Reducing Complexity of Data Flow Testing in the Verification of a IEC-62304 Flexible Workflow System

In the development of SW applications, the workflow abstraction gives primary relevance to the way how some process can be accomplished through a sequence of connected steps. This largely conditions analysis, implementation architecture, and verification. In particular, testing activities are naturally oriented towards a data flow approach, which effectively exercises dependencies among steps. In several application scenarios, the workflow model cannot completely determine the sequencing of actions and it must rather leave space to variability. While easily encompassed both in the analysis and implementation stages, this comprises a major hurdle for the testing stage due to the explosion in the number of allowed execution orders and paths.

We address the problem reporting on the verification of the control software of a Computer Assisted Surgery system. In this case, the workflow abstraction captures the constraints of a medical protocol, and variability in the order of steps reflects dynamic adaptation of the course of actions to the specific characteristics of each patient. This largely increases the testing effort needed to accomplish the prescriptions of the IEC-62304 certification standard. To cope with the problem, we show how data flow analysis can be used to identify an appropriate set of constraints that can be exploited in the verification stage, so as to reduce the test suite while preserving coverage.