Impact of Social Risk Decision Support

Improving Population and Clinical Health With Integrated Services and Advanced Analytics

The purpose of this study is to determine the impact of embedding a risk-stratification tool, designed to identify patient needs for services that address social determinant of health related needs, in a commercial electronic health record system (EHR).

Study Overview

• Status: Withdrawn
• Conditions: Health Social Determinant
• Intervention / Treatment: Other: Risk screening tool exposure

Detailed Description

Social determinant of health related needs and social risk factors complicate care delivery and drive health and well-being. Social needs are common among undeserved patient populations, but health care providers are often not equipped to routinely identify and address patients in need.

Using a combination of health information exchange, electronic health record, and aggregate datasets the investigators developed predictive algorithms to identify patients a highest risk for a need for a referral to a social worker, dietitian, behavioral health, or other wraparound service provider. Risk scores are available to primary care providers in two ways within the electronic health record system (EHR): 1) a graphical summary of individual risk or 2) a line listing of all scheduled patients.

The investigators are introducing the risk-stratification tool in an urban safety-net primary care provider on a voluntary usage basis.

• Study Type: Interventional
• Phase: Not Applicable

Contacts and Locations

Study Locations

• United States
  • Indiana
    • Indianapolis, Indiana, United States, 46202
      • Eskenazi Health

Participation Criteria

Eligibility Criteria

• Ages Eligible for Study: Child; Adult; Older Adult
• Accepts Healthy Volunteers: Yes
• Genders Eligible for Study: All

Description

Inclusion Criteria:

• Encounters among patients seeking primary care service at any of the 9 Eskenazi Health FQHC clinics in Indianapolis, IN from January 2017 to May 2020.
• The propensity score matched primary care encounters from non-Eskenazi facilities.

Exclusion Criteria:

• Emergency encounters or hospitalizations

Study Plan

How is the study designed?

Design Details

• Primary Purpose: Screening
• Allocation: Non-Randomized
• Interventional Model: Parallel Assignment
• Masking: None (Open Label)

Number of Arms

2

Arms and Interventions

Participant Group / Arm	Intervention / Treatment
Experimental: Intervention group; Encounters at primary care clinics with the risk screening tool	Other: Risk screening tool exposure; Risk screening tool is available to providers
No Intervention: Comparison group; Propensity score matched comparison encounters

What is the study measuring?

Primary Outcome Measures

Outcome Measure	Measure Description	Time Frame
ED utilization rate	Rate of potentially avoidable emergency department utilization as determined by encounters recorded in health information exchange data and categorized using the NYU ED Algorithm.	6 months
Missed primary care appointments rate	Rate of no show / cancelled appointments at the intervention site primary care clinics as recorded in the intervention site's electronic health record system	6 months

Secondary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Hospitalization rate	Rate of all cause and potentially preventable hospitalization as determined by encounters recorded in health information exchange data and categorized using AHRQ's prevention quality indicator definitions	6 months

Collaborators and Investigators

• Sponsor: Indiana University
• Collaborators: Robert Wood Johnson Foundation
• Investigators: Principal Investigator: Joshua R Vest, PhD, Associte Professor

Publications and helpful links

General Publications

• Kasthurirathne SN, Vest JR, Menachemi N, Halverson PK, Grannis SJ. Assessing the capacity of social determinants of health data to augment predictive models identifying patients in need of wraparound social services. J Am Med Inform Assoc. 2018 Jan 1;25(1):47-53. doi: 10.1093/jamia/ocx130.
• Vest JR, Grannis SJ, Haut DP, Halverson PK, Menachemi N. Using structured and unstructured data to identify patients' need for services that address the social determinants of health. Int J Med Inform. 2017 Nov;107:101-106. doi: 10.1016/j.ijmedinf.2017.09.008. Epub 2017 Sep 20.
• Vest JR, Menachemi N, Grannis SJ, Ferrell JL, Kasthurirathne SN, Zhang Y, Tong Y, Halverson PK. Impact of Risk Stratification on Referrals and Uptake of Wraparound Services That Address Social Determinants: A Stepped Wedged Trial. Am J Prev Med. 2019 Apr;56(4):e125-e133. doi: 10.1016/j.amepre.2018.11.009. Epub 2019 Feb 14.

Study record dates

Study Major Dates

• Study Start (Actual): June 1, 2019
• Primary Completion (Actual): December 31, 2020
• Study Completion (Actual): December 31, 2020

Study Registration Dates

• First Submitted: May 28, 2019
• First Submitted That Met QC Criteria: May 31, 2019
• First Posted (Actual): June 4, 2019

Study Record Updates

• Last Update Posted (Actual): February 10, 2021
• Last Update Submitted That Met QC Criteria: February 8, 2021
• Last Verified: February 1, 2021

More Information

Terms related to this study

• Keywords: risk prediction
• Other Study ID Numbers: VEST-RWJF-PHASE2

Plan for Individual participant data (IPD)

• Plan to Share Individual Participant Data (IPD)?: NO

Drug and device information, study documents

• Studies a U.S. FDA-regulated drug product: No
• Studies a U.S. FDA-regulated device product: No