Machine learning has been instrumental in improving the accuracy and automating medical diagnosis. In this research, we developed a decision tree-based machine learning model for automating the diagnosis of two diseases: left ventricular hypertrophy (LVH) and non-alcoholic fatty liver disease (NAFLD). A decision tree can discover the clinically relevant hidden patterns associated with LVH and NAFLD from clinical data. A decision tree can mimic the diagnostic procedure made by doctors and physicians can interpret all rules generated by a decision tree very easily, which makes it useful to use the proposed model as routine practices in clinical settings. Extensive experimental results demonstrate the superiority of the proposed algorithm.