SBIR Phase I: An intelligent mental health care companion for kids

Award ID: 2112093

The broader impact/commercial potential of this Small Business Innovation Research (SBIR) Phase I project is to proactively identify and resolve mental health issues for children ages 10 - 18 before treatments and consequences become more acute and significantly more costly. This project innovation proposes bringing care to children at the onset of need using chatbot companions tailored deliberately and precisely to each childs mental healthcare needs. Optionally, a child can be paired with live chat therapists and coaches no matter where the child is at home, school, or when on their own. The system leverages proven mobile device-accessed Cognitive Behavioral Therapies in tandem with machine learning (ML)-enabled technologies that learn from a variety of interactions with the child to detect and digitally triage their experiences of loneliness, anger, anxiety, and depression and to alert adults when intervention and treatment are deemed necessary. Without appropriate care, these symptoms frequently increase in severity over time and become more difficult to treat. Intervening early can help slow or halt mental illness, reducing for parents, schools, and society the practical and financial burdens associated with reactive, generalized mental healthcare treatments while nurturing children into happier, healthier adults. This Small Business Innovation Research (SBIR) Phase I project seeks to build a system to determine the nature and severity of a childs mental health needs through real-time, early detection. Research reveals children face more barriers than adults when obtaining mental healthcare, especially in rural, marginalized, and low-socioeconomic-status communities. Due to a severe shortage of child behavioral health practitioners across the country, children frequently wait up to a decade between the onset of mental health symptoms and treatment. This project seeks to eliminate the delay between when children first experience mental or emotional needs and when they receive appropriate care, ensuring they flourishnot flounderduring those crucial developmental years. Leveraging ML algorithms and proprietary question weighting, the project focuses on: 1) algorithm development to determine the most effective combination of chatbot and live chat counselor engagements to understand a childs immediate issues and provide resolutions for the child and their parent(s); 2) improvements to ensure the responses are fit for purpose, recognizing and flagging appropriate conversations for human interaction; and 3) refining the frequency and content of notifications; such as, adaptive motivational messages and recommendations to counselors for tailoring interactions. This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.

NSF Program Director: Alastair Monk