Mental Health Prediction via Conversational Speech Analysis
Summary
USPTO published patent application US20260100259A1 by Ellipsis Health, Inc. covering systems and methods for identifying mental health condition severity through passive processing of conversational speech and language. The application discloses language models and acoustic models that process conversation data to generate outputs for mental health assessment, as well as methods for tracking analytics on self-report questionnaires administered during conversations.
What changed
USPTO published a patent application for mental health detection technology that processes conversational speech and language data using language models and acoustic models. The application covers systems that listen to human-to-human conversations, generate model outputs for assessing mental health condition severity, and track self-report questionnaire analytics.
For technology companies developing mental health assessment tools, this patent application indicates potential future intellectual property considerations in speech-based mental health analysis. Healthcare providers utilizing or considering conversational AI tools for mental health screening should be aware of emerging IP in this space.
What to do next
- Monitor for updates
Archived snapshot
Apr 10, 2026GovPing captured this document from the original source. If the source has since changed or been removed, this is the text as it existed at that time.
SYSTEMS AND METHODS FOR PREDICTING MENTAL HEALTH CONDITIONS BASED ON PASSIVE PROCESSING OF CONVERSATIONAL SPEECH AND LANGUAGE
Application US20260100259A1 Kind: A1 Apr 09, 2026
Assignee
Ellipsis Health, Inc.
Inventors
Elizabeth Shriberg, Piotr Chlebek, Tomasz Rutowski, Amirhossein Haratinejadtorbati, Michael Aratow, Mainul Mondal, Melissa McCool, Vaishnavi Narayanan, Ishani Tagore, Yang Lu, Tulio Goulart, Robert Rozanski
Abstract
Described herein are systems and methods for identifying the severity of a mental health condition or symptoms of same by listening to a human-to-human conversation by receiving conversation data, processing the conversation data to generate a language model output and/or an acoustic model output using one or more language models and/or acoustic models. Further described herein are systems and methods for automatically tracking and providing analytics on self-report questionnaires administered during the conversation.
CPC Classifications
G16H 15/00 G10L 15/16 G16H 20/00 G16H 40/67
Filing Date
2025-12-12
Application No.
19417870
Related changes
Get daily alerts for USPTO Patent Applications - Health Informatics (G16H)
Daily digest delivered to your inbox.
Free. Unsubscribe anytime.
Source
About this page
Every important government, regulator, and court update from around the world. One place. Real-time. Free. Our mission
Source document text, dates, docket IDs, and authority are extracted directly from USPTO.
The summary, classification, recommended actions, deadlines, and penalty information are AI-generated from the original text and may contain errors. Always verify against the source document.
Classification
Who this affects
Taxonomy
Browse Categories
Get alerts for this source
We'll email you when USPTO Patent Applications - Health Informatics (G16H) publishes new changes.
Subscribed!
Optional. Filters your digest to exactly the updates that matter to you.