+1 877 705 1914• 24 / 7
HIPAA Compliant
ISO 27001 Certified

Actively Recruiting

Age: 18Years +
All Genders
Healthy Volunteers
ID07470463

Performance Evaluation of AIMD.1 AI Diagnostic System Compared to Licensed Clinicians Using Medical Images and Patient Simulations

Led by Magic Health Inc. (d.b.a. Nolla Health) · Updated on 2026-03-25

30

Participants Needed

1

Research Sites

N/A

Total Duration

AI-Summary

What This Trial Is About

Researchers are evaluating the diagnostic performance of a multimodal artificial intelligence AI system called AIMD.1. This AI system is designed to assist clinical reasoning by analyzing medical images and engaging in structured conversational diagnostic interactions. The study compares the AI systems performance with licensed clinicians using de-identified medical images and semi-synthetic patient simulations in a controlled, offline research environment. The goal is to benchmark the AI systems diagnostic accuracy before any real-world clinical use. The study consists of two main evaluation stages. In the first stage, the One-Shot Vision Differential Evaluation OSVDE, clinicians and the AI independently review individual de-identified medical images and generate a ranked list of possible diagnoses based on visual features alone. The image set includes roughly 11,500 to 15,000 images from multiple medical specialties and diverse disease categories. In the second stage, the Multi-Step Conversational Non-Inferiority Evaluation MSCNE, both clinicians and the AI complete diagnostic tasks using semi-synthetic patient simulations delivered through a conversational interface, allowing assessment of multi-step diagnostic reasoning similar to real clinical encounters. Approximately 10 to 30 licensed clinicians participate by completing diagnostic sessions remotely via computer or tablet with reliable internet. Sessions last 60 to 90 minutes in total, during which clinicians provide differential diagnoses for selected image and simulation cases. Researchers collect data on diagnostic accuracy, confidence calibration, and time-to-diagnosis, comparing clinician and AI performance. Clinicians are compensated for their time, and all data is anonymized. The study is expected to take about six months, involving data preparation, evaluation stages, analysis, and reporting.

CONDITIONS

Brief Title

Evaluation of One-Shot Vision Differential Diagnosis (OSVDE) and Multi-Step Conversational Non-Inferiority (MSCNE) in AI Medical Interviewing

Research Team

L

Luis R Soenksen, MSE, PhD

S

Sean Geiger, B.S.

Not the Right Trial for You?

Explore thousands of other clinical trials that might be a better match.
Sign up to get personalized trial recommendations delivered to your inbox.

Already have an account? Log in here