Identifying treatment effects of an informal caregiver education intervention to increase days in the community and decrease caregiver distress: a machine-learning secondary analysis of subgroup effects in the HI-FIVES randomized clinical trial.



Informal caregivers report substantial burden and depressive symptoms which predict higher rates of patient institutionalization. While caregiver education interventions may reduce caregiver distress and decrease the use of long-term institutional care, evidence is mixed. Inconsistent findings across studies may be the result of reporting average treatment effects which do not account for how effects differ by participant characteristics. We apply a machine-learning approach to randomized clinical trial (RCT) data of the Helping Invested Family Members Improve Veteran's Experiences Study (HI-FIVES) intervention to explore how intervention effects vary by caregiver and patient characteristics.


We used model-based recursive partitioning models. Caregivers of community-residing older adult US veterans with functional or cognitive impairment at a single VA Medical Center site were randomized to receive HI-FIVES (n = 118) vs. usual care (n = 123). The outcomes included cumulative days not in the community and caregiver depressive symptoms assessed at 12 months post intervention. Potential moderating characteristics were: veteran age, caregiver age, caregiver ethnicity and race, relationship satisfaction, caregiver burden, perceived financial strain, caregiver depressive symptoms, and patient risk score.


The effect of HI-FIVES on days not at home was moderated by caregiver burden (p < 0.001); treatment effects were higher for caregivers with a Zarit Burden Scale score ≤ 28. Caregivers with lower baseline Center for Epidemiologic Studies Depression Scale (CESD-10) scores (≤ 8) had slightly lower CESD-10 scores at follow-up (p < 0.001).


Family caregiver education interventions may be less beneficial for highly burdened and distressed caregivers; these caregivers may require a more tailored approach that involves assessing caregiver needs and developing personalized approaches.

Trial registration, ID:NCT01777490. Registered on 28 January 2013.





Published Version (Please cite this version)


Publication Info

Shepherd-Banigan, Megan, Valerie A Smith, Jennifer H Lindquist, Michael Paul Cary, Katherine EM Miller, Jennifer G Chapman and Courtney H Van Houtven (2020). Identifying treatment effects of an informal caregiver education intervention to increase days in the community and decrease caregiver distress: a machine-learning secondary analysis of subgroup effects in the HI-FIVES randomized clinical trial. Trials, 21(1). p. 189. 10.1186/s13063-020-4113-x Retrieved from

This is constructed from limited available data and may be imprecise. To cite this article, please review & use the official citation provided by the journal.



Megan E Shepherd-Banigan

Assistant Professor in Population Health Sciences

Dr. Megan Shepherd-Banigan designs research studies to improve the health, emotional well-being, and social functioning of adults with mental and physical disabilities. Her methods combine empirical approaches that address methodologically challenging research questions in health systems and policy research. Dr. Shepherd-Banigan uses large survey and administrative datasets to evaluate the impact of policies that support family members to care for adults with disabilities.  

Dr. Shepherd-Banigan won a VA Career Development Award from 2019-2024 and is studying ways to strengthen family support for veterans under-going traumatic stress treatment. She also leads a project that surveys family caregivers of Vietnam-era veterans who might be eligible for expanded support services under the VA Mission Act to evaluate program impacts. As co-investigator on an NIA-funded CARE IDEAS study (Terri Wetle, PI) , she is investigating end-of-life-care planning and well-being among dementia care dyads.  Finally, Dr. Shepherd-Banigan is leading a project in partnership with the Rosalynn Carter Institute for Caregivers to identify creative empirically-based approaches to support family caregivers. 


Valerie A. Smith

Associate Professor in Population Health Sciences

Valerie A. Smith, DrPH, is an Associate Professor in the Duke University Department of Population Health Sciences and Senior Research Director of the Biostatistics Core at the Durham Veterans Affairs Medical Center's Center of Innovation. Her methodological research interests include: methods for semicontinuous and zero-inflated data, economic modeling methods, causal inference methods, observational study design, and longitudinal data analysis. Her current methodological research has focused on the development of marginalized models for semicontinuous data.

Dr. Smith works largely in collaboration with a multidisciplinary team of researchers, with a focus on health policy interventions, health care utilization and expenditure patterns, program and policy evaluation, obesity and weight loss, bariatric surgery evaluation, and family caregiver supportive services.

Areas of expertise: Biostatistics, Health Services Research, Health Economics, and Health Policy


Michael Paul Cary

Elizabeth C. Clipp Term Chair of Nursing

Dr. Cary is an Associate Professor and Elizabeth C. Clipp Term Chair of Nursing in the Duke University School of Nursing. Dually trained as a health services researcher and applied data scientist, Dr. Cary uses AI and machine learning to study health disparities related to aging and develop strategies to advance health equity and improve healthcare delivery to older adults in diverse populations. His research has been supported by the National Library of Medicine, National Institute of Nursing Research, and the Duke Clinical and Translational Science Institute. He has published more than 50 manuscripts, book chapters, and editorials and has mentored numerous students and faculty members. In 2022, he was inducted as a Fellow of the American Academy of Nursing for his significant contributions to improve health and healthcare.

Most recently, he was selected by Duke Health to be the inaugural AI Health Equity Scholar. In this health system leadership position, he leads an interdisciplinary team in identifying clinical algorithms that perpetuate racial and ethnic health and health care disparities and implementing system-wide standards for mitigating their harmful discriminatory effects on patients. These meaningful contributions are vital to addressing health disparities and promoting equitable health outcomes for all patients at Duke and beyond.

Dr. Cary received a bachelor’s degree in health services administration from James Madison University. He also earned a bachelors, masters, and doctoral degree in nursing from the University of Virginia.

Unless otherwise indicated, scholarly articles published by Duke faculty members are made available here with a CC-BY-NC (Creative Commons Attribution Non-Commercial) license, as enabled by the Duke Open Access Policy. If you wish to use the materials in ways not already permitted under CC-BY-NC, please consult the copyright owner. Other materials are made available here through the author’s grant of a non-exclusive license to make their work openly accessible.