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

NCT07718893 | Not Yet Recruiting

• 1 other identifier: CITE-2026-02
• Study Type: interventional
• Target: 240
• Locations: 0 countries
• Sites: N/A

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; Clinical Decision Support

Outcome Measures

Primary Outcomes (2)

• 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 Outcomes (6)

• Clinician action on CITE flags

  Day 1 (index primary care encounter)

• Unresolved codifiable safety-hazard rate by arm (descriptive)

  Day 1 (index primary care encounter)

• Correction of codifiable hazards within 30 days

  Up to 30 days after the index encounter

• Completed referrals within 30 days

  Up to 30 days after the index encounter

• Clinical safety composite (exploratory)

  Day 1 (index primary care encounter)

Study Arms (3)

Arm 1: Unassisted care

NO INTERVENTION

Clinician develops the care plan without AI assistance.

Arm 2: AI with safety guardrails

ACTIVE 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 CITE

EXPERIMENTAL

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; Other: AI care plan with safety guardrails

Interventions

AI care plan with safety guardrails OTHER

AI-generated care plan produced under a safety-guardrail system prompt.

Arm 2: AI with safety guardrails; Arm 3: AI with safety guardrails plus CITE

CITE evidence-grounding retrieve-and-verify layer OTHER

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.

Arm 3: AI with safety guardrails plus CITE

Eligibility Criteria

• Age: 18 Years+
• Sex: all
• Healthy Volunteers: No
• Age Groups: Adult (18-64), Older Adult (65+)

You may qualify if:

• 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.

You may not qualify if:

• 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.

Sponsors & Collaborators

• Waymark: lead
• University of California, San Francisco: collaborator

Study Design

• Study Type: interventional
• Phase: not applicable
• Allocation: RANDOMIZED
• Masking: SINGLE
• Who Masked: OUTCOMES ASSESSOR
• Purpose: HEALTH SERVICES RESEARCH
• Intervention Model: PARALLEL
• Sponsor Type: INDUSTRY
• Responsible Party: PRINCIPAL INVESTIGATOR
• PI Title: Principal Investigator

Study Record Dates

• First Submitted: July 13, 2026
• First Posted: July 22, 2026
• Study Start (Estimated): September 1, 2026
• Primary Completion (Estimated): June 1, 2027
• Study Completion (Estimated): September 1, 2027
• Last Updated: July 22, 2026

Record last verified: 2026-07