Osteoporosis represents a significant clinical challenge, particularly in the aging population, leading to a heightened risk of fractures and long-term disability. Traditional therapeutic strategies often fall short, necessitating innovative approaches for effective fracture repair. Tissue Engineering (TE) has emerged as a transformative approach in regenerative medicine, focusing on developing three dimensional structures to facilitate the regeneration of damaged tissues. This thesis presents an investigation into the optimisation of 3D bioprinted scaffolds for bone repair, using Design of Experiments (DoE) and Machine Learning (ML) methodologies. The work details the development of a bioprinted collagen-hydroxyapatite scaffold for bone TE applications. Utilising DoE, the research optimises parameters affecting scaffold printability, mechanical integrity, and rheological properties. A significant advancement is made in automating scaffold degradation measurement through image analysis tools, comparing the efficacy of ML models such as Convolutional Neural Networks (CNN) and Long Short-Term Memory (LSTM) networks in scaffold degradation prediction using image-derived and numerical data. The thesis lays out the development of a ML framework that can quantify the structural integrity and functionality of bioprinted scaffolds over time. By doing so, it addresses critical challenges in bone TE, like the optimisation of scaffold properties and the real-time monitoring of degradation processes. An integral contribution of this thesis is the construction of a user-friendly interface platform that predicts scaffold degradation. Moreover, the research successfully develops an image analysis tool capable of detecting changes in pore size and porosity within scaffolds, validated using micro-CT images.