Explore the evidence.
Understand the reach.

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.