Project Lead
Andrea Stocco, PhD (Department of Psychology, UW College of Arts & Sciences; UW Institute for Learning and Brain Sciences (I-Labs))
Collaborators
Thomas Grabowski, MD (Departments of Radiology and Neurology, UW School of Medicine; UW Medicine Memory and Brain Wellness Center)
Hedderik van Rijn, PhD (Department of Experimental Psychology, University of Groningen)
Project Summary
The most salient and debilitating aspect of dementia is memory loss. Unfortunately, memory loss is also the most difficult to quantify because it relies on doctor-administered tests that cannot be repeated very often. Without frequent and accurate measurements, it is difficult for clinicians to make reliable diagnoses, for patients and their caretakers to prepare in advance and for researchers to better understand the relationship between brain changes and cognitive decline.
This project will recruit 100 patients who are just beginning to experience memory loss as well as 100 healthy controls. Their memory function will be measured weekly through a brief, online test that can be accessed through any device and performed in less than 10 minutes. Data from the test will be fed to a computer model that simulates how fast memories fade in each patient’s brain, and the parameter that represents each patient’s speed of forgetting will be tracked over time. While the model simulates the patient, it also adapts the difficulty of the weekly task, ensuring it remains engaging but doable as memory declines.
The weekly estimates will provide the first, detailed trajectories of how fast memory declines over time in healthy aging and in different forms of dementia. The trajectory of the rate of forgetting will be used to analyze MRI data, producing precise associations between different types of memory loss and different types of brain damage.
Project Leads
Rebecca Hendrickson, MD, PhD (Department of Psychiatry and Behavioral Sciences, UW School of Medicine; VA Puget Sound Healthcare System)
John Oakley, MD, PhD (Department of Neurology, UW School of Medicine)
Collaborators
Aaron Bunnell, MD (Department of Rehabilitation Medicine, UW School of Medicine)
Catherine McCall, MD (Department of Psychiatry and Behavioral Sciences, UW School of Medicine; VA Puget Sound Healthcare System)
Kathleen Pagulayan, PhD (Department of Psychiatry and Behavioral Sciences, UW School of Medicine; VA Puget Sound Healthcare System)
Abigail Schindler, PhD (Department of Psychiatry and Behavioral Sciences, UW School of Medicine; VA Puget Sound Healthcare System)
Project Summary
After COVID infection, 10-50% of people experience persistent symptoms such as fatigue, palpitations, insomnia, cognitive problems, and headache – often with significant associated distress and functional impairment. The exact combination of symptoms varies from person to person, and it is expected that the specific causes vary from person to person as well.
Because of this variability, the current recommendation is for an evaluation by a multidisciplinary team. This creates a demand on our medical system that far outstrips current resources, and risks exposing patients to long, complex medical evaluations whose results are hard to interpret. In addition, clinical treatment trials that mix patients with similar symptoms but different underlying causes have high failure rates.
To address these challenges, we are testing an online platform to identify patients whose pattern of symptoms suggest a particular underlying cause that is common after certain physical and psychological stressors: increased adrenergic (adrenaline/noradrenaline) signaling in the brain and peripheral nervous system. We will pair this with a smaller number of detailed in-person assessments to validate our symptom-based measures and characterize associated biomarkers.
Our results will provide a detailed assessment of the patterns of symptoms caused by high amounts of adrenergic that are seen in persistent post-COVID syndrome, how they change over time and their association with objective measures of cognition and physiology. The project will provide the information needed to begin clinical treatment trials using existing, well-tolerated treatments that modulate adrenergic signaling. We hope the results will also have strong relevance to other stress- and trauma-related disorders such as chronic fatigue syndrome and fibromyalgia.
Project Lead
Caleb Stokes, MD, PhD (Department of Pediatrics, UW School of Medicine)
Collaborators
Michael Gale, Jr., PhD (Department of Immunology, UW School of Medicine)
Juliane Gust, MD, PhD (Department of Neurology, UW School of Medicine; Seattle Children’s Research Institute, Center for Integrative Brain Research)
Francisco Perez, MD, PhD (Department of Radiology, UW School of Medicine)
Project Summary
Infection by West Nile Virus can lead to encephalitis, or harmful inflammation of the brain. The immune system is critical for controlling viral replication and spread early in West Nile Virus infection, but persistent immune activation causes encephalitis that can result in brain damage even after the virus has been cleared. Recent pharmacologic advances have produced drugs that modulate the body’s immune response and can control inflammation, but these drugs have not yet been tested in conditions of viral encephalitis. In order for patients to benefit from these therapies, clinicians need tools that help identify when excessive immune activity is causing encephalitis.
