This editorial discusses the integration of artificial intelligence (AI) into healthcare systems, focusing on the evaluation of clinically relevant outcomes and the ecosystem required for AI algorithms to succeed in clinical settings. Boussina et al. evaluated a deep learning sepsis prediction model (COMPOSER) in two emergency departments at UC San Diego Health, reporting a 17% relative reduction in in-hospital sepsis mortality and a 10% relative increase in sepsis bundle compliance over a five-month period. The study highlights the importance of integrating AI algorithms into clinical workflows, ensuring explainability, and continuous monitoring to adapt to evolving healthcare needs. However, the editorial also emphasizes the challenges posed by the human nature of healthcare, such as patient diversity and evolving treatment paradigms, which can affect the performance of AI models over time. The authors advocate for a multidisciplinary approach to address these challenges and ensure the successful implementation and adaptation of AI in healthcare.This editorial discusses the integration of artificial intelligence (AI) into healthcare systems, focusing on the evaluation of clinically relevant outcomes and the ecosystem required for AI algorithms to succeed in clinical settings. Boussina et al. evaluated a deep learning sepsis prediction model (COMPOSER) in two emergency departments at UC San Diego Health, reporting a 17% relative reduction in in-hospital sepsis mortality and a 10% relative increase in sepsis bundle compliance over a five-month period. The study highlights the importance of integrating AI algorithms into clinical workflows, ensuring explainability, and continuous monitoring to adapt to evolving healthcare needs. However, the editorial also emphasizes the challenges posed by the human nature of healthcare, such as patient diversity and evolving treatment paradigms, which can affect the performance of AI models over time. The authors advocate for a multidisciplinary approach to address these challenges and ensure the successful implementation and adaptation of AI in healthcare.