Machine learning approaches have been widely used for fault-prone module detection. Introduction of machine learning approaches induces development of new software metrics for fault-prone module detection. We have proposed an approach to detect fault-prone modules using the spam- filtering technique. To use our approach in the conventional fault-prone module prediction approaches, we construct a metric from the output of spam-filtering based approach. Using our new metric, we conducted an experiment to show the effect of new metric. The result suggested that use of new metric as well as conventional metrics is effective for accuracy of fault-prone module prediction.