Rare DisordersNCT07625436
Artificial Intelligence for General and Rare Disease Diagnosis
A study testing AI-Assisted Diagnosis in people with Rare Disorders and Rare Diseases, run by Peking Union Medical College Hospital at 11 sites in China.
Trial summary
A multicentre, randomised diagnostic accuracy study to evaluate whether the GENESIS AI diagnostic support system can improve diagnostic accuracy and efficiency for physicians managing real-world clinical general and rare cases. Read more about this study
- Who is it for?
- Ages 18 years and olderHealthy volunteers can take part
- Conditions the study is for
- Rare Disorders, Rare Diseases, Generalist AI
- What is being tested?
- AI-Assisted Diagnosis
- Could I receive a placebo?
- No, everyone receives an active treatment
- How many people
- 243 participants
- Where
- 11 sitesChina
- Study dates
- 10 Jun 2026to 19 Aug 2026
- Phase
- Interventional
- Are there results?
- None posted in the registry
Key requirements
Who can take part, as listed by the sponsor. Only the study team can confirm whether you are eligible, so take this list to your doctor.
- Ages 18 years and older
- All sexes
- Healthy volunteers accepted
- Adult, Older adult
Who may be able to join
- 1. Licensed physicians at the junior or senior level affiliated with internal medicine, neurology, pediatrics, and rare disease-related departments.
- 2. Willingness to provide written informed consent, adhere to trial protocols, and complete all required pre-study training prior to enrollment.
Who cannot join
- 1. Prior exposure to any of the clinical cases included in the study case library.
- 2. Direct participation in the design or development of the AI model.
Trial locations and contacts
11 sites in 1 country.
11 sites in 1 country
China11 sites
Cangzhou Central Hospital
Cangzhou
Dongguan People's Hospital
Dongguan
First People's Hospital of Foshan
Foshan
Guizhou Provincial People's Hospital
Guiyang
Jilin Central General Hospital
Jilin City
The First People's Hospital of Yunnan Province
Kunming
Tibet Autonomous Region People's Hospital
Lhasa
Fuping County Maternal and Child Hospital
Weinan
Wuhai People's Hospital
Wuhai
Qinghai Provincial People's Hospital
Xining
Zhangzhou Municipal Hospital of Fujian Province
Zhangzhou
About this study
Official title: A Multicentre, Randomised Diagnostic Accuracy Study Evaluating AI Assisted Diagnosis of General and Rare Diseases
A multicentre, randomised diagnostic accuracy study to evaluate whether the GENESIS AI diagnostic support system can improve diagnostic accuracy and efficiency for physicians managing real-world clinical general and rare cases.
Read the detailed description
Rare diseases collectively affect approximately 300 million individuals worldwide. This prolonged diagnostic delay is attributable in large part to the breadth of over 7,000 recognized rare conditions, which far exceeds the clinical exposure of any individual physician. GENESIS AI diagnostic support system was developed by Peking Union Medical College Hospital (PUMCH), supporting differential diagnosis generation, clinical workup planning, and genomic variant interpretation. A balanced crossover design ensures that each enrolled physician serves as their own control, substantially reducing confounding from inter-reader variability in baseline diagnostic competency. Within each physician, cases are randomly assigned at the case level to either the AI-assisted or unassisted condition, such that each physician reads a subset of cases with AI assistance and the remaining cases without. This within-reader, case-level randomization eliminates the need for a washout period and directly controls for inter-reader differences in baseline diagnostic competency. All cases are collected from real-world clinical settings with independently confirmed gold-standard diagnoses and span a pre-specified spectrum of rare and non-rare general disease categories, reflecting the differential diagnostic challenge encountered in routine clinical practice, to ensure diagnostic breadth and clinical representativeness. Diagnostic outputs are evaluated by an independent Expert Adjudication Committee, blinded to the assistance condition, using standardized scoring criteria established prior to data collection. Subgroup and exploratory analyses examined the consistency and variation of AI-assisted diagnostic performance across physician characteristics, institutional clinical capabilities, and case characteristics.
