DeepMedFake-Assisted Detection of Synthetic and Discordant Medical Images
12 de septiembre de 2026 actualizado por: Lv, Han, Beijing Friendship Hospital
Evaluation of the Clinical Performance and Multi-Setting Application of an AI-Based Medical Image Verification System
This prospective randomized controlled trial will evaluate whether DeepMedFake improves the identification of medical images that require further verification.
DeepMedFake is an artificial intelligence-based medical image analysis system that provides an image-authenticity risk assessment, a patient-image consistency risk assessment and a recommendation regarding further verification.
Hospital physicians and healthcare audit professionals will participate in a randomized two-period crossover design.
Each participant will assess one case set with DeepMedFake assistance and the other without AI assistance.
The primary outcome in each cohort is the sensitivity of the final verification decision, evaluated separately in the hospital clinical and healthcare audit cohorts.
Descripción general del estudio
Estado
Aún no reclutando
Condiciones
Intervención / Tratamiento
Tipo de estudio
Intervencionista
Inscripción (Estimado)
64
Fase
- No aplica
Contactos y Ubicaciones
Esta sección proporciona los datos de contacto de quienes realizan el estudio e información sobre dónde se lleva a cabo este estudio.
Estudio Contacto
- Nombre: Han Lv
- Número de teléfono: +8613901073227
- Correo electrónico: chrislvhan@126.com
Ubicaciones de estudio
-
-
Beijing Municipality
-
Beijing, Beijing Municipality, Porcelana, 100050
- Beijing Friendship hospital, Capital Medical University
-
Contacto:
- Han Lv, Professor
- Número de teléfono: +8613901073227
- Correo electrónico: chrislvhan@126.com
-
-
Criterios de participación
Los investigadores buscan personas que se ajusten a una determinada descripción, denominada criterio de elegibilidad. Algunos ejemplos de estos criterios son el estado de salud general de una persona o tratamientos previos.
Criterio de elegibilidad
Edades elegibles para estudiar
- Adulto
- Adulto Mayor
Acepta Voluntarios Saludables
Sí
Descripción
Inclusion Criteria:
- Aged 18 years or older.
- Able to complete reading periods and all required electronic study procedures.
- Completed the standardized study training and practice cases.
Provided written informed consent before participation.
（1）Hospital clinical cohort participants must also meet the following criteria:
- Hold a valid physician qualification.
- Currently practice in ophthalmology, radiology, ultrasound medicine, or a clinical specialty in which imaging of the neurological or cerebrovascular, cardiovascular, thoracic, abdominal, or musculoskeletal domain is routinely reviewed.
- Have direct professional experience reviewing all imaging modalities and clinical imaging domains assigned to them in the study.
Routinely use the assigned medical images for image interpretation, image verification or clinical decision-making.
（2）Healthcare audit cohort participants must also meet the following criteria:
- Currently work in healthcare audit, medical reimbursement review, medical-cost review or medical-material verification.
- Have experience reviewing medical imaging materials as part of their routine work.
- Have knowledge required to interpret the medical images and patient information presented in the study and to determine whether further verification is required.
Exclusion Criteria:
- Direct involvement in development of the locked DeepMedFake model, determination of model weights or selection of decision thresholds.
- Direct involvement in selection or construction of the formal case library or adjudication of the reference standard.
- Direct involvement in generation or implementation of the reader randomization sequence.
- Previous participation as a reader in the pilot study.
- Previous access to any formal study case, case-construction record or reference-standard label.
- Access to undisclosed study information that could permit advance identification of case type or image-generation method.
- A financial, professional or other conflict of interest considered likely to compromise independent case assessment.
Plan de estudios
Esta sección proporciona detalles del plan de estudio, incluido cómo está diseñado el estudio y qué mide el estudio.
¿Cómo está diseñado el estudio?
Detalles de diseño
- Propósito principal: Otro
- Asignación: Aleatorizado
- Modelo Intervencionista: Asignación cruzada
- Enmascaramiento: Único
Armas e Intervenciones
Grupo de participantes/brazo |
Intervención / Tratamiento |
|---|---|
|
Experimental: Crossover Sequence A
Participants undergo unassisted review of case set S1 during Period 1, followed by DeepMedFake-assisted review of case set S2 during Period 2.
|
DeepMedFake is an artificial intelligence-based medical image analysis system designed to support the detection of synthetic medical images and authentic medical images paired with discordant patient information.
