AI-Driven Mobile Application for Self-Monitoring Personalized Premenstrual Symptoms and Risk Assessment of Depressive Crises in Female University Students

Abstract

Premenstrual Syndrome (PMS) and depressive symptoms are common concerns for female university students, often triggered by hormonal fluctuations before menstruation. These conditions can severely impact academic performance, interpersonal relationships, and overall well-being, particularly when symptoms escalate into severe depressive episodes. Even though the prevalence, awareness, and self-management strategies among students are on the rise, they remain limited, particularly in cultural contexts where women's health and emotional well-being receive little attention. This study presents the development of an AI-driven mobile application designed to facilitate personalized tracking of premenstrual symptoms and assess the risk of depressive episodes. The application integrates machine learning models trained on self-reported psychological and physiological data, using validated instruments such as DASS-21 and PSST-A. The research adopted a mixed-methods approach, involving survey-based symptom identification, model training and validation, system design, and user satisfaction evaluation. This research contributes to the development of artificial intelligence-assisted self-care technology for the purpose of monitoring personal health and taking preventative psychological measures. The findings indicate that the application that was developed is beneficial in terms of forecasting the likelihood of someone suffering from depression and fostering self-awareness regarding mental health among college students. Considering this, the system has the potential to develop into a useful tool for providing aid to female students attending universities.