MindTrack: Doctor–Patient Mental Health Task Assignment & Prediction

This paper presented MindTrack, an Android-based doctor–patient mental health task assignment and trend analysis system. The proposed platform addresses an important gap in conventional therapy by enabling continuous, structured interaction between psychologists and patients outside formal sessions. Through secure task assignment, journaling, mood tracking, appointment scheduling, and anonymized machine learning-based analysis, the system supports both patient en-gagement and clinician awareness. The implemented prototype confirms the feasibility of combining mobile application development, cloud-based data management, and aggregate analytics within a privacy-aware mental health support platform. Testing across all four mod-ules on multiple Android API levels demonstrated correct functional behavior, real-time data synchronization, and mean-ingful ML-generated insights from anonymized data. The K-Means clustering module successfully differentiated patient engagement profiles, and the weekly mood trend visualizations provide psychologists with an at-a-glance summary of patient wellbeing trajectories. While the present system is not intended for autonomous diagnosis, it offers a practical foundation for data-informed therapeutic support. The platform bridges the gap between periodic clinical sessions and continuous daily care, reducing patient reliance on memory during appointments and en-abling psychologists to ground session discussions in objective behavioral data. The separation between personal identity records and analytical outputs ensures that privacy is preserved throughout the data lifecycle. With further validation using real patient data under ethi-cal approval, expanded sensing through wearable integration, richer language analysis via NLP, and predictive alerting capabilities, MindTrack can evolve into a robust clinical-assistive ecosystem for modern mental healthcare. The work presented here establishes a strong architectural and functional foundation for these future enhancements.

[1]     World Health Organization, “Depressive disorder (depression),” WHO Fact Sheets, Mar. 2023. [Online]. Available: https://www.who.int/ news-room/fact-sheets/detail/depression [2]     J. Torous, M. V. Kiang, J. Lorme, and J. Onnela, “New tools for new research in psychiatry: a scalable and customizable platform to empower data driven smartphone research,” JMIR Mental Health, vol. 3, no. 2, p. e16, 2016. [3]     D. C. Mohr, M. Zhang, and S. M. Schueller, “Personal sensing: under-standing mental health using ubiquitous sensors and machine learning,” Annu. Rev. Clin. Psychol., vol. 13, pp. 23–47, 2017. [4]     S. Santoshkumar, T. Salian, R. Shinde, and K. Kharatmol, “Psych Match: A Mental Health Tracker,” K.C. College of Engineering & Management Studies & Research, Thane, India. Available: https://kccemsr.edu.in [5]     S. P. R., B. K. G., S. M. J., S. H. N., and M. K. S., “Mental Health Tracker,” Int. J. Creative Research Thoughts, vol. 13, no. 5, 2025. Available: https://www.ijcrt.org/papers/IJCRT2505875.pdf [6]     N. Alias and N. Ibrahim, “Mental Health Journal and Mood Tracker System,” Applied Inf. Technol. Comput. Sci., vol. 6, no. 2, pp. 942–962, 2025. Available: https://penerbit.uthm.edu.my [7]     S. Aguilera and B. Muench, “There’s an app for that: Information technology applications for cognitive behavioral practitioners,” Behavior Therapist, vol. 35, no. 4, pp. 65–73, 2012. [8]     H. A. Wenze and M. E. Miller, “Use of ecological momentary assess-ment in mood disorders research,” Clin. Psychol. Rev., vol. 30, no. 6, pp. 794–804, 2010.