Vital signs for psychosis: personalized, always-on markers from speech and language
Official title: Vital Signs for Psychosis: Personalized Longitudinal Markers of Psychosis Severity Using Automated Speech and Language Analysis
Funded at Feinstein Institute for Medical Research · NIH-11378668 · Data updated 2026-11-12
A patient-friendly approach to using speech and language cues to measure psychosis severity over time, so clinicians can tailor care.
Quick facts
| Grant type | R01 grant |
|---|---|
| Study type | NIH-funded research |
| Funding institution | Feinstein Institute for Medical Research NIH-funded |
| Lab location | 1 site (Manhasset, United States) |
| Project start | August 1, 2025 |
| Project end | May 31, 2030 |
| Funding year | 2026 |
| Award (this year) | $817,859 |
| NIH project number | 5R01MH140013-02 |
| Project ID | NIH-11378668 on NIH RePORTER |
Who could benefit from this research
✓Could help
Adults with psychosis or related conditions who can participate in regular follow-up assessments over time.
✕Less likely to help
People who cannot participate in repeated follow-up assessments or have conditions that prevent reliable speech analysis may not benefit.
What this research studies
This project aims to create a low-cost, low-burden way to track psychosis severity using automated analysis of how people speak and what they say. It will adapt advanced models to each person, using repeated measurements over a year to produce personalized “vital signs” of illness. The team will first learn from a large, existing set of speech data from people with psychosis and related conditions, then test four deep-learning strategies in 100 participants over 15–50 timepoints. If successful, this could provide clinicians with actionable, ongoing markers to guide treatment decisions. Participation would involve regular assessments and speaking tasks as part of standard clinical follow-up.
Why it matters
Potential benefit: If successful, patients could receive more timely and personalized care based on objective markers of their psychosis.
How similar studies have gone: Previous work suggests speech and language features can relate to psychosis severity, but this project focuses on personalized, repeated-measures models to enable clinical use.
Where this research is happening
-
Feinstein Institute for Medical Research
Manhasset, United States Active
Researchers
- Principal investigator: Tang, Sunny Xiaojing — Feinstein Institute for Medical Research
- Study coordinator: Tang, Sunny Xiaojing
Related research
Other NIH-funded projects on the same topics.
-
Using language analysis to understand disorganized speech in psychosis
This study is looking at how to better understand and measure disorganized speech in people with psychosis, like schizophrenia and mood disorders, by using advanced computer techniques to analyze their speech, which could help doctors predict how well treatments are working and the risk of relapse.
-
Silent speech interface using a wearable tongue tracker to help people after laryngectomy communicate
A wearable system with tongue sensors and intraoral components aims to let people without a vocal cord use natural-sounding speech in daily life.
-
Overlap between how we speak and how we hold words in memory
A Duke-led project studies how the brain that talks relates to keeping verbal information in working memory, using advanced brain recordings from patients already undergoing medical care.
-
Psychosis in diverse settings across the world
This project studies how psychotic disorders show up and respond to treatment in adults with diverse backgrounds, including populations in Africa, the Caribbean, and other Global South settings.
-
Psychosis in Diverse Settings: Understanding Symptoms and Treatment Across Global South
A human-facing study will look at how psychotic disorders present and respond to treatment in adults from Africa, the Caribbean, and other Global South settings, using genetic and clinical data.
-
A new online brain-scan-style tool to spot early psychosis risk
A new online-based set of tasks and a computer model aims to identify people at high risk for developing psychosis earlier and more accurately.
About this research
- This is an active NIH-funded research project — typically early-stage science, not a clinical trial accepting patient enrollment.
- Some NIH-funded labs run parallel clinical studies or seek volunteers for related work. To check, contact the principal investigator or institution listed above.
- For full project details, budget, and progress reports, visit the official NIH RePORTER page.