This paper considers the problem of incorporating context in medical cyber-physical systems (MCPS) applications for the purpose of improving the performance of MCPS detectors. In particular, in many applications additional data could be used to conclude that actual measurements might be noisy or wrong (e.g., machine settings might indicate that the machine is improperly attached to the patient); we call such data context. The first contribution of this work is the formal definition of context, namely additional information whose presence is associated with a change in the measurement model (e.g., higher variance). Given this formulation, we developed the context-aware parameter-invariant (CA-PAIN) detector; the CA-PAIN detector improves upon the original PAIN detector by recognizing events with noisy measurements and not raising unnecessary false alarms. We evaluate the CA-PAIN detector both in simulation and on real-patient data; in both cases, the CA-PAIN detector achieves roughly a 20-percent reduction of false alarm rates over the PAIN detector, thus indicating that formalizing context and using it in a rigorous way is a promising direction for future work.