Abstract
Recent advances in cancer research emphasize the development of physiologically relevant models to better understand tumor behavior and therapeutic responses. The tumor microenvironment (TME) plays a pivotal role in tumor progression, metastasis, and treatment resistance. Three-dimensional (3D) bioprinting offers unique capabilities for constructing complex in vitro tumor models that closely replicate the TME heterogeneity and interactions. These biomimetic models surpass the limitations of traditional 2D cultures and reduce the reliance on animal testing. This review aimed to systematically map current research on 3D bioprinting and artificial intelligence (AI) applications in modeling TME across selected cancer types. The review was structured into three thematic domains: 3D bioprinting of TME models for selected cancer types, AI applications in 3D bioprinting regardless of clinical focus, and integration of AI with 3D bioprinting specifically for TME modeling. A comprehensive literature search was conducted in PubMed, covering publications from January 2020 to June 2025. The review was conducted in accordance with PRISMA-ScR guidelines and focused on peer-reviewed original research articles published in English. Included cancer types were colorectal cancer, oral cancer, breast cancer, and glioma. In total, 63 articles were screened for TME-specific 3D bioprinting, with 44 included. For AI applications in 3D bioprinting irrespective of cancer type, 67 records were identified and 14 met the inclusion criteria. Only one study explicitly integrated AI and 3D bioprinting for TME modeling, highlighting a critical research gap. These findings are illustrated in the PRISMA flowcharts for clarity. Despite growing interest in both 3D bioprinting and AI, their combined application for modeling of the tumor microenvironment remains limited. The reviewed literature demonstrates significant progress in bioink development, process optimization, and quality control through AI methods. However, further interdisciplinary research is necessary to realize the potential of AI in enhancing TME modeling for oncology applications.