- Conditions
- Rare Disorders, Rare Diseases, Generalist AI
- Being tested
- AI-Assisted Diagnosis
- Keywords
- Rare Diseases, Artificial Intelligence, Clinical Decision Support System (CDSS), Diagnosis, generalist AI
- Medical subject headings
- Rare Diseases, Disease
What participants receive
What participants receive. In a randomised study each person is assigned to one group by chance.
AI-Assisted DiagnosisOther
The GENESIS diagnostic AI model is used to accept free text input and assist in general and rare disease diagnoses. During the experimental condition, physicians may interact with the system freely alongside standard clinical resources to support their diagnostic reasoning.
| Study group | Role | What they receive |
|---|---|---|
| Intervention Arm | Experimental | Physicians complete assigned diagnostic tasks with the assistance of AI system in addition to conventional clinical resources. Receives: Other: AI-Assisted Diagnosis |
| Control Arm | No intervention | Physicians complete the assigned diagnostic tasks using conventional clinical resources only (e.g., medical databases and literature), without access to any generative AI tools. This arm reflects routine clinical diagnostic practice. |
What is being measured
The primary outcome is the main question the study is designed to answer.
Top-3 Diagnostic Accuracy
The percentage of definitive diagnosis is included within the physician's top 3 choices.
Measured: Up to 60 minutes per case (from case presentation to diagnostic report submission).
Secondary outcomes (12)
Top-1 diagnostic accuracy
The percentage of definitive diagnosis is included within the physician's top 1 choice.
Measured: Up to 60 minutes per case (from case presentation to diagnostic report submission).
Top-5 Diagnostic Accuracy
The percentage of definitive diagnosis is included within the physician's top 5 choices.
Measured: Up to 60 minutes per case (upon completion of each case reading).
Diagnosis Time per Case
Elapsed time from initial case presentation to final diagnostic report submission, recorded automatically via system logs.
Measured: Up to 60 minutes per case (from case presentation to diagnostic report submission).
Workup Plan Quality
Quality score of the clinical workup plan assigned by an independent expert committee using a standardized Likert Scale. Scores range from 1 to 10, with higher scores indicating better workup plan quality.
Measured: Up to 60 minutes per case (from case presentation to diagnostic report submission).
Physician Reported Usability of the AI-Assisted Diagnostic System
Physician-reported usability of the AI system, assessed after completion of each AI-assisted case reading using a 10-point physician-rated usability scale. Scores range from 1 to 10, with higher scores indicating better system usability.
Measured: Up to 60 minutes per case (upon completion of each case reading).
Physician Reported Workload
Task-related workload experienced by physicians, assessed after completion of each AI-assisted case reading using a 10-point Physician Workload Likert scale. Scores range from 1 to 10, with higher scores indicating a higher workload.
Measured: Up to 60 minutes per case (upon completion of each case reading).
Physician Satisfaction
Overall satisfaction of physicians with the diagnostic workflow, assessed after completion of each AI-assisted case reading using a 10-point Satisfaction Likert scale. Scores range from 1 to 10, with higher scores indicating higher satisfaction.
Measured: Up to 60 minutes per case (upon completion of each case reading).
Physician Intention to Adopt AI-Assisted Diagnostic Support
Physician willingness to integrate AI system into routine clinical practice, assessed after completion of each AI-assisted case reading using a 10-point Adoption Intention Likert scale. Scores range from 1 to 10, with higher scores indicating higher adoption intention.
Measured: Up to 60 minutes per case (upon completion of each case reading).
Physician-Reported Diagnostic Confidence
Physician-reported confidence in the final differential diagnosis, assessed after completion of each AI-assisted case reading using a 10-point physician-rated usability scale. Scores range from 1 to 10, with higher scores indicating higher confidence.
Measured: Up to 60 minutes per case (upon completion of each case reading).
Physician-Reported Workup Plan Confidence
Physician-reported confidence in the workup plan, assessed after completion of each AI-assisted case reading using a 10-point physician-rated usability scale. Scores range from 1 to 10, with higher scores indicating higher confidence.
Measured: Up to 60 minutes per case (upon completion of each case reading).
Physician-Reported Diagnostic Reasoning Clarity
Physician-reported clarity of the reasoning underlying the differential diagnosis, assessed after completion of each AI-assisted case reading using a 10-point physician-rated usability scale. Scores range from 1 to 10, with higher scores indicating better clarity.
