Advancing 3D bioprinting through machine learning and artificial intelligence

Abstract

3D bioprinting, a vital tool in tissue engineering, drug testing, and disease modeling, is increasingly integrated with machine learning (ML) and artificial intelligence (AI). Although some existing reviews acknowledge this integration, a detailed examination of system and process challenges remains to be discussed. This review divides the topic into two main areas: the process view, which sees bioprinting as a standalone system and outlines data-driven solutions for challenges such as material selection, parameter optimization, and real-time monitoring, and the system view, which delves into the broader ecosystem of bioprinting and its interaction with other technologies. We first present the latest techniques in managing process-specific challenges using ML/AI, highlighting future opportunities. We then navigate through system-wide challenges, emphasizing data-driven solutions. This review also sheds light on potential regulatory frameworks and the need for skilled workforce development, advocating for an alignment between policy and technology progression.