The need for organ transplants has risen, but the number of available organ donations for transplants has stagnated worldwide. Regenerative medicine has been developed to make natural organs or tissue-like structures with biocompatible materials and solve the donor shortage problem. Using biomaterials and embedded cells, a bioprinter enables the fabrication of complex and functional three-dimensional (3D) structures of the organs or tissues for regenerative medicine. Moreover, conventional surgical 3D models are made of rigid plastic or rubbers, preventing surgeons from interacting with real organ or tissue-like models. Thus, finding suitable biomaterials and printing methods will accelerate the printing of sophisticated organ structures and the development of realistic models to refine surgical techniques and tools before the surgery. In addition, printing parameters (e.g., printing speed, dispensing pressure, and nozzle diameter) considered in the bioprinting process should be optimized. Therefore, machine learning (ML) technology can be a powerful tool to optimize the numerous bioprinting parameters. Overall, this review paper is focused on various ideas on the ML applications of 3D printing and bioprinting to optimize parameters and procedures.
Keywords: 3D bioprinting; machine learning; optimization; regenerative medicine.