MindCheck

I developed MindCheck as my individual final-year project to support early mental health screening for teenagers using the SRQ-20 questionnaire and an Artificial Neural Network. I built an integrated mobile application that provides AI-based screening results and educational content, with guidance from a psychologist to ensure responsible result interpretation.

The main challenge was turning questionnaire data into meaningful screening information without presenting the results as a medical diagnosis. This required both technical implementation and careful consideration of how users would interpret the information.

I built a Flutter application that guides users through the SRQ-20 questionnaire and sends their responses to a Flask backend for analysis using an Artificial Neural Network with Backpropagation. The application presents screening results, detected symptom categories, educational content, and examination history. I also worked with a psychologist to review the content and interpretation of the screening results.

I independently handled system design, Flutter development, Flask API integration, MySQL database management, and ANN implementation. I also worked with a psychologist to review the screening content and result interpretation.

• Flutter
• Dart
• Python
• Flask
• MySQL
• Artificial Neural Network
• Backpropagation

• Interactive SRQ-20 questionnaire
• Initial mental health screening results
• Mental health symptom analysis
• Mental health educational content
• User screening history
• Artificial Neural Network with Backpropagation

I designed the screening flow, developed the mobile interface and backend, then trained, evaluated, and integrated the ANN model. I tested the application and reviewed the screening content with a psychologist.

Transitioning from rule-based logic to ANN required me to learn dataset preparation, model training, and API integration. Another important challenge was presenting the screening results clearly and responsibly, which I addressed by seeking validation and feedback from a psychologist.

This project strengthened my understanding of end-to-end mobile development and the practical integration of machine learning into an application. I learned how to prepare and evaluate an ANN model, connect different technologies, and translate technical outputs into understandable user experiences. It also taught me the importance of domain-expert feedback, responsible AI implementation, and approaching unfamiliar technical challenges through independent learning.