The key innovation of this project is the combination of noninvasive imaging with novel immune modulating drugs to improve the diagnosis and treatment of encephalitis. Our central hypothesis is that specialized immune cells known as macrophages are key drivers of encephalitis in West Nile Virus infection, and that preventing their activation will preserve memory and other cognitive functions. Our studies will explore and develop noninvasive positron emission tomography (PET) imaging as a tool for diagnosing brain inflammation. We will test our hypothesis utilizing West Nile Virus infection of mice, which captures the key elements of human disease including encephalitis. This model allows us to evaluate existing diagnostic and therapeutic tools currently used in humans for other purposes, from which we will define new clinical applications. We will thus be poised to translate our findings to human studies defining and treating viral encephalitis.
Project Lead
Trevor Cohen, MBChB, PhD, FACMI (Department of Biomedical Informatics and Medical Education, UW School of Medicine)
Collaborator
Ellen Bradley, MD (UCSF Weill Institute for Neurosciences)
Benjamin Buck, PhD (Department of Psychiatry and Behavioral Sciences, UW School of Medicine)
Project Description
Schizophrenia is a debilitating mental health condition with high societal and personal costs, due largely to chronic difficulties with social and occupational functioning. While classical symptoms of schizophrenia – such as hearing voices – are often responsive to medication, people with schizophrenia also experience difficulties in social cognition, or understanding and interpreting the intentions and emotions of others. Social cognition affects the ability to function in society, and is a key determinant of real-world outcomes in schizophrenia.
Despite its importance, we lack objective and easy-to-deploy instruments to assess social cognition. This measurement gap presents a critical stumbling block for development of interventions to improve social cognition, because the effects of potential treatments cannot be assessed efficiently and at high resolution. Better measurements are also needed to identify individuals likely to benefit from such treatments and monitor treatment effects over time.
This project will develop innovative automated methods to measure a key component of social cognition – the ability to recognize the intentions and emotions of others. The underlying idea is to present a participant with a cue – such as a short video clip intended to be amusing – and then apply computational methods to their spoken response to see if it aligns with the intention behind the cue. The result will be a set of validated measurement tools to facilitate objective, repeatable, and scalable assessment of social cognition. These tools will accelerate our ability to rigorously test new treatments targeting these key deficits impacting people living with schizophrenia.
Project Lead
Trevor Cohen, MBChB, PhD, FACMI (Department of Biomedical Informatics and Medical Education, UW School of Medicine)
Collaborator
Dror Ben-Zeev, PhD (Department of Psychiatry and Behavioral Sciences, UW School of Medicine)
Project Description
Cognitive therapies help patients by providing ways to modify habitual but unproductive thought patterns, known as maladaptive thinking styles. Cognitive therapies are effective in treating depression, amongst other conditions, and are increasingly delivered remotely as text-based interventions. This trend toward digital delivery has accelerated on account of physical isolation and psychological stressors during the global pandemic. While this means cognitive therapy can potentially reach more patients, the effectiveness of this therapy depends on the ability of a skilled practitioner to recognize types of maladaptive thinking, and there is a critical shortage of mental health practitioners with this expertise.
In radiology, computer-aided diagnosis systems driven by artificial intelligence are used to help physicians detect signs of illness they may otherwise miss. In this project, we will develop a computer-aided detection system to support text-based cognitive therapy. To do so, we will identify indicators of maladaptive thinking styles within a set of text messages exchanged between clients and their therapists, and train neural networks to detect these indicators automatically. The resulting tools will provide a basis for an artificial intelligence-based decision support system to help clinicians recognize and manage maladaptive thinking styles that will enhance the quality and effectiveness of text-based cognitive therapy.
Project Lead
Sean Mooney, PhD, FACMI (Department of Biomedical Informatics and Medical Education, UW School of Medicine)
Collaborators
Thomas Grabowski, MD (Departments of Radiology and Neurology, UW School of Medicine; UW Medicine Memory and Brain Wellness Center)
Michael J. Persenaire, MD (Department of Neurology, UW School of Medicine; UW Medicine Memory and Brain Wellness Center)
Project Description
UW Medicine has amassed detailed patient treatment and business data in its electronic medical record (EMR). This information is a treasure trove that is not used to its full potential for two reasons: 1) For each clinical encounter, only a fraction of the information in the EMR is relevant, and virtually all of the information a clinician engages remains in a format that obscures patterns and trends; and 2) In groups of patients with the same illness, data from the EMR could be used to discern larger trends in the course of the disease or evaluate the effect of practice patterns on patient outcomes. The EMR currently does not provide a way to access this information in an agile way.
