Breast cancer is the most common cancer in women across the globe and a major cause of death. Neoadjuvant chemotherapy (NACT) is the standard of care for patients with locally advanced breast cancer (stage II-III), delivered with the intention of shrinking the tumour before proceeding to surgery. However, only 39% of patients achieve pathological complete response and up to 12% experience no response at all. Non-responsive patients suffer the side-effects of their chemotherapy regimen without reaping any benefit. As such, there is a clear need to accurately identify non-responsive tumours as early as possible, enabling clinicians to discontinue the unsuccessful NACT and proceed with alternative treatment. For this purpose, we propose using digital twins: virtual replicates of a patient’s tumour cellularity, which can be evolved in time to predict evolution under a NACT regimen. Initial tumour cellularity is estimated from diffusion-weighted magnetic resonance imaging (MRI), and used to calibrate biophysically relevant mathematical models of tumour growth. The current state-of-the-art digital twin builds on the previous mechanically-coupled reaction-diffusion (MC-RD) tumour growth model to include drug delivery, and has been tested on five patients. The effects of the NACT treatment are estimated from dynamic contrast-enhanced MRI, without modelling the flows through which these processes occur. Building on these encouraging results, we expect that including fluid flow modelling should improve the accuracy of predictions. We aim to do this using multiple-network poroelastic theory (MPET), which has previously been successfully applied to flows in the brain. As a first step to these extensions, we have implemented the MC-RD model using FEniCS and validated it on several patients from the CHERNAC study. By extending to a larger cohort of patients undergoing more diverse NACT regimens, potential limitations of the underlying model can be identified. Addressing these limitations in our digital twin will facilitate more accurate predictions of NACT outcome.