CITE: Clinical Inference Tethered to Evidence - a Retrieve-and-verify Layer for AI Care Plans | NCT07718893

NCT07718893

Overview

NCT ID: NCT07718893
Lead Sponsor: WaymarkINDUSTRY
Official Title: A Randomized Controlled Trial of CITE (Clinical Inference Tethered to Evidence), an Evidence-Grounding Retrieve-and-Verify Layer That Flags Unsupported and Inappropriate Recommendations in AI-Generated Care Plans, Versus AI With Safety Guardrails Alone and Unassisted Care, in Medicaid Primary Care
Brief Summary: This trial evaluates CITE, a retrieve-and-verify layer that audits an AI-generated care plan against a full-text evidence corpus and flags patient-specific codifiable safety hazards to the clinician. The co-primary outcomes are how accurately CITE flags these hazards (sensitivity and specificity versus blinded clinician adjudication) and its clinician alert burden and acceptance, compared with AI care plans using safety guardrails alone and with unassisted clinician care, in Medicaid primary care.
Conditions: Quality of Health Care
Patient Safety

Status and Timeline

Status: Not yet recruiting
Last Update Posted: Jul 22, 2026Actual
Start Date: Sep 2026Estimated
Primary Completion Date: Jun 2027Estimated
Completion Date

Participation Criteria

Ages Eligible for Study: Adult (18-64)Older Adult (65+)
Sexes Eligible for Study: All
Accepts Healthy Volunteers?: No
Eligibility Criteria: INCLUSION CRITERIA:

Age 18 years or older.

Medicaid-enrolled and attributed to a participating Waymark primary care site.

Primary care encounter that requires clinical reasoning (not administrative-only).

English-language clinical documentation.

EXCLUSION CRITERIA:

Age less than 18 years.

Hospice or palliative-care-exclusive care plan.

Administrative-only or pharmacy-only encounter that does not surface a clinical decision to the supervising clinician.

Encounter where the supervising clinician is the principal investigator.

Enrollment in a competing AI-safety study within the prior 90 days.

Study Plan

Study Type: Interventional
Phase: Not Applicable
Enrollment: 240Estimated
Primary Purpose: Health Services Research
Allocation: Randomized
Interventional Model: Parallel Assignment
Masking: Single

Contacts and Locations

Central Contacts: No data available
Locations: No data available

Similar Studies

Participant Group/Arms

Arm 1: Unassisted careNo Intervention

Clinician develops the care plan without AI assistance.

Arm 2: AI with safety guardrailsActive Comparator

AI-generated care plan produced with a safety-guardrail system prompt; no CITE.

Other: AI care plan with safety guardrails

Arm 3: AI with safety guardrails plus CITEExperimental

AI-generated care plan with safety guardrails, then passed through CITE, which flags unsupported/inappropriate recommendations with evidence citations for the clinician.

Other: CITE evidence-grounding retrieve-and-verify layer