This trial is no longer recruiting.My employer runs this trial

ANCHOR AI for AI-assisted Healthcare

SB
Overseen BySanjay Basu, MD, PhD
Age: 18+
Sex: Any
Trial Phase: Academic
Sponsor: Waymark
No Placebo GroupAll trial participants will receive the active study treatment (no placebo)

What You Need to Know Before You Apply

What is the purpose of this trial?

This trial aims to improve patient safety by testing whether an AI tool called ANCHOR (Clinical AI Verification Layer) can reduce medical errors during doctor appointments. The study will compare traditional care, care assisted by a tool called Gemini, and care where Gemini is enhanced by ANCHOR. Suitable candidates for this trial include individuals who have had two or more emergency visits or one hospitalization in the past year, have multiple chronic conditions, and are under the care of a participating provider in Ohio, Washington, or Virginia. The trial seeks to determine how each method affects safety in medical decision-making for high-risk patients. As an unphased trial, it offers patients the chance to contribute to innovative research that could enhance healthcare safety and quality.

Will I have to stop taking my current medications?

The trial information does not specify whether you need to stop taking your current medications. However, since the trial involves high-risk patients with multiple medications, it seems likely that you can continue your current medications.

Is there any evidence suggesting that this trial's treatments are likely to be safe?

In other studies, Gemini 3.1 Pro has proven safe for use in healthcare settings. Safety checks of this AI model revealed no new risks compared to the original version. Many health systems already use it, indicating that healthcare professionals generally find it reliable.

For ANCHOR, a newer addition, the safety details remain less clear. However, it is designed to provide an extra layer of checking to Gemini 3.1 Pro's results, which is expected to reduce errors in clinical settings. Available data show no reports of problems directly linked to ANCHOR itself. This treatment is in an early testing phase, focusing on practical use, suggesting it is considered safe enough for broader testing.12345

Why are researchers excited about this trial?

Researchers are excited about the ANCHOR AI for AI-assisted Healthcare trial because it explores new ways to enhance clinical decision-making using artificial intelligence. Unlike current standard care, which relies solely on physician judgment, the Gemini 3.1 Pro system offers AI-generated care recommendations, providing decision-support that can streamline and enhance clinical workflows. The addition of the ANCHOR Clinical AI Verification Layer further distinguishes this approach by adding a layer of verification that uses a comprehensive set of clinical rules and specialist agents to ensure the AI's recommendations are safe and accurate. This innovative system aims to support healthcare providers in making more informed decisions, potentially improving patient outcomes and efficiency in healthcare delivery.

What evidence suggests that this trial's treatments could be effective?

Research has shown that the Gemini 3.1 Pro model, when used with a safety prompt, can help doctors make better diagnoses. Studies have found that this model's problem-solving ability surpasses earlier versions, achieving scores as high as 77.1% on complex tasks. This capability provides more reliable advice to doctors. In this trial, some participants will receive care using the Gemini 3.1 Pro model alone.

Another group will receive care with the addition of ANCHOR, a system that double-checks information to enhance these improvements. ANCHOR includes expert tools that identify drug interactions and ensure treatments follow guidelines, potentially reducing mistakes in medical decisions. While researchers continue to collect data, these features aim to improve patient safety by making clinical assessments more thorough and accurate.56789

Who Is on the Research Team?

SB

Sanjay Basu, MD, PhD

Principal Investigator

Waymark

Are You a Good Fit for This Trial?

This trial is for adults (18+) who are considered high-risk patients—such as those with recent hospital visits, multiple medications, or chronic conditions—receiving care from a participating Waymark provider in Ohio, Washington, or Virginia. Only clinical encounters needing medical decision-making are included.

Inclusion Criteria

2. Attributed to a participating Waymark provider (academic medical center, community-hospital network, federally qualified health center, or independent physician practice in Ohio, Washington, or Virginia; full TIN-consolidated list deposited at the Open Science Framework).
3. Meets high-risk multidisciplinary criteria (combined claims-based and clinical: 2 or more emergency-department visits or 1 or more hospitalization in the prior 12 months, 5 or more active medications, 2 or more active specialist relationships, 2 or more chronic conditions, or claims-based equivalents).
4. Encounter occurs in one of the three Waymark service modalities: high-risk primary care, specialty care coordination, or real-time telemedicine urgent care.
See 3 more

Timeline for a Trial Participant

Screening

Participants are screened for eligibility to participate in the trial

2-4 weeks

Active Enrollment

Randomization of 240 patients across three arms over a 12-week period

12 weeks
Multiple encounters per patient

Follow-up

Participants are monitored for safety and effectiveness after treatment

4 weeks
Outcome adjudication within 4 weeks post-encounter

30-day Monitoring

Monitoring for emergency department visits and hospitalizations within 30 days post-randomization

30 days

What Are the Treatments Tested in This Trial?

Interventions

  • ANCHOR Clinical AI Verification Layer
  • Gemini 3.1 Pro with Safety Prompt

Trial Overview

The study compares three approaches to supporting doctors during high-risk patient visits: standard care without AI help; using Gemini 3.1 Pro AI with safety prompts; and adding an extra ANCHOR verification layer to the AI system. Patients are randomly assigned to one of these groups.

How Is the Trial Designed?

3

Treatment groups

Experimental Treatment

Active Control

Group I: Arm 3 - Gemini 3.1 Pro + ANCHOR (intervention)Experimental Treatment1 Intervention
Group II: Arm 1 - Unassisted standard care (control)Active Control1 Intervention
Group III: Arm 2 - Gemini 3.1 Pro with safety prompt (active comparator)Active Control1 Intervention

Find a Clinic Near You

Who Is Running the Clinical Trial?

Waymark

Lead Sponsor

Trials
1
Recruited
180+

Citations

Gemini 3.1 Pro: A smarter model for your most complex tasks

... 3.1 Pro achieved a verified score of 77.1%. This is more than double the reasoning performance of 3 Pro. Side-by-side comparison of ...

A systematic review on the generative AI applications in ... - PMC

Recent reviews highlight the growing impact of ML approaches in biomedical fields, including applications in diagnosing rare diseases and improving clinical ...

Gemini 3.1 Pro

Better tool use. Simultaneous, multi-step tasks. Gemini 3.1's agentic capabilities can build more helpful and intelligent personal AI assistants.

structured AI standardized patients for clinical ...

Reporting guideline for the early-stage clinical evaluation of decision support systems driven by artificial intelligence: DECIDE-AI. Nature.

Gemini 3 Pro and Gemini 3.1 Pro vs GPT-5.1 and GPT-5.2 ...

Compare GPT-5.1, GPT-5.2, Gemini 3 Pro and Gemini 3.1 Pro for clinical AI workflows now available in CompliantChatGPT. Understand key differences, features ...

ANCHOR Validation Trial in High-Risk Multidisciplinary Care

Arm 2 (Gemini 3.1 Pro with safety prompt, n=80): Gemini 3.1 Pro generates the recommendation under a clinical-safety system prompt, content ...

Gemini 3 in Healthcare: An Analysis of Its Capabilities

We then examine how Gemini 3 (and related Google AI tools) are being used or developed for drug discovery, clinical care, and healthcare ...

MedMisBench: Measuring Epistemic Resilience of LLMs ...

To assess whether search and self-verification can restore epistemic resilience, we evaluate Gemini-3.1-pro-preview and Gemini-3.1-flash-lite- ...

structured AI standardized patients for clinical ...

Clinical communication skills are fundamental to patient safety, yet their develop- ment requires deliberate practice with realistic patient ...