AI System for Anatomic Recognition & Lesion Detection in Nasopharyngolaryngoscopy: A Prospective Study
Trial statusRecruiting
Trial phaseNot listed
Trial typeObservational
Biological sexAll
Age18+
SponsorRuijin Hospital
About this trial
An artificial intelligence-assisted system is trained and validated by collecting nasopharyngolaryngoscopy images from patients.
Eligibility criteria
This trial does not accept healthy volunteersQualifiers
Age ≥ 18 years;
Underwent standard electronic nasopharyngolaryngoscopy;
Patients who underwent biopsy sampling have a clear pathological diagnosis;
Signed a written informed consent form.
Disqualifiers
Image quality is substandard with severe motion artifacts;
Lesion images are unclear and incomplete.
Trial population
Image data of patients who underwent nasopharyngolaryngoscopy and met the research requirements were collected from various sub-centers nationwide.
Trial design
Design model
Other
Time perspective
Other
Treatments tested in this trial
Diagnostic
Other interventionThe deep learning model is trained using the training dataset and tested with the internal validation set.
Diagnostic
Other interventionThe prospective dataset is used for the comparative testing of the model and physicians.
Treatment groups
500 Participants
are divided into 2 treatment groupsGroup A: Model training and validation cohorts1 intervention
Group B: Prospective test cohort1 intervention
Trial outcomes
Primary outcomes
1
performance of lesion detection
The area under the receiver operating characteristic curve (ROC-AUC) of the model for abnormal lesion detection
Time frame
Within 3 months after the completion of prospective data collection2
performance of anatomic site recognition
The average precision (AP) of the model for recognizing nasopharyngeal and laryngeal anatomic sites
Time frame
Within 3 months after the completion of prospective data collectionSecondary outcomes
1
Comparison of diagnostic performance between the model and physicians
Differences in sensitivity, specificity, and overall accuracy between the AI model and endoscopists with different years of experience
Time frame
Within 3 months after the completion of prospective data collectionSponsors and contacts
Click on the lead sponsor to view all of their trials.
Source ClinicalTrials.gov