu method", to develop a causal machine learning model (CML) for the diagnosis of African swine fever (ASF). The Lububu method was developed to build causal machine learning models by focusing on the contextual understanding of a particular phenomenon and using technological tools to improve accuracy. Its main goal is to identify cause-and-effect relationships that can lead to better outcomes in various fields, including manufacturing, energy production, agriculture, transportation, data management, medicine and computer science. In this study, the Lububu method serves as an experimental framework for the construction of a CML model tailored to ASF diagnosis. This involves gathering comprehensive knowledge about ASF, covering aspects such as the causes, symptoms, transmission patterns and diagnostic procedures. This detailed contextual understanding supports the development of a model that can accurately identify ASF-related factors, ultimately increasing diagnostic effectiveness. By combining AI innovation and epidemiological expertise, this approach redefines ASF diagnostics and paves the way for data-driven, ethical and globally applicable solutions for veterinary medicine.

This review emphasizes the urgent need for effective diagnostic strategies for African swine fever (ASF), a serious disease affecting pig populations worldwide. The aim of the review is to analyze the existing research on ASF diagnostics through a comprehensive literature review, focusing on different diagnostic approaches, including clinical assessments, PCR tests, ELISA, rapid tests and epidemiological models. It examines their sensitivity, specificity and overall performance, addressing challenges such as the varying sensitivity of tests and cross-reactivity. The review highlights both the strengths and limitations of current methods and suggests areas for improvement and standardization. Recommendations are made for future research and the development of innovative diagnostic tools to improve ASF surveillance and control. This study makes a practical contribution by providing a detailed assessment of ASF diagnostic methods from which veterinary scientists and practitioners can benefit. Theoretical contributions include the identification of gaps in ASF diagnostics and the refinement of discussions on diagnostic accuracy and reliability. These findings are consistent with the journal’s focus on infectious diseases and veterinary research and support progress in veterinary medicine and animal welfare.

This study focused on improving the diagnosis of African swine fever (ASF) by improving accuracy, reliability and precision using various machine learning algorithms. Data from the European Union Reference Laboratory for ASF and the EU Animal Disease Information System (ADIS) containing clinical information on wild and domestic pigs were processed and converted into numerical and categorical formats for analysis. Various machine learning models were tested as part of the study, including linear regression, Bayesian regression, support vector machines (SVM), decision trees, random forest classifiers, artificial neural networks (ANNs) and logistic regression. The models were evaluated using metrics such as accuracy, precision, recall, F1-score and root mean square error (RMSE). The results showed that the SVM achieved the lowest performance with 44.4% accuracy, followed by the logistic regression model with 61.5%. The neural network model achieved 69% accuracy, closely followed by the decision tree model with 70%. The linear regression model performed slightly better with 74% accuracy. Bayesian regression achieved a higher accuracy of 80%, while the Random Forest model outperformed all others, achieving the highest accuracy of 88.9%. These results make an important contribution to economic efficiency and innovative applications in veterinary medicine and improve disease management through advanced machine learning techniques.