Clinical Application Flow
The following diagram illustrates how our emotion-aware AI system maintains conversational context and emotional understanding across multiple patient interactions, ensuring continuity of care even when different healthcare providers handle successive sessions.
Key components include the Hippocampal Module for memory encoding and retrieval, the Emotion Module for real-time emotion recognition, and the Clinical Decision Support system that provides relevant patient insights to healthcare providers.
Research Focus Areas
Emotion Recognition in Clinical Settings
Developing algorithms to identify emotional states from voice patterns and text in healthcare conversations, with emphasis on privacy and clinical accuracy.
Long-Term Memory Architecture
Creating AI systems that can retain and appropriately recall patient information across sessions while maintaining data privacy and security.
Clinical Decision Support
Researching how AI can provide relevant patient history and insights to healthcare providers in real-time during consultations.
Human-AI Collaboration
Studying optimal interaction patterns between healthcare professionals and AI assistants to enhance rather than replace human care.
Research Outputs
Project Status
The project is currently in the active research and development phase. Our team is working on core algorithm development, with initial prototypes undergoing internal testing. We are collaborating closely with Fraser Health clinicians to ensure our research aligns with real-world healthcare needs.
Next steps include expanded testing with anonymized data, refinement of emotion recognition models, and preparation for clinical pilot studies pending ethics approval.