Performance Evaluation of Artificial Intelligence Screening Model in Coronary Heart Disease Detection

Condition(s) studied

Investigational drug(s) / intervention(s)

Physician readers will be assisted with AI-derived probability and diagnosis of obstructive coronary heart disease: Physician readers will be assisted with AI-derived probability and diagnosis of obstructive coronary heart disease. The AI tool provides individualized obstructive CHD probabilities and diagnosis, leveraging retinal biomarkers associated with cardiovascular risk.

Physician readers will be assisted with RF-CL table to calculate the probability of obstructive coronary heart disease: Physicians use a RF-CL table (risk factor weighted clinical likelihood table) to calculate the probability of obstructive CHD.

Study 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.

Eligibility

Primary outcome measure(s)

• 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.

Trial sites (3)

More Tsinghua University trials in China

Other trials for the same condition