Endotracheal Tube, Nasogastric Tube, Pneumothorax
Conditions
Keywords
Computer-aided detection system, Artificial intelligence, Pneumothorax diagnosis, Endotracheal tube, Nasogastric tube, Clinical effectiveness, Cost effectiveness
Brief summary
Background Advancements in artificial intelligence (AI) have driven significant breakthroughs in computer-aided detection (CAD) for chest X-ray imaging. National Taiwan University Hospital (NTUH) research team previously developed an AI-based emergency Capstone CXR system (MOST 111-2634-F-002-015-, Capstone project), which led to the creation of a chest X-ray module. This chest X-ray module has an established model supported by extensive research and is ready for direct application in clinical trials without requiring additional model training. This study will utilize three submodules of the system: detection of misplaced endotracheal tubes, detection of misplaced nasogastric tubes, and identification of pneumothorax. Objective This study aims to apply a real-time chest X-ray CAD system in emergency and critical care settings to evaluate its clinical and economic benefits without requiring additional chest X-ray examinations or altering standard care and procedures. The study will evaluate the CAD system's impact on mortality reduction, post-intubation complications, hospital stay duration, workload, and interpretation time, alongside a cost-effectiveness comparison with standard care. Methods This study adopts a pilot trial and cluster randomized controlled trial design, with random assignment conducted at the ward level. In the intervention group, units are granted access to AI diagnostic results, while the control group continues standard care practices. Consent will be obtained from attending physicians, residents, and advanced practice nurses in each participating ward. Once consent is secured, these healthcare providers in the intervention group will be authorized to use the CAD system. Intervention units will have access to AI-generated interpretations, whereas control units will maintain routine medical procedures without access to the AI diagnostic outputs. Results The study was funded in September 2024. Data collection is expected to last from January 2025 to December 2027. Conclusions This study anticipates that the real-time chest X-ray CAD system will automate the identification and detection of misplaced endotracheal and nasogastric tubes on chest X-rays, as well as assist clinicians in diagnosing pneumothorax. By reducing the workload of physicians, the system is expected to shorten the time required to detect tube misplacement and pneumothorax, decrease patient mortality and hospital stays, and ultimately lower healthcare costs.
Interventions
OTHERAI-assisted model
physicians will be authorized to access the AI model's predictions during patient care as an additional decision-making reference. These predictions will be generated in seconds and can help identify issues such as tube misplacement (e.g., nasogastric tube, endotracheal tube) and pneumothorax through AI analysis of CXRs, which will alert the physician to review the images.
Sponsors
National Taiwan University Hospital
Fu Jen Catholic University Hospital
Min-Sheng General Hospital
National Taiwan University
Study design
Allocation
RANDOMIZED
Intervention model
PARALLEL
Primary purpose
DIAGNOSTIC
Masking
NONE
Intervention model description
Each group requires 5,450 patients.
Eligibility
Sex/Gender
ALL
Age
18 Years to No maximum
Healthy volunteers
No
Inclusion criteria
for units: * Emergency critical care or intensive care units. * The units included the patients requiring chest X-rays due to endotracheal intubation, nasogastric tube insertion, or ventilator use with a risk of pneumothorax.
Exclusion criteria
for units: * The unit supervisor doesn't agree to participate in the trial. * The unit is unable to implement the AI-assisted system (e.g., no data connection or system support). Inclusion Criteria for Patients: ● Patients who are adults and require chest X-ray due to one of the following conditions: endotracheal intubation, nasogastric intubation, or the use of a ventilator with the potential to cause pneumothorax.
Design outcomes
Primary
| Measure | Time frame | Description |
|---|---|---|
| In-hospital Mortality | During the hospital stay, an average of 1 week | The patient's survival is monitored after undergoing a chest X-ray until hospital discharge. |
Secondary
| Measure | Time frame | Description |
|---|---|---|
| Length of Hospital Stay | During the hospital stay, an average of 1 week | The time a patient spends in the hospital from admission to discharge, usually measured in days. |
| Misplacement Detection Time | During the hospital stay, an average of 1 week | Evaluates whether the AI system can reduce the time to detect misplaced catheters or pneumothorax, thereby improving the timeliness of clinical intervention. |
Countries
Taiwan
Outcome results
None listed