We have developed innovative software, “Leaf,” that allows medical providers to access population-based EMR data in real time. Leaf is now used at several academic medical centers nationally. In this project, we will collaborate with the UW Memory and Brain Wellness Center to design and evaluate “dashboards” that visualize how a patient’s history and trajectory compare to other, similar patients. For instance, daily function and cognitive testing data for a person with Alzheimer’s disease, already gathered over the course of several years, could be graphed and compared to the same information from all UW patients with Alzheimer’s disease. We will pilot these dashboards in Leaf and collect patient and provider feedback. We intend to publish our results and make code available as part of the open Leaf platform for rapid dissemination.
Project Lead
Amritha Bhat, MBBS, MD, MPH (Department of Psychiatry and Behavioral Sciences, UW School of Medicine)
Collaborators
Douglass Russell, MD (Department of Psychiatry and Behavioral Sciences, UW School of Medicine)
Committee for Children, Nurture Seattle
Project Description
Perinatal mood and anxiety disorders affect one in seven pregnant and postpartum women nationwide, making them the most common complication of pregnancy. Unfortunately, only one in 20 women who need treatment for these conditions actually receives it. This translates to a multigenerational issue, which can negatively affect the mother and child’s long-term physical, emotional and developmental health. It also means an estimated $14.2 billion annually in societal costs in the U.S. alone. While not every perinatal individual with mental health concerns has access to a mental health provider, cell phones and text messaging are ubiquitous. Nonjudgmental support delivered through text messaging may be a low cost approach to reaching women who need emotional support in the perinatal period.
Our project aims to evaluate a text-based mentoring program, the Nurture Program, and assess whether it is possible to support mothers through their third trimester of pregnancy and nine months postpartum and enhance their emotional well-being. The Nurture Program combines the convenience of secure text messaging with the personalization of having a trained peer mentor with whom the mother can develop a trusting relationship. This program also provides resources on child development, connections to local support agencies and suggestions for parent-child bonding and parental wellness activities. Surveyed participants of the Nurture Program consistently report their mentor helped them feel less stressed and more confident in their role as a parent. This study will allow us to measure the impact of this cost-effective approach to promoting perinatal emotional well-being.
Project Lead
Katherine Anne (Kate) Comtois, PhD, MPH (Department of Psychiatry and Behavioral Sciences, UW School of Medicine)
Collaborators
Trevor Cohen, MBChB, PhD, FACMI (Department of Biomedical Informatics and Medical Education, UW School of Medicine)
Andrea Hartzler, PhD (Department of Biomedical Informatics and Medical Education, UW School of Medicine)
Bill Lober, MD, MS (Department of Biobehavioral Nursing and Heath Informatics, UW School of Nursing; Department of Biomedical Informatics and Medical Education, UW School of Medicine; Department of Global Health, UW School of Public Health)
Project Description
On top of climate change, political divisiveness and cultural turbulence, we have faced the most devastating pandemic since global influenza 100 years ago. The resulting social and economic stresses have manifested as widespread anxiety, a worsening opioid epidemic and the highest suicide rates in decades.
Proven behavioral health strategies like Caring Contacts offer hope. Caring Contacts is a program where suicidal individuals receive periodic letters or text messages from a behavioral health practitioner, creating a connection and showing someone cares. Caring Contacts have reduced suicide deaths, attempts and thoughts of suicide and offer an easy re-connection to healthcare, but behavioral health practitioners are in high demand and short supply and often struggle with prioritizing messages and sending timely replies. By analyzing a patient’s text messages, computerized algorithms can identify indicators of risk and other important information to help behavioral health practitioners with the nature and timing of their responses, allowing one behavioral health practitioner to reach hundreds of suicidal patients.
This project brings together behavioral health care, mobile technologies that people now expect and innovative methods to identify critical signs of suicide risk that busy practitioners may miss. Our team consists of experts in behavioral health, usability and design, artificial intelligence/natural language processing, software engineering, health care information systems and emergency medicine. Our goal is simple: to use technology to provide critical support for those in crisis, and to save lives.
