Multiple linear regression and clustering techniques are tools that have been extensively applied in several financial, technical, and biomedical arenas, where vast quantities of data are produced and stored. These techniques show promise in analyzing the performance of departments responsible for and related to hospital equipment maintenance and, thereafter, identifying and improving areas of concern. As a contributory measure, this research is focused on the analysis of quality and effectiveness of corrective (nonscheduled) maintenance tasks in the healthcare environment and the improvement of those processes. The two main objectives of this research are to build a predictor for a TAT indicator to estimate its values and to use a numeric clustering technique to find possible causes of undesirable values of TAT.