AI system for optimization of mental health care

This technology is a web-based AI system which uses real-time speaker diarization, transcription, and natural language processing (NLP) to optimize and support mental health care services.

Unmet Need: Diagnostic and patient monitoring assistance for mental health care providers

Current methods for the diagnosis and monitoring of psychiatric illness like psychotherapy, are limited by healthcare practitioners availability and provider/patient relationship. Treatment plans and outcomes are also determined using self-reported measures and therapists’ notes, which may vary between individuals and incorporate bias. There is a need for an efficient AI mental health care support that is not limited by extensive pre-training and preliminary voice registration requirements.

The Technology: An AI-based natural language processing (NLP) toolkit for optimizing psychotherapy

This technology is a cluster of machine-learning-based frameworks used to process and analyze verbal input from psychotherapy sessions and provide recommendations to mental health care providers. This web-based system can perform speaker diarization and transcription in real-time without pre-training, monitor patient health, and provide real-time feedback and treatment strategies for healthcare providers. It also offers an AI-assisted organizational system to log and brainstorm information, and a visual interactive dashboard for psychotherapy session, making it a valuable tool for mental health support.

Applications:

• Psychiatric support platform for diagnosis, monitoring, prevention
• Research and education tool for mental health practitioners
• Improved voice command, teleconferencing, and transcription systems
• Support platform for schools and customer service systems

Advantages:

• No pre-training required and real-time registration
• Provides feedback to providers
• Web-based
• Unbiased

Lead Inventor:

Baihan Lin

Patent Information:

Patent Pending (US 20230320642)

Related Publications:

• Toleubay Y, Agravante DJ, Kimura D, Lin B, Bouneffouf D, Tatsubori M. “Utterance Classification with Logical Neural Network: Explainable AI for Mental Disorder Diagnosis.” arXiv. 2023 Jun 6.

• Lin B, Cecchi G, Bouneffouf. “Psychotherapy AI companion with reinforcement learning recommendations and interpretable policy dynamics.” WWW '23 Companion: Companion Proceedings of the ACM Web Conference 2023. 2023 Apr 30: 932-939.

• Lin B, Bouneffouf D, Cecchi G. “Neural Topic Modeling of Psychotherapy Sessions.” arXiv. 2022 Apr 13.

• Lin B, Zhang X. “Speaker diarization as a fully online bandit learning problem in MiniVox.” Proceedings of The 13th Asian Conference on Machine Learning, PMLR. 2021; 157: 1660-1674.

Tech Ventures Reference:

• IR CU22109, CU22237, CU22238, CU22239, CU22270, CU23008, CU23291

• Licensing Contact: Beth Kauderer