Effectiveness of a clinical decision support system with prediction modeling to identify patients with health-related social needs in the emergency department: Study protocol

dc.contributor.authorMazurenko, Olena
dc.contributor.authorHarle, Christopher A.
dc.contributor.authorBlackburn, Justin
dc.contributor.authorMenachemi, Nir
dc.contributor.authorHirsh, Adam
dc.contributor.authorGrannis, Shaun
dc.contributor.authorBoustani, Malaz
dc.contributor.authorMusey, Paul I., Jr.
dc.contributor.authorSchleyer, Titus K.
dc.contributor.authorSanner, Lindsey M.
dc.contributor.authorVest, Joshua R.
dc.contributor.departmentHealth Policy and Management, Richard M. Fairbanks School of Public Health
dc.date.accessioned2025-06-16T13:47:35Z
dc.date.available2025-06-16T13:47:35Z
dc.date.issued2025-05-12
dc.description.abstractIntroduction: Health-related social needs (HRSNs) encompass various non-medical risks from a patient's life circumstances. The emergency department (ED) is a crucial yet challenging setting for addressing patient HRSNs, a clinical decision support (CDS) intervention could assist in identifying patients at high risk of having HRSNs. This project aims to implement and evaluate a CDS intervention that offers ED clinicians risk prediction scores to determine which patients will likely screen positive for one or more HRSNs. Materials & methods: The FHIR-based CDS intervention, implemented in the ED setting of a health system in Indianapolis, Indiana, will use health information exchange data to generate logit-derived probability scores that estimate an adult patient's likelihood of screening positive for each of the following HRSNs: housing instability, food insecurity, transportation barriers, financial strain, and history of legal involvement. For each HRSN, ED clinicians will have access to the patient's likelihood of screening positive categorized as "high," "medium," or "low" based on tertiles in the distribution of each likelihood score. Clinician participation in the CDS will be voluntary. The intervention's effects will be assessed using a difference-in-difference approach with a pre-post design and a propensity-matched comparison group of ED patients from the same metropolitan area. Outcomes of interest include whether a formal HRSN screening was conducted, whether a referral was made to an HRSN service provider (e.g., social worker), and whether a repeat ED revisit (at 3, 7, and 30 days) or primary care follow-up (within 7 days) occurred. Discussion: Efficiently and accurately identifying patients with HRSNs could help link them to needed services, improving outcomes and reducing healthcare costs. This protocol will contribute to a growing body of research on the role of CDS interventions in facilitating improved screenings and referrals for HRSNs.
dc.eprint.versionFinal published version
dc.identifier.citationMazurenko O, Harle CA, Blackburn J, et al. Effectiveness of a clinical decision support system with prediction modeling to identify patients with health-related social needs in the emergency department: Study protocol. PLoS One. 2025;20(5):e0323094. Published 2025 May 12. doi:10.1371/journal.pone.0323094
dc.identifier.urihttps://hdl.handle.net/1805/48747
dc.language.isoen_US
dc.publisherPublic Library of Science
dc.relation.isversionof10.1371/journal.pone.0323094
dc.relation.journalPLoS One
dc.rightsAttribution 4.0 Internationalen
dc.rights.urihttp://creativecommons.org/licenses/by/4.0/
dc.sourcePMC
dc.subjectClinical decision support systems
dc.subjectHospital emergency service
dc.subjectIndiana
dc.titleEffectiveness of a clinical decision support system with prediction modeling to identify patients with health-related social needs in the emergency department: Study protocol
dc.typeArticle
Files
Original bundle
Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
Mazurenko2025Effectiveness-CCBY.pdf
Size:
735.11 KB
Format:
Adobe Portable Document Format
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
2.04 KB
Format:
Item-specific license agreed upon to submission
Description: