Intramedullary (IM) nailing is a widely accepted treatment for femoral shaft fractures due to its good healing rate and rapid return to full weight bearing. However, a significant number of patients experience impairments years after treatment. To enhance individual outcomes, a personalized rehabilitation protocol based on impairment monitoring is essential. We propose a continuous surface electromyography (EMG) measurement system worn on vastus lateralis (VL) and vastus medialis (VM) in combination with a convolutional neural network (CNN) to monitor the load put on the treated leg, as this is an indicator of impairments and healing progress. To test the feasibility of such an approach, a study was conducted with healthy participants (N = 8) simulating a reduced load on the leg. Our study showed promising results, as the CNN could on average achieve a validation accuracy of 91.6% in classifying steps with normal and reduced load on the leg. These results demonstrate the potential of using EMG measurements from VL and VM to monitor changes in leg loading during rehabilitation and offer the opportunity to improve individual rehabilitation after IM nailing.