Postpartum Depression (PPD) is a complex and prevalent mental health condition, often challenging to diagnose and treat effectively. While PPD has been widely studied in the context of traditional risk factors, the research linking chronic diseases to mental health issues is limited. Predicting PPD by utilizing the power of machine learning algorithms can lead to timely intervention and management of the condition. In this paper, we present results obtained from various predictive machine learning models to forecast the likelihood of depression for mothers who suffer from one or more chronic diseases. All models demonstrate a close alignment in their SHAP analysis in identifying key predictors. The results also highlight how chronic diseases could potentially interact with other common risk factors and increase the likelihood of PPD. The models consistently identified chronic diseases, asthma, and anemia as key predictors along with other interacting features. The results demonstrate the potential of machine learning as a screening tool to improve diagnostic precision and support personalized care for enhanced quality of life. An interactive diagnostic screening tool based on these models was also developed.