An increasing proportion of software characterizes modern automated systems such as vehicles. It can be used to provide new functions to improve the customer experience in terms of automation, personalization, and connectivity. For system development, this means that classic processes must be rethought and supplemented by new strategies. This is mapped via the trend of the software-defined systems. In this context, individual components can be improved over the entire life cycle. In order for these updates to function properly, testing before deployment is commonplace. However, since the software is complex and it is infeasible to test 100% of the possible scenarios, a software update can still lead to unforeseen side effects. At the same time, it must be monitored whether the desired update effects actually apply. In the worst case, the side effects include errors that must be found as quickly as possible in order not to negatively influence product quality and subsequent innovation cycles. The goal of this work is to detect side effects that manifest themselves as anomalies at runtime and to trace them back to the corresponding code change. For this purpose, a new approach is presented that uses the digital twin of the vehicle as an information base, providing operational data and simulations parallel to operation. The simulation generates synthetic data also containing the rare and risky cases that can then be matched against the operational data to identify anomalies. Once an anomaly is detected, a subsequent analysis follows that relates the anomaly to a causal code sequence. The presented approach is realized using the example of a model vehicle with microcontrollers and corresponding peripherals such as sensors and motors. The model vehicle is simulated using the simulation software SimulIDE, which provides the synthetic data. The evaluation shows that the trace back of side effects to the respective code sequences can successfully be achieved.