Measured: Up to 60 minutes per case (upon completion of each case reading).
Physician-Reported Evidence Clarity
Physician-reported clarity of clarity of the clinical evidence supporting the diagnostic assessment, assessed after completion of each AI-assisted case reading using a 10-point physician-rated usability scale. Scores range from 1 to 10, with higher scores indicating better clarity.
Measured: Up to 60 minutes per case (upon completion of each case reading).
Timeline
From the start of the study to its completion; the mark is today. Estimated dates are the sponsor’s plan.
- First posted4 Jun 2026
- Study start10 Jun 2026
- Primary completion19 Aug 2026
- Study completion19 Aug 2026
Resources
- Official record on ClinicalTrials.govThe registry entry this page is built from, with its full change history.
- Other trials for Rare DisordersStudies of the same condition, open and under way.
- More trials run by Peking Union Medical College HospitalThe sponsor's other registered studies.
- What the trial phases meanHow a treatment moves from first tests in people to approval.
More details
For doctors and researchers: how the study is designed, who runs it, and its registry IDs.
Study design
- Study type
- Interventional
- Phase
- Phase N/A
- Primary purpose
- Diagnosis
- Allocation
- Randomised
- Intervention model
- Crossover
- Model description
- Within-reader randomised, incomplete-crossed multi-reader multi-case design; each physician evaluates different cases under the two conditions, and each case is evaluated by multiple physicians.
- Masking
- Single blind
- Who is masked
- Outcomes assessor
- Enrolment
- 243 participants (actual)
Sponsor and investigators
- Lead sponsor
- Peking Union Medical College Hospital
- Sponsor type
- University, hospital or other
- Collaborators
- Cangzhou Central Hospital, Zhangzhou Municipal Hospital of Fujian Province, Dongguan People's Hospital, First People's Hospital of Foshan, Tibet Autonomous Region People's Hospital, Guizhou Provincial People's Hospital, The First People's Hospital of Yunnan, Qinghai People's Hospital, Tianshui 407 Hospital, Wuhai People's Hospital, Fuping County Maternal and Child Hospital
- Responsible party
- Principal investigator, Shuyang Zhang, MD, PhD, Peking Union Medical College Hospital
- Investigators
- Shuyang Zhang, Principal investigator, Peking Union Medical College Hospital
IDs, dates and publications
- ClinicalTrials.gov ID
- NCT07625436
- Sponsor's protocol ID
- PUMCH I-23PJ948
- Status last verified
- Oct 2026
- First submitted
- 28 May 2026
- Last updated
- 14 Oct 2026
- Results posted
- No
- Data monitoring committee
- Yes
- FDA-regulated drug
- No
- FDA-regulated device
- No
Study at a glance
From the registry record, last updated by the sponsor on 14 Oct 2026. Recruitment status is as the sponsor reported it: confirm with the study team.
- Official title
- A Multicentre, Randomised Diagnostic Accuracy Study Evaluating AI Assisted Diagnosis of General and Rare Diseases
- ClinicalTrials.gov ID
- NCT07625436
- Acronym / sponsor ID
- PUMCH I-23PJ948
- Conditions
- Rare Disorders, Rare Diseases, Generalist AI
- Keywords
- Rare Diseases, Artificial Intelligence, Clinical Decision Support System (CDSS), Diagnosis, generalist AI
- Study type
- Interventional
- Recruitment status
- Completed
- Enrolment
- 243 participants (actual)
- Lead sponsor
- Peking Union Medical College HospitalUniversity, hospital or other
- Collaborators
- Cangzhou Central Hospital, Zhangzhou Municipal Hospital of Fujian Province, Dongguan People's Hospital, First People's Hospital of Foshan, Tibet Autonomous Region People's Hospital, Guizhou Provincial People's Hospital, The First People's Hospital of Yunnan, Qinghai People's Hospital, Tianshui 407 Hospital, Wuhai People's Hospital, Fuping County Maternal and Child Hospital
- Study start
- 10 Jun 2026 (actual)
- Primary completion
- 19 Aug 2026 (actual)
- Study completion
- 19 Aug 2026 (actual)
- First posted
- 4 Jun 2026 (actual)
- Results
- Not posted in the source record
Clinical summary
The research question as the sponsor registered it. This describes what the study plans to test, not what it found.
