Performance Evaluation of Artificial Intelligence Screening Model in Coronary Heart Disease Detection
- Conditions
- Coronary Heart Disease
- Registration Number
- NCT06658600
- Lead Sponsor
- Tsinghua University
- Brief Summary
To determine whether an integrated AI decision support can save time and improve accuracy of assessment of obstructive coronary heart disease (CHD), the investigators are conducting a randomized controlled study of AI guided measurements of obstructive CHD probability compared to clinical assessment in preliminary evaluations by physicians.
- Detailed Description
This is a randomized controlled trial (RCT) evaluating the effectiveness of an AI-based decision support tool in the preliminary assessment of obstructive CHD by physicians. Retrospectively collected medical records of participants with chest pain or dyspnea will be randomly assigned to either guideline group or AI group after baseline assessment:
There are three settings:
1. Clinical Intuition (baseline assessment) Physicians assess obstructive CHD probability without any external assistance. Assessment relies solely on the physician's clinical judgment and experience.
2. Guideline-Based Group (Guideline Group) Physicians use a RF-CL table (risk factor weighted clinical likelihood table) to calculate the probability of obstructive CHD.
This approach aligns with current clinical guidelines to assist in decision-making.
3. AI-Assisted Group (AI Group) Physicians receive CHD probability estimates and diagnostic recommendations from an AI model based on retinal photographs.
The AI tool provides individualized obstructive CHD probabilities, leveraging retinal biomarkers associated with cardiovascular risk.
Primary Objective To evaluate whether AI-guided decision support could improves diagnostic accuracy of obstructive CHD to a greater extent than standard clinical assessments, both compared to clinical intuition.
Secondary Objective To assess whether AI-guided decision support reduces the time required to complete preliminary assessments of obstructive CHD.
Participants, Readers and Randomization Participants: Case records of participants with chest pain or dyspnea, all underwent CT coronary angiography or invasive coronary angiography.
Readers: Physicians performing preliminary evaluations of obstructive CHD patients.
Randomization: Participants and readers will be randomized into one of the groups (RF-CL or AI) after clinical assessment at baseline using block randomization to ensure balanced group sizes.
Recruitment & Eligibility
- Status
- ACTIVE_NOT_RECRUITING
- Sex
- All
- Target Recruitment
- 900
Not provided
Not provided
Study & Design
- Study Type
- INTERVENTIONAL
- Study Design
- PARALLEL
- Primary Outcome Measures
Name Time Method Diagnostic Accuracy of Participants with Obstructive Coronary Heart Disease Through study completion, an average of 1 week Whether AI-guided decision support improves the diagnostic accuracy of obstructive coronary heart disease (CHD) to a greater extent than standard clinical assessments (RF-CL), both compared to clinical intuition.
All participants of the case records had underwent CT angiography or invasive angiography. The diagnostic accuracy, sensitivity and specificity will be compared across groups.
- Secondary Outcome Measures
Name Time Method Time Consumed by Physician Readers to Provide the Diagnosis Impression of Obstructive Coronary Heart Disease. Through study completion, an average of 1 week The time consumed by physician readers will be recorded by an algorithm implemented on the website for reading.
Trial Locations
- Locations (3)
Tsinghua University
🇨🇳Beijing, Beijing, China
Shanghai Health and Medical Center
🇨🇳Shanghai, Shanghai, China
Shanghai Sixth People's Hospital
🇨🇳Shanghai, Shanghai, China