CITE: Clinical Inference Tethered to Evidence - a Retrieve-and-verify Layer for AI Care Plans
For patients and families
In plain language
An automatic summary of structured registry data. It is an orientation aid, not a substitute for the official protocol or a physician assessment.
- What is being studied
- The protocol lists: CITE evidence-grounding retrieve-and-verify layer, AI care plan with safety guardrails.
- Who it may be relevant to
- Registry conditions: Quality of Health Care, Patient Safety, Clinical Decision Support. Basic parameters: from 18 years · All.
- What needs checking
- Age, condition and sex are only basic indicators. Prior treatment, laboratory values and other mandatory requirements appear in the eligibility criteria below.
- Where it takes place
- Center list to be confirmed — check the primary protocol.
- Next step
- Save the trial, show it to the treating physician, and confirm current recruitment with the study center. Costs, documents and travel →
Unsure about the terms? Read our patient guide →
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
Overview
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.
Detailed description
Patients are randomized 1:1:1 to (1) unassisted clinician care; (2) AI-generated care plan with safety guardrails; (3) AI-generated care plan with safety guardrails plus CITE. CITE audits the finalized plan against a frozen, versioned evidence corpus and returns physician-facing flags for patient-specific codifiable safety hazards (a recommended drug contraindicated by this patient's diagnosis or laboratory value; a drug-allergy conflict; a dropped high-risk medication; a guideline-indicated therapy omitted for an active diagnosis; a stated quantity refuted by the corpus), each with a verbatim quote and citation; the clinician retains decision authority. Randomization uses a deterministic HMAC permuted-block scheme; outcome assessors are blinded to arm. The co-primary outcomes are (1) the diagnostic accuracy (sensitivity and specificity) of CITE against blinded clinician adjudication, and (2) clinician alert burden (flags per encounter) and acceptance, comparing the CITE arm with the guardrail arm; both are estimable at the enrolled sample size because they do not depend on a rare between-arm event. The unresolved codifiable-hazard rate by arm is reported as a descriptive secondary: codifiable hazards are infrequent, so the trial is not powered for a between-arm efficacy contrast on hazard reduction. A prior trial of a different mechanism (a generic deterministic rule-corpus that surfaced roughly 30 or more flags per encounter and was uninformative) was completed with null results and is registered separately; this trial evaluates a materially different, patient-specific intervention and set of outcomes. Determined exempt by WCG IRB (low risk). Analysis is pre-registered on OSF (https://doi.org/10.17605/OSF.IO/ENXCW).
Interventions
- Other CITE evidence-grounding retrieve-and-verify layer
Reads the AI care-plan text and verifies each recommendation/claim against a full-text evidence corpus; returns physician-facing flags (commission/confabulation/unsupported/omission) with verbatim quotes and citations. Clinician retains decision authority. - Other AI care plan with safety guardrails
AI-generated care plan produced under a safety-guardrail system prompt.
Primary outcome measures
- Diagnostic accuracy of CITE against clinician adjudication [Time frame: Day 1 (index primary care encounter)]
- Clinician alert burden (flags surfaced per encounter) [Time frame: Day 1 (index primary care encounter)]
Secondary outcome measures (6)
- Clinician action on CITE flags [Time frame: Day 1 (index primary care encounter)]
- Unresolved codifiable safety-hazard rate by arm (descriptive) [Time frame: Day 1 (index primary care encounter)]
- Correction of codifiable hazards within 30 days [Time frame: Up to 30 days after the index encounter]
- Completed referrals within 30 days [Time frame: Up to 30 days after the index encounter]
- Clinical safety composite (exploratory) [Time frame: Day 1 (index primary care encounter)]
- 30-day acute care utilization (exploratory) [Time frame: Up to 30 days after the index encounter]
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.
Criteria are shown verbatim from the registry (in English). Final eligibility is always assessed by the study center.
Healthy volunteers: No
Study design
- Allocation
- Randomized
- Model
- Parallel assignment
- Masking
- Single blind
- Primary purpose
- Health services research
Study locations
Center list to be confirmed — check the primary protocol.
Identifiers
NCT: NCT07718893 · CITE-2026-02