A multicentre, randomised diagnostic accuracy study to evaluate whether the GENESIS AI diagnostic support system can improve diagnostic accuracy and efficiency for physicians managing real-world clinical general and rare cases.
Detailed description
Rare diseases collectively affect approximately 300 million individuals worldwide. This prolonged diagnostic delay is attributable in large part to the breadth of over 7,000 recognized rare conditions, which far exceeds the clinical exposure of any individual physician. GENESIS AI diagnostic support system was developed by Peking Union Medical College Hospital (PUMCH), supporting differential diagnosis generation, clinical workup planning, and genomic variant interpretation. A balanced crossover design ensures that each enrolled physician serves as their own control, substantially reducing confounding from inter-reader variability in baseline diagnostic competency. Within each physician, cases are randomly assigned at the case level to either the AI-assisted or unassisted condition, such that each physician reads a subset of cases with AI assistance and the remaining cases without. This within-reader, case-level randomization eliminates the need for a washout period and directly controls for inter-reader differences in baseline diagnostic competency. All cases are collected from real-world clinical settings with independently confirmed gold-standard diagnoses and span a pre-specified spectrum of rare and non-rare general disease categories, reflecting the differential diagnostic challenge encountered in routine clinical practice, to ensure diagnostic breadth and clinical representativeness. Diagnostic outputs are evaluated by an independent Expert Adjudication Committee, blinded to the assistance condition, using standardized scoring criteria established prior to data collection. Subgroup and exploratory analyses examined the consistency and variation of AI-assisted diagnostic performance across physician characteristics, institutional clinical capabilities, and case characteristics.
Study design
- Primary purpose
- Diagnosis
- Allocation
- Randomised
- Intervention model
- Crossover
- Masking
- Single blind (outcomes assessor)
- Number of arms
- 2
- Model description
- Within-reader randomised, incomplete-crossed multi-reader multi-case design; each physician evaluates different cases under the two conditions, and each case is evaluated by multiple physicians.
| Arm | Type | Receives |
|---|---|---|
| Intervention Arm | Experimental | Other: AI-Assisted DiagnosisPhysicians complete assigned diagnostic tasks with the assistance of AI system in addition to conventional clinical resources. |
| Control Arm | No intervention | –Physicians complete the assigned diagnostic tasks using conventional clinical resources only (e.g., medical databases and literature), without access to any generative AI tools. This arm reflects routine clinical diagnostic practice. |
Who may qualify
- Ages
- 18 years and older
- Sex
- All
- Healthy volunteers
- Accepted
- Age groups
- Adult, Older adult
Key inclusion criteria (2 listed)
- 1. Licensed physicians at the junior or senior level affiliated with internal medicine, neurology, pediatrics, and rare disease-related departments.
- 2. Willingness to provide written informed consent, adhere to trial protocols, and complete all required pre-study training prior to enrollment.
Key exclusion criteria (2 listed)
- 1. Prior exposure to any of the clinical cases included in the study case library.
- 2. Direct participation in the design or development of the AI model.
Eligibility is decided by the study team after screening; this overview does not establish that a patient qualifies. Full inclusion and exclusion criteria.
Interventions
| Intervention | Type | Arms |
|---|---|---|
| AI-Assisted DiagnosisThe GENESIS diagnostic AI model is used to accept free text input and assist in general and rare disease diagnoses. During the experimental condition, physicians may interact with the system freely alongside standard clinical resources to support their diagnostic reasoning. | Other | Intervention Arm |
Primary outcome
Top-3 Diagnostic Accuracy
Time frame: Up to 60 minutes per case (from case presentation to diagnostic report submission).
The percentage of definitive diagnosis is included within the physician's top 3 choices.
12 secondary outcomes
Top-1 diagnostic accuracy
Time frame: Up to 60 minutes per case (from case presentation to diagnostic report submission).
Top-5 Diagnostic Accuracy
Time frame: Up to 60 minutes per case (upon completion of each case reading).
Diagnosis Time per Case
Time frame: Up to 60 minutes per case (from case presentation to diagnostic report submission).
