Patents

Modality.AI's IP portfolio fortifies its leadership in CNS trial AI, emphasizing multimodal endpoint generation. 

US Patent No. 12,300,277 (May 2025):
Customizing Computer Generated Dialog for Different Pathologies

The patent describes a new method for customizing computer-generated dialog sessions to improve interaction for users with speech pathologies, such as dysarthria.  Recognizing that standard dialog systems often struggle with the unique characteristics of disordered speech; this invention focuses on adapting the system's voice activity detection (VAD) to better understand when a user is speaking by identifying spans of speech and non-speech in the user's audio and then adjusting specific configurable parameters. By making the dialog system more sensitive and accurate for users with speech impairments, this method aims to significantly enhance the effectiveness of automated remote monitoring and assessment tools.

US Patent No. 12,412,668 (September 2025):
Interpretable Index Score for Combining Multimodal Metrics for Remote Monitoring of Condition Progression

This patent covers novel methods for processing and analyzing speech and multimodal interactions, including the computation of interpretable index scores for the purposes of remote assessment of neurological and mental conditions. Key elements include: Techniques for detecting and evaluating speech, facial and behavioral signals captured over cloud-based multimodal conversations with a virtual human guide; Systems that combine multiple input channels for improved context awareness; and Methods to combine measures computed from multiple modalities of health information into a single, interpretable score for further analyses, actions and downstream processing.

US Patent No. 12,444,505 (October 2025):
Multimodal Metrics for Remote Monitoring of Condition Progression

The patent protects methods and systems that advance automated, real-time analysis of human performance in guided interactions, work that underpins our virtual-guide approach. These automated, guided evaluations help transform subjective observations into quantifiable, repeatable measures that improve consistency and sensitivity in clinical trials.

US Patent No. 12,521,051 (January 2025):
Multimodal Investigation of Speech, Text, Cognitive and Facial Video Features for Characterizing Depression With and Without Medication

The patent protects a system for remotely determining the potential presence of depression in a user. The system includes a virtual agent that administers one or more tasks to the user. The user performs the tasks and the performance is captured by a camera. The captured audiovisual data is sent to a server that derives objective metrics which are then applied to a classifying algorithm. 

.  .  .