Research perspectives on animal health in the era of artificial intelligence

Abstract

Leveraging artificial intelligence (AI) approaches in animal health (AH) makes it possible to address highly complex issues such as those encountered in quantitative and predictive epidemiology, animal/human precision-based medicine, or to study host × pathogen interactions. AI may contribute (i) to diagnosis and disease case detection, (ii) to more reliable predictions and reduced errors, (iii) to representing more realistically complex biological systems and rendering computing codes more readable to non-computer scientists, (iv) to speeding-up decisions and improving accuracy in risk analyses, and (v) to better targeted interventions and anticipated negative effects. In turn, challenges in AH may stimulate AI research due to specificity of AH systems, data, constraints, and analytical objectives. Based on a literature review of scientific papers at the interface between AI and AH covering the period 2009-2019, and interviews with French researchers positioned at this interface, the present study explains the main AH areas where various AI approaches are currently mobilised, how it may contribute to renew AH research issues and remove methodological or conceptual barriers. After presenting the possible obstacles and levers, we propose several recommendations to better grasp the challenge represented by the AH/AI interface. With the development of several recent concepts promoting a global and multisectoral perspective in the field of health, AI should contribute to defract the different disciplines in AH towards more transversal and integrative research.

Keywords: Animal disease; Artificial intelligence; Data; Decision support tool; Livestock; Modelling.

Figure 1

Interactions between animal health (AH), artificial intelligence (AI), and closely related research domains. This illustration is pinpointing only the links between AH (in blue), AI and its main subfields (in red), and other related fields of research (in black). It can be naturally complexified through the interactions between AH and other research topics (e.g., human medicine) or between core disciplines (e.g., statistics and physics).

Figure 2

AI at the service of mechanistic epidemiological modelling (adapted from [51]). A. Modellers develop each epidemiological model de novo, producing specific codes not easily readable by scientists from other disciplines or by model end-users. B. Using AI approaches to combine a domain-specific language and an agent-based software architecture enhances reproducibility, transparency, and flexibility of epidemiological models. A simulation engine reads text files describing the system to automatically produce the model code. Complementary add-ons can be added if required. Models are easier to transfer to animal health managers as decision support tools.

Figure 3

Extracting information from massive data to monitor animal health and better rationalise treatments.

Figure 4

Identifying relevant strategies to control bovine paratuberculosis at a regional scale (adapted from [76]). Classically, identifying relevant strategies means defining them a priori and comparing them, e.g., by modelling. Only a small number of alternatives can be considered. If all alternatives are considered as in the figure, it results in a multitude of scenarios whose analysis becomes challenging. Here, each point corresponds to the epidemiological situation after 9 years of pathogen spread over a network of 12 500 dairy cattle herds for a given strategy (asterisk: no control). Initially, 10% of the animals are infected on average in 30% of the herds. The blue dots correspond to the most favourable strategies. Mobilizing AI approaches in such a framework, especially optimization under constraints, would facilitate the identification of relevant strategies by exploring the space of possibilities in a more targeted manner.