It provides an image-authenticity risk assessment, a patient-image consistency risk assessment and a recommendation regarding further verification.
In this study, DeepMedFake is used as a decision-support tool to assist participants in determining whether the image requires further verification before downstream clinical or healthcare audit use.
Final judgments and verification decisions are made by the participants.
|
|
Experimental: Crossover Sequence B
Participants undergo DeepMedFake-assisted review of case set S1 during Period 1, followed by unassisted review of case set S2 during Period 2.
|
DeepMedFake is an artificial intelligence-based medical image analysis system designed to support the detection of synthetic medical images and authentic medical images paired with discordant patient information.
It provides an image-authenticity risk assessment, a patient-image consistency risk assessment and a recommendation regarding further verification.
In this study, DeepMedFake is used as a decision-support tool to assist participants in determining whether the image requires further verification before downstream clinical or healthcare audit use.
Final judgments and verification decisions are made by the participants.
|
|
Experimental: Crossover Sequence C
Participants undergo unassisted review of case set S2 during Period 1, followed by DeepMedFake-assisted review of case set S1 during Period 2.
|
DeepMedFake is an artificial intelligence-based medical image analysis system designed to support the detection of synthetic medical images and authentic medical images paired with discordant patient information.
It provides an image-authenticity risk assessment, a patient-image consistency risk assessment and a recommendation regarding further verification.
In this study, DeepMedFake is used as a decision-support tool to assist participants in determining whether the image requires further verification before downstream clinical or healthcare audit use.
Final judgments and verification decisions are made by the participants.
|
|
Experimental: Crossover Sequence D
Participants undergo DeepMedFake-assisted review of case set S2 during Period 1, followed by unassisted review of case set S1 during Period 2.
|
DeepMedFake is an artificial intelligence-based medical image analysis system designed to support the detection of synthetic medical images and authentic medical images paired with discordant patient information.
It provides an image-authenticity risk assessment, a patient-image consistency risk assessment and a recommendation regarding further verification.
In this study, DeepMedFake is used as a decision-support tool to assist participants in determining whether the image requires further verification before downstream clinical or healthcare audit use.
Final judgments and verification decisions are made by the participants.
|
¿Qué mide el estudio?
Medidas de resultado primarias
Medida de resultado |
Medida Descripción |
Periodo de tiempo |
|---|---|---|
|
Reader Performance With and Without DeepMedFake Assistance: Sensitivity of the Final Verification Decision in the Hospital Clinical Cohort
Periodo de tiempo: During both reading periods, up to 4 weeks after randomization
|
The percentage of reference-standard abnormal cases assigned to further verification by hospital physicians will be estimated under DeepMedFake-assisted and unassisted review.
The effect measure is the absolute percentage-point difference between review conditions.
|
During both reading periods, up to 4 weeks after randomization
|
|
Reader Performance With and Without DeepMedFake Assistance: Sensitivity of the Final Verification Decision in the Healthcare Audit Cohort
Periodo de tiempo: During both reading periods, up to 4 weeks after randomization
|
The percentage of reference-standard abnormal cases assigned to further verification by healthcare audit professionals will be estimated under DeepMedFake-assisted and unassisted review.
The effect measure is the absolute percentage-point difference between review conditions.
|
During both reading periods, up to 4 weeks after randomization
|
Medidas de resultado secundarias
Medida de resultado |
Medida Descripción |
Periodo de tiempo |
|---|---|---|
|
Reader Performance With and Without DeepMedFake Assistance: Specificity of the Final Verification Decision in the Hospital Clinical Cohort
Periodo de tiempo: During both reading periods, up to 4 weeks after randomization
|
The percentage of authentic, information-matched cases assigned to no further verification by hospital physicians will be estimated under each review condition and compared between conditions.
|
During both reading periods, up to 4 weeks after randomization
|
|
Reader Performance With and Without DeepMedFake Assistance: Specificity of the Final Verification Decision in the Healthcare Audit Cohort
Periodo de tiempo: During both reading periods, up to 4 weeks after randomization
|
The percentage of authentic, information-matched cases assigned to no further verification by healthcare audit professionals will be estimated under each review condition and compared between conditions.
|
During both reading periods, up to 4 weeks after randomization
|
|
Sensitivity of the Final Verification Decision for Synthetic Medical Image Cases
Periodo de tiempo: During both reading periods, up to 4 weeks after randomization
|
The percentage of reference-standard synthetic-image cases assigned to further verification will be estimated under each review condition.
