Social Engagement Support System for Social Determinants of Health

Overseen By Ian Stockwell, PhD

Age: 18 - 65

Sex: Any

Trial Phase: Academic

Sponsor: University of Maryland, Baltimore County

No Placebo Group All trial participants will receive the active study treatment (no placebo)

Compensation: Varies

Number of Visits: Unknown

Duration: 12 months

249660 Participants Needed

Trial Summary

What is the purpose of this trial?

The goal of this clinical trial is to determine if artificial intelligence and machine learning (AI/ML) models can help address social needs in Medicaid enrollees. The main questions it aims to answer are: Can AI/ML models accurately identify social needs from administrative healthcare data? Can AI/ML models accurately predict which people will engage with social supports? Researchers will compare individuals who live in different regions to see if AI/ML models perform better than the status quo.

Will I have to stop taking my current medications?

The trial information does not specify whether you need to stop taking your current medications.

What data supports the effectiveness of the treatment Social Engagement Support System for Social Determinants of Health?

The research highlights the importance of addressing social determinants of health, which are factors like living conditions and social support that affect health outcomes. Screening tools like the Core 5 have been effective in identifying social needs, suggesting that systems focusing on social engagement can help connect patients with necessary resources, potentially improving health outcomes. ^{1 2 3 4 5}

How is the Social Engagement Support System treatment different from other treatments for social determinants of health?

The Social Engagement Support System is unique because it focuses on using electronic systems to capture and utilize social health data, which is often not included in traditional medical records. This approach aims to integrate social factors into healthcare, potentially improving health outcomes by addressing social determinants of health directly. ^{2 3 6 7 8}

Eligibility Criteria

This trial is for members of a partner health plan aged between 18 and 64. It's designed to see if AI can identify and predict engagement with social supports among Medicaid enrollees. The study excludes individuals outside this age range or not part of the health plan.

Timeline

Screening

Participants are screened for eligibility to participate in the trial

2-4 weeks

Treatment

Participants receive care coordination resources supported by the Social Engagement Support System

12 months

Follow-up

Participants are monitored for changes in health-related social needs and engagement success

4 weeks

Treatment Details

Interventions

• Social Engagement Support System

Trial Overview The trial is testing an AI/ML-based Social Engagement Support System to improve identification and prediction of social needs in healthcare data. It compares the effectiveness of these models against traditional methods across different regions.

Participant Groups

Group I: SESS - Treatment Experimental Treatment 1 Intervention

This arm will receive care coordination resources supported by our Social Engagement Support System, including the triage of screening outreach based on predicted risk of an unmet social need and engagement support to decrease like likelihood of dropout from the social services workflow.

Group II: SESS - Control Active Control 1 Intervention

This arm will receive no intervention.

Who Is Running the Clinical Trial?

University of Maryland, Baltimore County

Lead Sponsor

Trials

13

Recruited

2,400+

National Institute on Minority Health and Health Disparities (NIMHD)

Collaborator

Trials

473

Recruited

1,374,000+

Findings from Research

There is a significant gap in guidance for healthcare practitioners on how to address patients' social needs in clinical settings, despite evidence linking social circumstances to health outcomes.

The article proposes a three-tier framework for implementing social determinants interventions in healthcare, focusing on individual patients, healthcare institutions, and broader population strategies, along with methods for data collection and targeted interventions.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

Collecting and applying data on social determinants of health in health care settings. Gottlieb, L., Sandel, M., Adler, NE.[2022]

A new social health screening (SHS) tool was developed based on feedback from health consumer advocates, patients, and clinicians, aimed at addressing social determinants of health (SDH) in clinical settings.

In a pilot study with 50 patients from anxiety and sleep disorder clinics, both patients and clinicians responded positively to the SHS tool, indicating its potential to enhance understanding of individual social circumstances and promote health equity.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

Developing a screening tool to recognise social determinants of health in Australian clinical settings. Browne-Yung, K., Freeman, T., Battersby, M., et al.[2020]

The implementation of the Core 5 social risk screening tool in a presurgical spine population successfully identified social risk factors in 59% of patients, highlighting the importance of addressing social determinants of health before surgery.

Staff reported high usability and acceptance of the screening tool, with an average score of 4.4 out of 5, indicating that it can be effectively integrated into clinical workflows to connect patients with necessary resources.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

Implementing screening for social determinants of health using the Core 5 screening tool. Bradywood, A., Leming-Lee, TS., Watters, R., et al.[2021]

References

1. United States pubmed.ncbi.nlm.nih.gov

Collecting and applying data on social determinants of health in health care settings. [2022]

2. Japan pubmed.ncbi.nlm.nih.gov

Social vital signs for improving awareness about social determinants of health. [2020]

3. Australia pubmed.ncbi.nlm.nih.gov

Developing a screening tool to recognise social determinants of health in Australian clinical settings. [2020]

4. England pubmed.ncbi.nlm.nih.gov

Implementing screening for social determinants of health using the Core 5 screening tool. [2021]

5. Ireland pubmed.ncbi.nlm.nih.gov

Exploring patients' health information communication practices with social network members as a foundation for consumer health IT design. [2018]

6. United States pubmed.ncbi.nlm.nih.gov

Capturing Social Health Data in Electronic Systems: A Systematic Review. [2019]

7. England pubmed.ncbi.nlm.nih.gov

A call for social informatics. [2021]

8. England pubmed.ncbi.nlm.nih.gov

Development and trialling of a tool to support a systems approach to improve social determinants of health in rural and remote Australian communities: the healthy community assessment tool. [2021]