Workup Plan Quality
Time frame: Up to 60 minutes per case (from case presentation to diagnostic report submission).
Physician Reported Usability of the AI-Assisted Diagnostic System
Time frame: Up to 60 minutes per case (upon completion of each case reading).
Physician Reported Workload
Time frame: Up to 60 minutes per case (upon completion of each case reading).
Physician Satisfaction
Time frame: Up to 60 minutes per case (upon completion of each case reading).
Physician Intention to Adopt AI-Assisted Diagnostic Support
Time frame: Up to 60 minutes per case (upon completion of each case reading).
Physician-Reported Diagnostic Confidence
Time frame: Up to 60 minutes per case (upon completion of each case reading).
Physician-Reported Workup Plan Confidence
Time frame: Up to 60 minutes per case (upon completion of each case reading).
Physician-Reported Diagnostic Reasoning Clarity
Time frame: Up to 60 minutes per case (upon completion of each case reading).
Physician-Reported Evidence Clarity
Time frame: Up to 60 minutes per case (upon completion of each case reading).
Results and safety
The study is completed, but results are not available in the source record. That does not mean the treatment did or did not work.
Research links
- Official record on ClinicalTrials.govLast updated by the sponsor 14 Oct 2026.
Related trials for Rare Disorders
RecruitingObservational study
Genome Medical Sequencing for Gene Discovery
Intellectual Disabilities, Congenital Anomaly
RecruitingObservational study
The KidneyCARE (Community Access to Research Equity) Study
Chronic Kidney Disease, Dialysis
RecruitingObservational study
Characterization of Patients With Uncommon Presentations and/or Uncommon Diseases Associated With the Cardiovascular System
Metabolic Disease, Obesity
RecruitingObservational study
Clinical and Genetic Evaluation of Individuals With Undiagnosed Disorders Through the Undiagnosed Diseases Network
Genetic Disease
RecruitingPhase 2
Testing the Effectiveness of Two Immunotherapy Drugs (Nivolumab and Ipilimumab) With One Anti-cancer Targeted Drug (Cabozantinib) for Rare Genitourinary Tumors
Bladder Adenocarcinoma, Bladder Clear Cell Adenocarcinoma
Referral and contact
AzTrials does not enrol participants or take referrals. Contact the study team or a site listed below; they decide who can take part. This study is not recruiting at the moment.
Shuyang Zhang principal investigator
Peking Union Medical College Hospital
11 sites in 1 country: see every site and its status.
Questions about this trial
What is this clinical trial studying?
A study testing AI-Assisted Diagnosis in people with Rare Disorders and Rare Diseases, run by Peking Union Medical College Hospital at 11 sites in China.
The full registered description is in the About this study section and the official record.
Who may be eligible to take part?
The sponsor lists 2 inclusion and 2 exclusion criteria. Eligibility is decided by the study team after screening, so read the full criteria and contact a listed site.
Is this clinical trial currently recruiting?
The record says: finished, as of the sponsor's last update on 14 Oct 2026. Status can change between updates, so confirm with the study contact before making plans.
Where is the study taking place?
The record lists 11 sites in China. Whether a site is taking part right now should be confirmed with that site. See every site.
What are the possible benefits and risks?
They depend on the study and the treatment, and no study can promise a benefit. The study team explains the known risks during informed consent, before anyone joins; the record itself does not list them.
Are results available for this study?
The study is completed, but results are not available in the source record. That does not mean the treatment did or did not work.
How can a doctor refer a patient or contact the research team?
The record lists no contact. The official record names the sponsor, who can be asked directly. AzTrials does not enrol participants or take referrals.
What does the primary outcome measure?
Top-3 Diagnostic Accuracy (time frame: Up to 60 minutes per case (from case presentation to diagnostic report submission).). It is what the study was designed to measure, not a finding.
Where can I read the original study information?
Does a listing mean the treatment is approved or proven to work?
No. A listing means the study is registered. It does not show that the treatment is safe, works, or is approved by a regulator.
How often is this information updated?
AzTrials copies changed records from ClinicalTrials.gov every night and reloads the whole registry every week. The sponsor last updated this record on 14 Oct 2026.