Developing Data-Driven Clinical Signatures For People Who Experience Hallucinations
This multi-year project is funded by a $12.6 Million grant award from the National Institute of Mental Health (NIMH). The study is a collaboration between the University of Washington, University of Minnesota, and Louisiana State.
Our multidisciplinary team is collecting data from a large sample of people who experience hallucinations in all 50 U.S. States using an array of smartphone behavioral measurement tools: audio diaries, self-reports, and performance-based cognitive tests. With the aid of artificial intelligence and novel computational modelling strategies, our team aims to derive data-driven clinical signatures to predict individual differences in severe negative outcomes; identify and mitigate bias in modelling across groups defined by race, sex, and age; examine whether adding smartphone- captured behavioral data to information that is typically available in the clinical record improves model clinical utility; and produce machine learning-ready data structures that adhere to FAIR (Findable, Accessible, Interoperable, Reusable) principles.
If successful, these measures and models can be used to guide scalable clinical decision making, resource allocation, treatment, and impactful prevention efforts.
Learn more here: Project Description
Digital Phenotyping
Dror Ben-Zeev, PhD
Department of Psychiatry and Behavioral Sciences, University of Washington
​
Trevor Cohen, PhD
Department of Psychiatry and Behavioral Sciences, University of Washington
​
Justin Tauscher, PhD
Department of Psychiatry and Behavioral Sciences, University of Washington
​
Anna Larsen, PhD
Department of Psychiatry and Behavioral Sciences, University of Washington
​
Benjamin Buck, PhD
Department of Psychiatry and Behavioral Sciences, University of Washington
​
Alexa Beaulieu, MPH
Department of Psychiatry and Behavioral Sciences, University of Washington
​
Arya Kadakia, BA
Department of Psychiatry and Behavioral Sciences, University of Washington
​
Sitara Marin, LMHCA
Department of Psychiatry and Behavioral Sciences, University of Washington
​
Ella DeVries, BA
Department of Psychiatry and Behavioral Sciences, University of Washington
Mobile RDoC​
​
Auditory Verbal Hallucinations (AVH) occur in the context of a range of mental health conditions as well as in individuals who are otherwise considered healthy. AVH lead to significant distress, impairment, and need for care in some, but not others.
The RDoC framework is ideally suited to better understand the phenomenology of AVH as they may be part of a continuum of psychotic experience ranging from “normal” to pathological. Building on the principles of the RDoC framework, this project focuses on AVH as part of the broader construct of Auditory Perception and leverages an integrative multi-method paradigm leveraging measures from two RDoC units of analysis: Self-Report and Behavior.
​
Our multidisciplinary investigative team is using integrated mobile data collection techniques piloted extensively (Ecological Momentary Assessment for self-report and automated multi-modal sensing to capture behavior) to study AVH experience and associated behaviors, as they occur in real-time/real-place in people with and without need for care.
​
Funding by: National Institute of Mental Health
​
​
Persecutory Ideation
​
Persecutory ideation (PI), or a continuum of thoughts related to harm from others, is elevated in a range of psychiatric conditions and in up to 20% of the general population. These thoughts can range from slightly elevated concerns about threats, to the distressing and disruptive delusions that are common in schizophrenia-spectrum disorders.
​
Recent developments in mobile technology allow – for the first time – a real-time, real-place window into the dynamic emergence of PI. The project will remotely recruit 200 individuals with clinically significant persecutory ideation to engage with an integrated mobile health assessment system combining brief self-report and passive sensors for one month. The research team will explore these data to identify potential factors associated with PI emergence, maintenance, and exacerbation as well as potential targets for intervention development. Recruiting individuals remotely also provides the opportunity to compare individuals with PI who seek treatment to those who do not, examining potential demographics, clinical characteristics, or beliefs that determine help-seeking in this population.
​
Funding by: National Institute of Mental Health and the Brain and Behavior Foundation NARSAD Young Investigator Award to Dr. Ben Buck.
​
​