Toggle utilizes Comp Cog AI, a machine learning-based assessment tool that predicts anxiety, depression, and suicidal planning through a three-minute image-based survey. This technology enables organizations to efficiently identify mental health challenges, ensuring timely intervention for individuals in need of care.
Funding
Funding not disclosed
Founders
Product
Problem
Current methods for assessing mental health, such as anxiety, depression, and suicidal planning, often require extensive questionnaires and clinical evaluations, which can be time-consuming and costly. These traditional approaches may also be susceptible to manipulation, leading to inaccurate results and delayed interventions.
Solution
ToggleAI offers a machine learning-based assessment tool that predicts the likelihood of anxiety, depression, and suicidal planning through a brief, image-based survey. The platform leverages Comp Cog AI, a proprietary technology that combines computational cognition with machine learning to analyze a user's responses to images. This approach provides a rapid and cost-effective method for identifying individuals at risk, enabling organizations to proactively offer support and resources. The digital experience consists of a picture rating survey accessible via mobile or web, and a web portal for administrators to review and assess results.
Target Audience
ToggleAI primarily serves organizations and institutions seeking to efficiently identify mental health challenges among their members, including healthcare providers, educational institutions, and employers.
Features
- Three-minute image-based survey for rapid mental health assessment
- Comp Cog AI technology combining computational cognition and machine learning
- Prediction of anxiety, depression, and suicidal planning
- Accuracy range of 75-95% across conditions, based on peer-reviewed findings
- Resistance to manipulation and gaming, ensuring repeatable results
- Web portal for administrators to review and assess results
- Cloud-based infrastructure for cost-effective and scalable deployment