Infectious diseases, accounting for 90% of the health problems worldwide, represent a global health challenge, increasingly driven by climate change, rapid urbanization, changing land-use patterns, global travel, trade, and mobility.1,2 Aging, co-morbidities, increased implantation of prostheses and devices, and multi-drug-resistant microorganisms are among the factors contributing to this challenge.3 These elements not only complicate disease management but also heighten the risk of infections and recurrence. Moreover, the detection of low-grade inflammation and occult infections remains difficult, leading to delayed diagnosis and therapy. As a result, in clinical practice, there is a growing need for innovative approaches to facilitate early detection, enable timely specific therapy, and efficiently assess treatment response.4,5 Similarly, inflammatory diseases often follow an insidious course, making early diagnosis challenging. The lack of specific signs and symptoms in the initial stages of the disease, frequently results in delayed treatment, disease progression and, in many cases, irreversible disability. This progression places an increasing burden on quality of life of patients and caregivers, and the healthcare system, necessitating early diagnosis and efficiently therapeutic strategies.6 Artificial Intelligence (AI) is offering promising solutions to transform healthcare and address these challenges in infection and inflammation.7 Moreover, the pandemic has served as a case study in which AI has been successfully applied.8 AI tools are increasingly used for a growing number of tasks in the imaging field ranging from technical applications which improve the sensitivity of scanners to biomedical applications.9 In this review we report the state-of-the-art knowledge on the application of AI models in infection and inflammation nuclear medicine imaging.