Abstract
Traditional screening for conditions such as neurological disorders, respiratory diseases, and mental health issues often relies on manual assessments that can be time-consuming and expensive. Many conditions are frequently only identified after significant progression. This disclosure describes a method for automated health screening through the analysis of acoustic biomarkers within conversational interfaces. Voice samples are captured during natural interactions (with prior consent) or through specific user prompts requesting this and are processed by artificial intelligence models to identify vocal patterns associated with various medical conditions. The analysis may be performed on-demand or through continuous monitoring of voice data across multiple communication platforms. This technology enables large-scale, non-invasive screening, allowing for earlier detection and providing objective data to assist in determining when professional medical consultation is necessary.
Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 License.
Recommended Citation
Clancy, Molly, "Automated Acoustic Biomarker Analysis for Health Condition Screening in Conversational Interfaces", Technical Disclosure Commons, ()
https://www.tdcommons.org/dpubs_series/9928