One-shot image diagnosis and multi-step conversational AI for medical interviewing
Official title: AI Medical Interviewing and Diagnostic System Performance Evaluation: One-Shot Vision Differential Diagnosis (OSVDE) and Multi-Step Conversational Non-Inferiority (MSCNE) Evaluation.
Run by Magic Health Inc. (d.b.a. Nolla Health) · NCT07470463 · Data updated 2026-11-12
This study tests whether a multimodal AI can match licensed clinicians at making diagnoses from de-identified images and simulated patient conversations.
Quick facts
| Study type | Observational |
|---|---|
| Ages | 18 Years and up |
| Sex | All |
| Enrollment | 30 (estimated) |
| Sponsor | Magic Health Inc. (d.b.a. Nolla Health) Industry-sponsored |
| Locations | 1 site (New York, New York) |
| Status | Recruiting |
| Started | March 19, 2026 |
| Main results expected | September 19, 2026 |
| Study ends | September 19, 2026 |
| Registry record updated | March 25, 2026 |
| Trial ID | NCT07470463 on ClinicalTrials.gov |
Is this trial a fit for you?
✓Likely a good fit
Ideal participants are licensed clinicians (e.g., dermatology, internal medicine, emergency medicine, ophthalmology, family medicine, pediatrics, and related specialties) who are 18 or older and can complete remote evaluation sessions.
✕Probably not a fit
Because this is an offline benchmark using de-identified images and simulated cases, patients will not receive direct clinical care benefits from participation.
A plain-English reading of the study's rules. Only the study team can confirm whether you qualify.
What this trial studies
The study benchmarks AIMD.1, a multimodal AI diagnostic system, against licensed clinicians using de-identified medical images and semi-synthetic patient simulations. It has two stages: One-Shot Vision Differential Evaluation (clinicians give ranked diagnoses from single images) and Multi-Step Conversational Non-Inferiority Evaluation (clinicians work through simulated multi-turn cases). Clinician diagnostic responses are collected prospectively and compared to the AI on identical tasks using retrospective public image datasets and simulated cases. All work is done offline with no impact on real-world patient care.
Why it matters
Potential benefit: If successful, the AI could help clinicians produce faster or more accurate differential diagnoses from images and conversational histories.
How similar studies have gone: Previous AI systems have matched or exceeded clinician performance for specific image-based tasks in fields like dermatology and ophthalmology, but multimodal conversational diagnostic systems are less well validated.
Who can join: the full rules
Show full inclusion / exclusion criteria
Inclusion Criteria: * Active license in Dermatology, Internal Medicine, Otolaryngology, Gynecology, Orthopedics, Pediatrics, Geriatrics, Emergency Medicine, Ophthalmology, Psychiatry, Endocrinology, Family Medicine, or a closely related specialty * Age 18 years or older * Ability to complete diagnostic evaluation sessions remotely using a computer or tablet with reliable internet access Exclusion Criteria: * Loss of active license in an eligible specialty * Inability to complete the evaluation session remotely
Where it's running
-
Nolla Health (Magic Health Inc.)
New York, New York, United States Recruiting
Study contacts
- Principal investigator: Luis R Soenksen, MSE, PhD — Nolla Health
- Study coordinator: Luis R Soenksen, MSE, PhD
- Email: soenksen@nollahealth.com
- Phone: (617) 936-9293
Similar studies
Other studies for the same condition or treatment. Recruiting studies are listed first.
-
Automated ABPI for Peripheral Artery Disease: A Pilot Look at Two Devices
This pilot checks if two automated ankle-brachial pressure index devices can reliably detect PAD across symptom levels and after bypass surgery, using patient and clinician feedback for practicality.
-
AI support in emergency medicine helps doctors make differential diagnoses
This study tests whether a generative AI tool can help emergency doctors arrive at more accurate differential diagnoses for adult patients at Karolinska University Hospital.
How to take part
- Review the eligibility criteria above with your treating physician.
- Check the official listing on ClinicalTrials.gov for the latest contact details and recruitment status.
- Contact the study coordinator or principal investigator to ask for pre-screening. Pre-screening is free and never obligates you to enroll.