Project Lead
Jennifer Erickson, DO, FAPA (Department of Psychiatry and Behavioral Sciences, UW School of Medicine)
Collaborators
Charles Bombardier, PhD (Department of Rehabilitation Medicine, UW School of Medicine)
Jesse Fann, MD, MPH (Department of Psychiatry and Behavioral Sciences, UW School of Medicine)
Cherry Junn, MD (Department of Rehabilitation Medicine, UW School of Medicine)
Cara Towle, RN, MSN (Department of Psychiatry and Behavioral Sciences, UW School of Medicine)
Project Description
Traumatic brain injury (TBI) is a major cause of disability in Washington state and throughout the US. TBI increases the risk and complexity of multiple behavioral health conditions including post traumatic stress disorder, depression, anxiety, irritability, anger/aggression, substance misuse and cognitive impairment. In addition, TBI impairs a person’s ability to manage their health care and increases the risk of unemployment, long-term functional impairment, and caregiver burnout. Successful TBI recovery can depend in large part on access to and engagement in behavioral health treatment. Unfortunately, TBI-focused community resources are scarce and fragmented. Treatment of post-TBI symptoms often falls to community providers who have little support and are under-prepared to manage these complexities. This burden disproportionally affects rural providers who have little access to specialist care at academic centers.
The purpose of this project is to create and assess the use of the ECHO (Extension for Community Healthcare Outcomes) model to provide education and support by experienced TBI experts to community providers who treat persons with TBI. The ECHO model uses both a virtual educational lecture series and patient case discussion to improve provider preparedness to treat patients and improve patient outcomes. We will launch a monthly to bi-monthly program that will train providers from a variety of disciplines and settings in identification and evidence-based behavioral health treatments, web technologies and mobile technologies, and provide detailed case consultation. We will assess the success, reach and impact of our TBI ECHO by collecting and comparing attendee experiences, clinical information and patient outcomes.
Project Leads
Chieh (Sunny) Cheng, RN, PhD (Nursing and Healthcare Leadership, School of Nursing, UW Tacoma)
Sarah Kopelovich, PhD (Department of Psychiatry and Behavioral Sciences, UW School of Medicine)
Collaborator
Dong Si, PhD (Division of Computing & Software Systems, School of Science, Technology, Engineering & Mathematics, UW Bothell)
Project Description
The World Health Organization ranks psychotic disorders as the third most disabling health condition worldwide. Eleven million Americans will experience psychosis during their lifetime, and roughly 60 million Americans have a loved one affected by psychosis. Research affirms that psychotherapeutic interventions can help family caregivers develop skills to better connect and communicate with their loved one, which corresponds to better treatment engagement, symptom improvement, fewer hospitalizations, improved functioning, reduced substance use, reduced mortality and overall improvement in quality of life for the individual with psychosis. Family interventions are therefore critical to a holistic and effective clinical response to a psychotic disorder. Nevertheless, a recent federal investigation found that fewer than 2% of US families caring for someone with psychosis had received a family intervention for psychosis.
Psychosis REACH (Recovery by Enabling Adult Carers at Home) is a family intervention for psychosis co-developed by faculty in the UW Department of Psychiatry and Behavioral Sciences that delivers psychoeducation and illness management skills training to family caregivers in the community. To enhance broad and equitable access to tens of millions of family and caregivers, this project will develop “Psychosis iREACH,” a digital platform that uses Artificial Intelligence (AI) technology to deliver Psychosis REACH to diverse families navigating psychosis. A virtual coach will assist families to access self-management skills practice, automated self-assessment, tailored training goals and individualized learning trajectories whenever and wherever families need the support. Psychosis iREACH represents a multidisciplinary collaboration among faculty in the School of Medicine, School of Nursing and School of Science, Technology, Engineering & Mathematics.
Project Lead
Dror Ben-Zeev, PhD (Department of Psychiatry and Behavioral Sciences, UW School of Medicine)
Collaborators
Allie Franklin, LICSW (UW Medicine Behavioral Health Institute at Harborview Medical Center)
Jessica Maura, PhD (Department of Psychiatry and Behavioral Sciences, UW School of Medicine)
Nami Bhatt, LMHC (Specialized Treatment for Early Psychosis (STEP) Program, Harborview Medical Center)
Project Description
Psychotic disorders are brain illnesses that increase individuals’ risk for hospitalizations, substance use, homelessness, victimization and suicide. Significant declines in functioning occur during the first years of psychotic illness, a phase called early psychosis. Time-sensitive treatment can mitigate the negative outcomes of these conditions, in some cases leading to partial or full recovery. However, young adults are particularly reluctant to seek services or engage in traditional clinic-based care. Novel approaches are needed to successfully reach this critically vulnerable population, in time.
