ML pipelines, as key components of ML systems, shall be developed following quality assurance techniques. Unfortunately, it is often the case in which they present maintainability issues, due to the experimental nature of data collection and ML model construction. In this work, we perform a first evaluation of a set of metrics, proposed in previous research, for measuring the presence of code smells related to maintainability, in ML pipeline application examples. Moreover, we provide the lessons learnt and insights gained from this evaluation.