Inspiration
Wave Care was inspired by the lack of trust and innovation in mental health care diagnostics, particularly in communities like mine, where mental illness is stigmatized and dismissed. My mom’s struggles with untreated mental health issues, coupled with the high misdiagnosis rates for depression, motivated me to develop a solution that combines science and empathy. A simple experiment analyzing brainwave patterns during emotional stimuli sparked the idea of using EEG data and AI to build a tool that adds objectivity to depression diagnosis.
What it does
Wave Care is an AI-powered diagnostic aid that analyzes EEG data to identify depression susceptibility patterns. Using a convolutional neural network, it processes thousands of EEG image frames to predict whether someone is clinically depressed. The algorithm is distributed via API licensing, enabling seamless integration with existing EEG technology in hospitals and clinics. Wave Care provides a quantitative layer to complement traditional qualitative methods like the DSM-5.
How we built it
Wave Care started with research on EEG patterns and depression diagnostics. I developed a convolutional neural network that processes EEG data and iteratively tested it with a dataset of 1000+ patients. The API infrastructure was built to ensure compatibility with hospital systems. Input from psychiatrists, health tech experts, and hospital administrators informed the design and business model.
Challenges we ran into
Adapting complex EEG data into actionable insights required overcoming technical hurdles in AI training, such as addressing biases in datasets. Another major challenge was gaining trust from stakeholders in healthcare, a field often resistant to adopting new technologies. Additionally, refining the algorithm to achieve high accuracy while maintaining practicality for hospital use was a key focus.
Accomplishments that we're proud of
We’ve achieved an 89.5% accuracy rate in diagnosing depression, significantly outperforming the current industry standard. Furthermore, building partnerships with research institutes and gaining insights from leading psychiatrists and health tech professionals were significant milestones.
What we learned
This journey has taught me the importance of combining technical innovation with user-centered design. Listening to the needs of diverse stakeholders, from patients to psychiatrists, helped shape Wave Care into a tool that addresses real-world gaps. I also learned that change in healthcare requires persistence, collaboration, and a clear demonstration of value.
What's next for Wave Care
The next step is to pilot Wave Care in private clinics to demonstrate its efficacy and value to larger healthcare systems. Simultaneously, we will refine the algorithm, expand the dataset, and focus on regulatory approval to ensure the solution meets medical standards. In the long term, I aim to extend Wave Care’s capabilities to diagnose other mental health conditions and break stigma in communities worldwide.
Log in or sign up for Devpost to join the conversation.