EmpathiCare

Inspiration In the healthcare industry, professionals often confront emotionally charged situations demanding a delicate and empathetic response. The challenge lies in providing sufficient emotional training for healthcare providers. Our inspiration arises from the imperative need to bridge this gap by introducing a tool that simulates emotionally challenging scenarios, ultimately enhancing the emotional intelligence of healthcare providers.

What it does Our tool immerses healthcare providers in emotionally difficult situations, scrutinizing their reactions to predefined prompts. Utilizing a pre-trained VGGNET19 model from Hugging Face, we implemented a facial expression classifier to discern the emotion and intensity conveyed by the healthcare provider. Additionally, by analyzing facial expressions and transcripts, we generate remarks on the response. The tool incorporates a time-series analysis, providing insights into the evolving emotional responses. Finally, the ChatGPT plugin is employed to present cohesive reports with charts and timestamps, highlighting instances when the healthcare provider's response may have been inappropriate.

How we built it We harnessed the power of the VGGNET19 model from Hugging Face for facial expression classification. Leveraging Intel's cloud infrastructure, we efficiently prototyped and trained our model. The tool adopts a time-series approach to capture the dynamic nature of emotional reactions, ensuring a comprehensive and accurate analysis.

Challenges we ran into Our journey was marked by several challenges. Initial stages involved extensive research to identify a compelling and useful idea. We faced difficulties in selecting the most suitable model for face detection, and choosing the right model for initial detection posed an additional challenge.

Accomplishments that we're proud of We successfully developed a viable beta version of our emotional training tool. Our sense of accomplishment extends to the effective utilization of Intel's cloud infrastructure for prototyping and model training, significantly enhancing the tool's efficiency and scalability.

What we learned The development process imparted valuable lessons, emphasizing the critical role of meticulous model selection, particularly in emotionally nuanced applications. The challenges we encountered strengthened our problem-solving skills and underscored the importance of thorough research.

What's next for Empathicare Our future plans involve refining the existing model to enhance accuracy and incorporating additional features for a more comprehensive training experience. We aspire to create a robust and user-friendly tool that makes a substantial contribution to the emotional training of healthcare providers.