Pneumonia, Respiratory Failure (Pediatric Patients)
Conditions
Keywords
Severe pneumonia, Bronchoscopy, Navigation system, Artificial intelligence, Computer-assisted, Diagnostic support
Brief summary
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.
Detailed description
Rationale: Severe pneumonia often requires bronchoscopy for diagnosis and therapy, yet accurate segmental localization and consistent interpretation are operator-dependent and time-consuming. Prior work by the sponsor team integrated CT-based planning with real-time bronchoscopic guidance and AI-based lesion characterization. The investigational system overlays guidance and voice prompts during bronchoscopy to standardize navigation and reduce errors. Design: Prospective multicenter controlled study in ICUs/respiratory units. Approximately 100 adults undergoing clinically indicated bronchoscopy for severe pneumonia will be enrolled across \ 10 centers in China. Procedures will be performed either with AI assistance or with standard bronchoscopy per site workflow. Outcomes include: (1) diagnostic agreement versus a predefined reference (primary); (2) navigation success/loss-of-path; (3) procedure time; and (4) adverse events (e.g., bleeding, hypoxemia, infection). Enrollment is planned to start in Sep 2025, with anticipated primary completion around Sep 2026. Operations: Data will be collected using a standardized CRF and analyzed per a prespecified SAP. The investigational software is integrated with an endoscopic image processor developed with an industry partner; physicians can follow or ignore AI suggestions at their discretion. The study will generate evidence on effectiveness and safety to inform subsequent registration testing and scaling.
Interventions
DEVICEEmbodied-Intelligence-Assisted Bronchoscopy Navigation and Diagnostic System (EIBRONCH)
Software/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
OTHERConventional Bronchoscopy (Standard of Care)
Bronchoscopy per site routine without investigational AI assistance; no additional device or drug
Sponsors
Nanjing University
Micro-Tech (Nanjing) Co., Ltd.
Chinese Medical Association
Study design
Allocation
NON_RANDOMIZED
Intervention model
PARALLEL
Primary purpose
DIAGNOSTIC
Masking
NONE
Intervention model description
Prospective multicenter parallel two-arm study comparing AI-assisted bronchoscopy with conventional bronchoscopy. Consecutive eligible adults undergoing clinically indicated bronchoscopy for severe pneumonia will be enrolled at \ 10 hospitals in China. Participants are assigned to one of two arms per site protocol (non-randomized). In the AI arm, the investigational system provides real-time visual and voice guidance; standard of care is otherwise identical in both arms.
Eligibility
Sex/Gender
ALL
Age
18 Years to No maximum
Healthy volunteers
No
Inclusion criteria
1. Age ≥18 years. 2. Severe pneumonia requiring clinically indicated bronchoscopy for diagnosis and/or therapy, as determined by the treating team. 3. Written informed consent from the patient or a legally authorized representative. 4. Expected to tolerate bronchoscopy with current respiratory support (e.g., HFNC/NIV/IMV) per site protocol
Exclusion criteria
1. 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. 2. Uncorrected coagulopathy likely to increase bleeding risk (e.g., platelets \<50×10\^9/L or INR \>1.5) per site policy. 3. Known pregnancy or breastfeeding if the investigator judges risk outweighs benefit according to site policy. 4. Participation in another interventional drug/device study that could interfere with outcomes. 5. Any condition that, in the investigator's judgment, makes participation unsuitable (e.g., emergent life-saving bronchoscopy without time for consent).
Design outcomes
Primary
| Measure | Time frame | Description |
|---|---|---|
| Diagnostic agreement versus central adjudication | From index bronchoscopy to central adjudication within 7 days | 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 |
Secondary
| Measure | Time frame | Description |
|---|---|---|
| Navigation success rate | During the bronchoscopy procedure | 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) | During the bronchoscopy procedure | 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. |
Contacts
Primary ContactMing Chen, MD
Outcome results
None listed