This study will evaluate an embodied-intelligence-assisted bronchoscopy navigation and diagnostic system for patients with severe pneumonia who require clinically indicated bronchoscopy. The system provides real-time visual cues and voice prompts to help physicians localize target lung segments and describe endobronchial findings; physicians remain fully responsible for all clinical decisions. The trial is designed as a prospective, multicenter, controlled study conducted at about ten hospitals in China, with an anticipated sample size of approximately 100 patients. The primary objective is to determine whether AI assistance improves diagnostic agreement compared with the reference assessment, while secondary objectives include navigation success (e.g., loss-of-path rate), procedure time, and complication rates. The results will provide evidence on the safety and effectiveness of AI-assisted bronchoscopy and support product validation and registration.
Age ≥18 years.
Severe pneumonia requiring clinically indicated bronchoscopy for diagnosis and/or therapy, as determined by the treating team.
Written informed consent from the patient or a legally authorized representative.
Expected to tolerate bronchoscopy with current respiratory support (e.g., HFNC/NIV/IMV) per site protocol
Standard contraindications to bronchoscopy, such as uncontrolled hypoxemia despite support (SpO2 <90% for ≥30 s on FiO2 ≥0.60), hemodynamic instability requiring escalating vasopressors, or malignant arrhythmia not controlled.
Uncorrected coagulopathy likely to increase bleeding risk (e.g., platelets <50×10^9/L or INR >1.5) per site policy.
Known pregnancy or breastfeeding if the investigator judges risk outweighs benefit according to site policy.
Participation in another interventional drug/device study that could interfere with outcomes.
Parallel
Embodied-Intelligence-Assisted Bronchoscopy Navigation and Diagnostic System (EIBRONCH)
DeviceSoftware/hardware system integrated with the bronchoscopic image chain. Uses pre-procedure planning and in-procedure computer vision to provide real-time visual cues and voice prompts for airway navigation and lesion characterization. Decision-support only; not implanted; used during the bronchoscopy procedure
Conventional Bronchoscopy (Standard of Care)
Other interventionBronchoscopy per site routine without investigational AI assistance; no additional device or drug
Diagnostic agreement versus central adjudication
Participant-level proportion whose bronchoscopic diagnosis (target segment localization and lesion category) matches the reference standard defined by a blinded expert panel (≥2 senior bronchoscopists; disagreements resolved by a third reviewer) reviewing procedure images/videos and clinical data. Metric: percent agreement and Cohen's kappa with 95% CI; analysis unit: participant
Navigation success rate
Participant-level proportion of procedures that successfully reach the prespecified target bronchial segment without any loss-of-path event (\>10 s) requiring external repositioning or restarts. Analysis unit: procedure.
Procedure time to target segment (minutes)
Minutes from scope insertion to confirmation of the prespecified target segment (via endobronchial landmarks and site protocol). Reported as mean (SD) or median (IQR) and between-arm difference with 95% CI.
Click on the lead sponsor to view all of their trials.
Chinese Medical Association
Lead sponsor
Nanjing University
Collaborator
Micro-Tech (Nanjing) Co., Ltd.
Collaborator
This trial is not recruiting at the moment. You can still explore other options:
