This systematic review, conducted by Amin et al., examines the ability of wearable devices and smartphones to recognize, monitor, and identify features of depression in diagnosed individuals. From Pubmed and the Web of Science databases, 9 studies on this topic were included in this review. The information collected from the participants of these studies included call logs, step counts, sleep, heart rate, and GPS data, and depression severity was determined based on questionnaire scores from the Patient Health Questionnaire - 8/9 (PHQ - 8/9) and Beck Depression Inventory - Second Edition. From their results, Amin et al. found that among these studies, one was able to detect significant sleep association with depression severity. Additionally, 6 studies examined the usage of machine learning software in utilizing collected information to predict depression severity, and across the studies, model accuracy ranged from approximately 79% to 87%. While certain issues - such as participant dropout, the lack of active intervention studies, and incomplete or missing data - need to be addressed by future studies, Amin et al. concludes that these results demonstrate the potential of wearable devices and smartphones in monitoring and assisting individuals diagnosed with major depressive disorder through data collection and machine learning.