DeepMedFake-assisted and unassisted review will be compared separately within the hospital clinical and healthcare audit cohorts.
|
During both reading periods, up to 4 weeks after randomization
|
|
Sensitivity of the Final Verification Decision in Discordant Cases
Periodo de tiempo: During both reading periods, up to 4 weeks after randomization
|
The percentage of authentic images paired with discordant patient information that are assigned to further verification will be estimated under each review condition.
DeepMedFake-assisted and unassisted review will be compared separately within the hospital clinical and healthcare audit cohorts.
|
During both reading periods, up to 4 weeks after randomization
|
|
Sensitivity of the Image-Authenticity Judgment
Periodo de tiempo: During both reading periods, up to 4 weeks after randomization
|
The percentage of reference-standard synthetic-image cases classified as suspected synthetic images will be estimated under each review condition and compared separately within each reader cohort.
|
During both reading periods, up to 4 weeks after randomization
|
|
Specificity of the Image-Authenticity Judgment
Periodo de tiempo: During both reading periods, up to 4 weeks after randomization
|
The percentage of reference-standard authentic-image cases classified as not suspected to be synthetic will be estimated under each review condition and compared separately within each reader cohort.
|
During both reading periods, up to 4 weeks after randomization
|
|
Sensitivity of the Patient-Image Consistency Judgment
Periodo de tiempo: During both reading periods, up to 4 weeks after randomization
|
Among authentic images, the percentage of discordant cases classified as discordant with the displayed patient information will be estimated under each review condition and compared separately within each reader cohort.
Synthetic-image cases will be excluded from this analysis.
|
During both reading periods, up to 4 weeks after randomization
|
|
Specificity of the Patient-Image Consistency Judgment
Periodo de tiempo: During both reading periods, up to 4 weeks after randomization
|
Among authentic images, the percentage of information-matched cases classified as matching the displayed patient information will be estimated under each review condition and compared separately within each reader cohort.
Synthetic-image cases will be excluded from this analysis.
|
During both reading periods, up to 4 weeks after randomization
|
|
Case-Level Workflow Time
Periodo de tiempo: During both reading periods, up to 4 weeks after randomization
|
Elapsed time in seconds from successful case loading to submission of the final required case-level response, including selection of a proposed first verification pathway when required.
Recorded pauses will be excluded.
Workflow time will be compared between review conditions separately within each reader cohort.
|
During both reading periods, up to 4 weeks after randomization
|
Colaboradores e Investigadores
Aquí es donde encontrará personas y organizaciones involucradas en este estudio.
Patrocinador
Fechas de registro del estudio
Estas fechas rastrean el progreso del registro del estudio y los envíos de resultados resumidos a ClinicalTrials.gov. Los registros del estudio y los resultados informados son revisados por la Biblioteca Nacional de Medicina (NLM) para asegurarse de que cumplan con los estándares de control de calidad específicos antes de publicarlos en el sitio web público.
Fechas importantes del estudio
Inicio del estudio (Estimado)
20 de septiembre de 2026
Finalización primaria (Estimado)
20 de octubre de 2026
Finalización del estudio (Estimado)
31 de octubre de 2026
Fechas de registro del estudio
Enviado por primera vez
12 de septiembre de 2026
Primero enviado que cumplió con los criterios de control de calidad
12 de septiembre de 2026
Publicado por primera vez (Actual)
16 de septiembre de 2026
Actualizaciones de registros de estudio
Última actualización publicada (Actual)
16 de septiembre de 2026
Última actualización enviada que cumplió con los criterios de control de calidad
12 de septiembre de 2026
Última verificación
1 de septiembre de 2026
Más información
Términos relacionados con este estudio
Palabras clave
Otros números de identificación del estudio
- 2026-P2-308-01
Plan de datos de participantes individuales (IPD)
¿Planea compartir datos de participantes individuales (IPD)?
NO
Información sobre medicamentos y dispositivos, documentos del estudio
Estudia un producto farmacéutico regulado por la FDA de EE. UU.
No
Estudia un producto de dispositivo regulado por la FDA de EE. UU.
No
Esta información se obtuvo directamente del sitio web clinicaltrials.gov sin cambios. Si tiene alguna solicitud para cambiar, eliminar o actualizar los detalles de su estudio, comuníquese con register@clinicaltrials.gov. Tan pronto como se implemente un cambio en clinicaltrials.gov, también se actualizará automáticamente en nuestro sitio web. .