USCDI SDOH Data Elements

USCDI SDOH elements move social risk data from unstructured narratives into discrete, coded fields. This transition enables automated processing, quality reporting, and clinical decision support.

• Data Class: Problems — Captures SDOH diagnoses using ICD-10-CM Z-codes (Z55-Z65)
• Data Class: Health Concerns — Documents patient-identified social needs not yet coded as diagnoses
• Data Class: Procedures — Records interventions like counseling for food insecurity
• Eliminates reliance on free-text parsing for core exchange use cases

USCDI does not just name a broad category; it defines specific, exchangeable elements. For SDOH, this includes granularity down to the level of a single screening observation.

• SDOH Assessment class includes elements for Food Insecurity, Housing Instability, and Transportation Insecurity
• Each element can be paired with a standardized screening tool name (e.g., PRAPARE, AHC-HRSN)
• Allows for the exchange of both the raw answer and the interpreted risk score
• Distinguishes between a patient's self-reported concern and a clinician's formal diagnosis

The USCDI SDOH elements are harmonized with the Gravity Project's consensus-driven terminology. This alignment ensures that the codes used for exchange are clinically relevant and map to real-world screening instruments.

• Gravity Project develops value sets for FHIR SDOH Observation resources
• Standardizes concepts like 'Less than high school education' or 'Homeless shelter'
• Bridges the gap between a screening question on a form and a computable, interoperable data point
• Prevents the proliferation of local, non-standard codes that block semantic interoperability

By standardizing SDOH data for exchange, USCDI creates the foundational data layer for population-level health equity analysis. Aggregated, de-identified data can reveal systemic disparities.

• Enables calculation of quality measures stratified by social risk factors
• Supports the integration of individual-level SDOH data with geospatial indices like the Area Deprivation Index (ADI)
• Allows accountable care organizations to identify high-risk cohorts with both medical and social complexity
• Provides the data necessary to measure the impact of social care interventions on clinical outcomes

USCDI guidance emphasizes the importance of metadata to maintain data integrity. For SDOH elements, this means tracking the source, time, and method of data capture to prevent misuse.

• Author and Authoring Time elements track who documented the data and when
• Distinguishes between patient-reported, provider-assessed, and derived data
• Prevents a historical, resolved housing issue from being misinterpreted as an active problem
• Supports data quality audits by tracing an exchanged SDOH observation back to its original source document

A subset of diagnosis codes (Z55-Z65) used to document social determinants of health in a patient's structured medical record. These codes capture specific risks such as housing instability (Z59.0), lack of adequate food (Z59.4), or unemployment (Z56.0). Unlike free-text mentions, Z-codes provide structured, billable data that can be exchanged via USCDI-compliant systems, though they remain significantly underutilized in clinical practice.

A consensus-driven initiative that develops standardized data elements and value sets for representing social determinants of health in EHRs and FHIR APIs. The Gravity Project defines structured screening instruments, coded observations, and interoperable terminology that directly inform the USCDI SDOH data classes. Key contributions include standardized value sets for food insecurity, housing stability, and transportation access.

A Fast Healthcare Interoperability Resources resource used to represent a specific, screened social risk finding in a standardized, exchangeable format. This resource captures the screening instrument used, the patient's response, and the coded finding using Gravity Project value sets. It is the primary mechanism for exchanging USCDI-mandated SDOH data between certified systems.

An automated sequence of natural language processing components designed to extract, classify, and structure social determinant risk factors from unstructured clinical narratives. Key stages include:

• Named Entity Recognition for identifying mentions like 'homeless' or 'unemployed'
• Negation detection to distinguish affirmed vs. denied risks
• Experiencer detection to identify whether the patient or a family member is affected
• Temporality classification to determine if the risk is current, historical, or future

An automated workflow that tracks a patient's journey from a positive social risk screening through to a confirmed connection with a community-based service provider. When a USCDI SDOH data element flags a need—such as food insecurity—the closed-loop system initiates a referral, monitors acceptance, and verifies service delivery. This closes the gap between screening and resolution, ensuring social risk data drives actionable outcomes.

The application of predictive models to segment a patient population by their level of social risk, enabling targeted interventions and resource allocation. These models combine USCDI-structured SDOH data with area-level indices like the Social Vulnerability Index (SVI) and Area Deprivation Index (ADI) to identify high-risk cohorts. Outputs inform population health strategies and value-based care contract performance.