Winter 2025 pilot awardees report mid-project progress in their research

Optimizing the Population Impact and Equity of Collaborative Care Delivery: Evaluation of the Collaborative Care Fidelity Checklist

Investigators
Anna Ratzliff, Department of Psychiatry & Behavioral Sciences
Elizabeth Austin, Department of Health Systems and Population Health
Brittany Blanchard, Department of Psychiatry & Behavioral Sciences

Project update
The Collaborative Care Model (CoCM) is an integrated population health approach for addressing mental health in general healthcare settings. The UW Advancing Integrated Mental Health Solutions (AIMS) Center recently developed the CoCM Checklist, and proposed a multidisciplinary collaboration to develop items that assess health equity in CoCM delivery, conduct a mixed-methods psychometric evaluation of the CoCM Checklist with equity items and complete a preliminary evaluation of CoCM components associated with patient improvement.

In preparation for IRB submission, we created recruitment materials to reach more than 133 clinic contacts. These included information sheets, initial and follow-up emails, a one-page flyer with a QR code linking to the information sheet and a phone script. A community advisor reviewed the materials, provided feedback and wrote a letter of support. We revised the materials based on his input, and the University of Washington IRB approved the study and all recruitment materials on March 31, 2025.

Our recruitment process uses a multi-step approach. First, we mail flyers to all contacts. Next, we send weekly recruitment emails for up to four weeks or until a response is received. If emails go unanswered, we call contacts and leave voicemails. In addition to these efforts, AIMS Center coaches share a brief PowerPoint slide during trainings and office hours, and study information is posted on the sign-in page of all AIMS Center registries.

To date, we have recruited 14 clinics toward our goal of 25, representing 56 percent of our target. Of the 133 contacts, 14 have agreed to participate and signed a Data Use Agreement (DUA), 21 are interested but have not signed, 22 declined and 78 have not responded.

Piloting the Equity in Injury Prevention Toolkit with People Who are Unhoused

Investigators
Barclay Stewart, Department of Surgery
Megan Moore, School of Social Work
Tony Machacha, King County Regional Homelessness Authority
Caitlin Orton, Department of Surgery

Project update
The aims of this pilot were to 1) pilot EQUIP Toolkit with people living unhoused within high burn injury risk areas of Seattle; and 2) assess EQUIP Toolkit implementation using the RE-AIM Framework (e.g., reach, effectiveness, adoption, implementation, maintenance) to support the future large-scale dissemination within King County.

Significant progress has been made in these aims. We have partnered with four lead outreach specialists (OS) who are responsible for supporting people living in tents and encampments within districts of Seattle that have the highest incidence of fires related to homelessness. The research team accompanied each lead OS during an outreach to initiate the distribution of EQUIP (prevention education and fire extinguishing and warming equipment) and discuss strategies for engaging their clients. The four lead OS have since been distributing EQUIP and answering online surveys every three weeks.

A couple of months after the initiation of EQUIP, the research team joined each lead OS to complete interviews with people living unhoused in their catchment areas. These interviews included questions about the reach, effectiveness, and maintenance of EQUIP. Distribution of EQUIP will continue through April and data collection will continue as planned.

First Bite: A Pilot Caregiver Training and Consultation Program to Address Critical Feeding Challenges for Autistic Children and Reduce Waitlist Length

Investigators
Brittany St John, Department of Rehabilitation Medicine
Tanya St. John, Department of Speech & Hearing Sciences
Yev Veverka, Institute on Human Development & Disability
Sara Kover, Department of Speech & Hearing Sciences
Jessica Greenson, Institute on Human Development & Disability
Nicole Bergstrom, Institute on Human Development & Disability
Sarah Lemke, Institute on Human Development & Disability
Kelleen Dunley, Institute on Human Development & Disability

Project update
The First Bite program is designed to pilot a 10-week caregiver education initiative with 12 participants, focusing on two primary outcomes: achieving child feeding goals and reducing the need for direct feeding services. During the initial grant period, the team refined program materials and developed an eight-module caregiver workbook, complete with guides, activities, goal-tracking tools, and summary sheets. These workbooks were printed and mailed to enrolled caregivers.

The first session launched on October 6 and will conclude December 19, 2025. Recruitment exceeded expectations, with 10 caregivers enrolling. Two withdrew due to scheduling conflicts but plan to join the second session, scheduled for January through March 2026. Seven caregivers remain actively engaged, maintaining a 93% attendance rate. At the midpoint evaluation, all caregivers had set two individualized feeding goals; five families reported progress on at least one goal, and three achieved or exceeded a goal, while two remained at baseline.

In addition to the core program, a Master of Occupational Therapy capstone project was integrated to assess program acceptability. This evaluation includes interviews with caregivers and clinic administrators to inform recommendations for expanding First Bite to additional clinical sites.

Exploring the Effectiveness and Implementation of Paid Leave Programs for Domestic Violence

Investigators
Avanti Adhia, ScD, Department of Child, Family, and Population Health Nursing
Heather D. Hill, Daniel J. Evans School of Public Policy & Governance
Krista Neumann, Department of Pediatrics
Ann Richey, Department of Epidemiology

Project update
Domestic violence (DV) is prevalent and carries significant individual, community and societal costs. State “safe leave” policies, including paid leave, provide survivors time off to address legal, medical or safety issues and represent one strategy to address DV at the outer layers of the social ecology. The goal of this Tier 2 project is to generate preliminary evidence on the effectiveness and implementation of paid leave programs for DV. Following IRB approval, we have made substantial progress on all three aims.

