For conditions like osteoporosis, changes in bone pore geometry even when porosity is constant have been shown to correlate to increased fracture risk using techniques such as dual-energy x-ray absorptiometry (DXA) and computed tomography (CT). Additionally, studies have found that bone pore geometry can be characterized by ultrasound to determine fracture risk, since certain pore geometries can cause stress concentration which in turn will be a source for fracture. However, it is not yet fully understood if changes in pore geometry can be detected by ultrasound when the porosity is constant. Therefore, this study develops an unsupervised machine learning model classifying pore geometry between bioinspired and quadrilateral pore scaffolds with constant porosity using experimental ultrasound wave transmission data. Our results demonstrate that differences in pore geometry can be detected by ultrasound, even at constant porosity, and that these differences can be distinguished in an unsupervised manner with machine learning. For traumatic bone injuries and late-stage osteoporosis where fracture occurs, tissue scaffolds are used to aid the healing of fractures or bone loss. The scaffold design is optimized to match material properties closely with bone, and healing can be enhanced with ultrasound stimulation. In this study we predict the combined effects of ultrasound parameters, such as wave frequency and mode of displacement, and scaffold material properties on bone tissue growth. We therefore develop an unsupervised machine learning clustering model of bone tissue growth in the scaffolds using finite element analysis and bone growth algorithms evaluating effects of pore geometry, scaffold materials, ultrasound wave type and frequency, and mesenchymal stem cell distribution on bone tissue growth. The computational predictions of tissue growth agreed within 10% of comparable experimental studies. The data corresponding to pore geometry, mesenchymal stem cell distribution, and scaffold material demonstrate distinct clusters of total bone formation, while ultrasound frequency and mesenchymal stem cell distribution show distinct clusters in bone growth rate. These variables can be tuned to tailor the scaffold design and optimize the required amount and rate of bone growth to meet a patient's specific needs.