查看文章

To the Editor—Artificial intelligence (AI)-based technologies dominate medical headlines and are routinely touted as the panacea for a number of longstanding deficiencies across health systems globally. Stakeholders from healthcare, government, computer science and industry backgrounds are confident that AI can be positioned to tackle (1) the high rate of avoidable medical errors,(2) workflow inefficiencies and (3) delivery inefficiencies associated with contemporary healthcare provision1. Despite these lofty ambitions, the integration of AI into everyday practice within the health sector has been limited thus far. So far, the majority of AI interventions that are close to translation are predominantly in the field of medical diagnostics. In the current paradigm, diagnostic investigations require timely interpretation from an expert clinician in order to generate a diagnosis and to direct subsequent episodes of care. The …