Aim 1: We conducted a policy landscape analysis of state safe leave programs. Reviewing reports, policy documents and legislature websites for all 50 states and DC, we examined three policy tools—paid family and medical leave, sick leave and victim leave—and their key dimensions through October 2025. We aggregated and analyzed these data to summarize policy features, distribution and changes over time, and submitted a commentary based on findings.

Aim 2: Using CDC’s Pregnancy Risk Assessment Monitoring System data, we are examining associations between state paid family and medical leave programs and DV during pregnancy. We obtained, merged and cleaned data from 2000–2022, finalized our analysis plan and are running proposed analyses.

Aim 3: We are exploring paid leave use for DV in two states with different program structures through qualitative interviews. We finalized states, developed protocols, identified participants and drafted interview guides for paid leave staff and social service partners. Recruitment and interviews are underway, providing rich qualitative insights that complement Aims 1 and 2.

Advancing Equitable AI for Stroke Diagnosis: A Global Foundation Model for Non-Contrast CT and CTA Imaging

A portion of the funding for this award came via a partnership with the UW Office of Global Affairs, which seeks to enhance the UW’s global engagement and reach.

Investigators
Mehmet Kurt, Department of Mechanical Engineering (and by courtesy, Bioengineering and Radiology)
Jacob Ruzevick, Department of Neurosurgery
Udunna Anazodo, McGill University and Crestview Radiology Ltd., Lagos, Nigeria
Maruf Adewole, Medical Artificial Intelligence Laboratory (MAI Lab), Crestview Radiology Ltd., Lagos, Nigeria

Project update
This project aims to develop, evaluate, and disseminate brain lesion AI methods that remain reliable for underrepresented populations, resource-constrained clinical environments and realistically sized datasets. Over the current funding period, we advanced ischemic stroke and brain tumor imaging research while building sustainable dissemination and training pathways focused on equity in medical imaging AI.

For ischemic stroke, we completed and presented a study at MICCAI demonstrating that clinically informed preprocessing significantly improves lesion segmentation from non-contrast CT and CTA. By incorporating skull stripping, intensity windowing, and vascular information, we improved mean Dice scores by 38.4% compared to standard preprocessing, with further gains using vessel segmentations. This pipeline ranked first in the ISLES’24 challenge, validating that CT-based methods can achieve clinically useful performance without MRI.

In parallel, we published a MICCAI 2025 paper on glioma segmentation using Sub-Saharan African MRI data, addressing the lack of benchmarks for resource-limited settings. Using a small, multi-institutional dataset, we found nnU-Net delivered strong, stable performance (Dice scores up to 0.89), matching or exceeding more complex architectures. These results underscore that robust, accessible methods can support equity in global healthcare.

To advance dissemination and capacity building, we co-organized the MIRASOL workshop at MICCAI 2025, connecting researchers, clinicians, and policymakers to address challenges in resource-constrained settings. The program emphasized approaches that “do more with less” and included a trainee-led organizing committee to foster leadership and sustainability. We also mentored three SPARK Academy trainees, providing technical guidance and networking opportunities.

Finally, we curated 160 paired CT–MRI stroke datasets from Harborview Medical Center to enable MRI-referenced evaluation of CT-based models, supporting future validation and funding efforts.

Pilot Study to Integrate Low-Barrier, Culturally and Linguistically Responsive Mental Health Care into Community-Based Social Services

Investigators

Lesley Steinman Department of Health Systems & Population Health
Najma Mohamed, Neighborhood House
Jacob Bentley, Department of Rehabilitation Medicine
Tricia Aung, Department of Human Centered Design & Engineering
Roberto Orellana, School of Social Work
KeliAnne Hara-Hubbard, Department of Health Systems & Population Health
Farhiya Osman, Neighborhood House

Project update
Our community–academic partnership aims to improve access to low-barrier, culturally and linguistically appropriate mental health care through trusted social service organizations. The pilot study will evaluate whether and how an adapted Problem Management Plus (PM+) model works for social service providers and Somali clients and their families. We have trained community-based organization (CBO) providers in PM+ and will assess both its impact and delivery. In addition to testing PM+ feasibility in U.S. CBOs, we will refine methods for future community-engaged mental health research.

To date, the team has:

• Trained six providers to deliver PM+ through a 12-week, 30-hour program that included demonstrations, role plays, and feedback. All providers were certified in PM+.
• Convened a co-design council and conducted one-on-one sessions to refine data collection tools.
• Finalized data collection protocols and tools for the pilot study in collaboration with CBO leaders, managers, providers, and the co-design council.
• Secured IRB approval for pilot study activities, including a reliance agreement for CBO engagement and approval to include participants ages 16 and 17.
• Developed new tools, trainings, and protocols to improve community-engaged data collection and facilitate adapted PM+ delivery by providers from diverse backgrounds, as requested by the CBO. Client recruitment is scheduled to begin in December 2025.
• Engaged graduate students to expand research efforts and align with community needs.