The vast majority of young adults with early psychosis own mobile phones, identify texting as their preferred communication modality, and report an interest in messaging-based treatments. We developed a texting intervention for people with psychosis called the Mobile Interventionist. Treatment is conducted via daily recovery-oriented text conversations between patients and a trained messaging practitioner. This novel form of engagement produces an asynchronous but continuous form of treatment and combines the advantages of digital health (i.e., accessibility, reach beyond the brick-and-mortar clinic, low intensity), with the flexibility, personal tone and sensitivity of a clinician. Several studies have demonstrated that our texting intervention approach is feasible, acceptable, engaging and effective. This initiative will help translate this promising research into real-world clinical practice by implementing the Mobile Interventionist texting model at the University of Washington’s Specialized Treatment Program for Early Psychosis (STEP).
Clinically, the intervention may improve the illness management of young adults with early psychosis participating in the pilot, improving their long-term trajectories. Programmatically, the pilot bridges the research/practice gap by providing training and guided clinical experience to a real-world clinical team.
Project Lead
Linda Shapiro, PhD (Paul G. Allen School of Computer Science & Engineering and Department of Electrical and Computer Engineering, UW College of Engineering)
Collaborators
Thomas Grabowski, MD (Departments of Radiology and Neurology, School of Medicine; UW Medicine Memory and Brain Wellness Center)
Sheng Wang, PhD (Paul G. Allen School of Computer Science & Engineering, UW College of Engineering)
Project Description
Alzheimer’s Disease (AD) is a degenerative condition that affected 5.8 million seniors in 2020 and is the sixth leading cause of death in the United States. Detecting mild cognitive impairment, often a precursor to AD, and predicting its advance to AD dementia are key clinical diagnostic problems. Early diagnosis can motivate early intervention with lifestyle changes that build cognitive reserve or reduce comorbidity and thus prolong functional independence. MRI scans and specialized tests for AD-related proteins in spinal fluid or on PET brain scans are available, but it is not known how best to deploy these expensive tests or combine the information from them. New computer-based “machine learning” software tools may provide a solution to these problems.
This project will explore the use of a machine learning technology called deep learning to diagnose the stage of AD and to predict its progression. We will use the data available from the scientifically open Alzheimer’s Disease Neuroimaging Initiative (ADNI) database, which contains MRI, PET, risk genes, cerebrospinal fluid and other data. We will develop a deep learning model that performs its predictions using MRI data alone, and can also augment the MRI data with the other datatypes for improved performance at some expense. Our modern machine-learning methods are designed to be rationally factored in with other individualized clinical information to aid clinicians in these vital diagnostic decisions.
Project Lead
Tim Althoff, PhD (Paul G. Allen School of Computer Science & Engineering, UW College of Engineering)
Collaborators
David Atkins, PhD (Department of Psychiatry and Behavioral Sciences, UW School of Medicine)
Adam Miner, PsyD, MS (Psychiatry and Behavioral Sciences, School of Medicine, Stanford University)
Project Description
Millions of people lack access to mental health treatment due to barriers such as limited therapist availability, long wait times, high cost, and stigma. The COVID-19 pandemic has problematically increased demand for treatment while decreasing access. Because the internet is widely available, many people first turn to the internet for mental health support, giving rise to massive online psychotherapy, counseling and peer-to-peer support platforms such as Ginger and Talklife. However, not all conversations lead to improvement and may miss opportunities to help or even make things worse as platforms struggle to keep up with the increasing demands and lack methods for evaluating and promoting high-quality conversations.
This project seeks to improve the quality and scalability of online mental health support through real-time, evidence-based conversation feedback. We will leverage and analyze datasets of support interactions and associated outcomes across millions of individuals that use the partnering online mental health platforms at Ginger and Talklife. Our goal is to develop and pilot-test artificial intelligence methods that provide supporters on these platforms with practical just-in-time feedback and training. If successful, at least three benefits will follow our work. First, millions of help seekers using partnering mental health platforms Ginger and Talklife will receive higher quality responses through, for example, an expression of higher empathy. Second, those providing help will gain expertise faster and with less distress. Third, platforms and researchers will discover conversational best practices which can then be used to improve helper training and quality evaluation.