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

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

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.

Study Overview

• Status: Not yet recruiting
• Conditions: Patient Safety; Quality of Health Care; Clinical Decision Support
• Intervention / Treatment: Other: AI care plan with safety guardrails; Other: CITE evidence-grounding retrieve-and-verify layer

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).

• Study Type: Interventional
• Enrollment (Estimated): 240
• Phase: Not Applicable

Participation Criteria

Eligibility Criteria

• Ages Eligible for Study: Adult; Older Adult
• Accepts Healthy Volunteers: No

Description

INCLUSION CRITERIA:

1. Age 18 years or older.
2. Medicaid-enrolled and attributed to a participating Waymark primary care site.
3. Primary care encounter that requires clinical reasoning (not administrative-only).
4. English-language clinical documentation.

EXCLUSION CRITERIA:

1. Age less than 18 years.
2. Hospice or palliative-care-exclusive care plan.
3. Administrative-only or pharmacy-only encounter that does not surface a clinical decision to the supervising clinician.
4. Encounter where the supervising clinician is the principal investigator.
5. Enrollment in a competing AI-safety study within the prior 90 days.

Study Plan

How is the study designed?

Design Details

• Primary Purpose: Health Services Research
• Allocation: Randomized
• Interventional Model: Parallel Assignment
• Masking: Single

Number of Arms

3

Arms and Interventions

Participant Group / Arm	Intervention / Treatment
No Intervention: Arm 1: Unassisted care; Clinician develops the care plan without AI assistance.
Active Comparator: Arm 2: AI with safety guardrails; AI-generated care plan produced with a safety-guardrail system prompt; no CITE.	Other: AI care plan with safety guardrails; AI-generated care plan produced under a safety-guardrail system prompt.
Experimental: Arm 3: AI with safety guardrails plus CITE; AI-generated care plan with safety guardrails, then passed through CITE, which flags unsupported/inappropriate recommendations with evidence citations for the clinician.	Other: AI care plan with safety guardrails; AI-generated care plan produced under a safety-guardrail system prompt.; 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.

What is the study measuring?

Primary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Diagnostic accuracy of CITE against clinician adjudication	Sensitivity and specificity (with positive and negative predictive values) of the CITE checker for clinically consequential codifiable safety hazards, using blinded clinician adjudication of the plan as the reference standard. Every plan contributes, so the estimate does not depend on a rare between-arm event. Exact-binomial 95% confidence intervals; reported overall and by hazard family.	Day 1 (index primary care encounter)
Clinician alert burden (flags surfaced per encounter)	Number of safety flags surfaced to the clinician per encounter in the CITE arm versus the guardrail arm, with clinician acceptance rate. Co-primary usability outcome: a verifier that surfaces an unmanageable number of flags is not deployable regardless of sensitivity (the prior-trial mechanism surfaced a median of about 30 per encounter). Pre-registered acceptability ceiling: median CITE flags per encounter at or below three.	Day 1 (index primary care encounter)

Secondary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Clinician action on CITE flags	Proportion of CITE flags accepted vs overridden by the clinician, by flag type (commission, confabulation, unsupported, omission).	Day 1 (index primary care encounter)
Unresolved codifiable safety-hazard rate by arm (descriptive)	Proportion of patient-specific codifiable-hazard checkpoints with an unresolved hazard in the finalized plan, by arm, with the Arm 3 minus Arm 2 difference and 95% confidence interval. Pre-specified as descriptive and hypothesis-generating: codifiable hazards are infrequent, so the trial is not powered for a between-arm efficacy contrast on this measure at the enrolled sample size.	Day 1 (index primary care encounter)
Correction of codifiable hazards within 30 days	Among checkpoints with a hazard in the finalized plan, the proportion acted on and corrected within 30 days (documented resolution, completed referral, or corrected order). Proximal clinical effectiveness measure.	Up to 30 days after the index encounter
Completed referrals within 30 days	Proportion of initiated referrals completed within 30 days.	Up to 30 days after the index encounter
Clinical safety composite (exploratory)	Four-component clinical safety composite carried from the prior trial. Pre-specified as exploratory; underpowered at the planned sample size.	Day 1 (index primary care encounter)
30-day acute care utilization (exploratory)	Emergency department visits and hospitalizations within 30 days. Exploratory.	Up to 30 days after the index encounter

Collaborators and Investigators

• Sponsor: Waymark
• Collaborators: University of California, San Francisco

Study record dates

Study Major Dates

• Study Start (Estimated): September 1, 2026
• Primary Completion (Estimated): June 1, 2027
• Study Completion (Estimated): September 1, 2027

Study Registration Dates

• First Submitted: July 13, 2026
• First Submitted That Met QC Criteria: July 16, 2026
• First Posted (Actual): July 22, 2026

Study Record Updates

• Last Update Posted (Actual): July 22, 2026
• Last Update Submitted That Met QC Criteria: July 16, 2026
• Last Verified: July 1, 2026

More Information

Terms related to this study

• Other Study ID Numbers: CITE-2026-02

Drug and device information, study documents

• Studies a U.S. FDA-regulated drug product: No
• Studies a U.S. FDA-regulated device product: No
• product manufactured in and exported from the U.S.: No