Repository of Phase Signals for Algorithm Development and Testing in CAD in CHINA (CADChina)

Analytics 4 Life (A4L) is a medical information technology company that uses advanced signal processing techniques for the purposes of assessing and diagnosing disease. A4L is currently focused on developing a non-invasive solution for the assessment of significant coronary artery disease using the cardiac Phase Space Tomography Analysis (cPSTA) System. Through proprietary variable extraction to define phase space signals as metrics in mathematical terms and machine learned formulas, A4L has developed a cost-effective solution to collect and analyze phase signals as data indicative of cardiac performance. The cPSTA System passively reconstructs and displays images from this data using topological data analysis (TDA) to provide a computationally tractable method of interrogating the complex physiological processes of the heart with the intent to understand and characterize the cardiac tissue properties.

A4L has providing the Phase Signal Recorder (PSR) to the sponsor for use in this study. The primary objective of this study is to collect resting phase signals from eligible subjects using the Phase Space Recorder (PSR) prior to coronary angiography for the purpose of machine learning and testing an algorithm developed to assess the presence of significant coronary artery disease (CAD).The definition of significant CAD, which is well established in the literature, is either the presence of a stenosis ≥50% by angiography or reduced blood flow of <0.80as measured by Fractional Flow Rate (FFR) or instantaneous free-wave ratio (iFR) <0.89.Each subject's CAD status will be assessing the presence of significant CAD in the major coronary arteries including the left main artery (LMA), left anterior descending artery (LAD), circumflex artery (LCX), and the right coronary artery (RCA) and their distributions.

Accurately assessing the presence or absence of CAD and evaluating other physiologic measures is vital to the assessment of cardiac health/illness. As such, the following additional assessments are planned to support further support goal: establishing a ROC curve for the primary objective to describe a full range of sensitivity and specificity trade-offs; and, developing and testing machine-learned algorithms to validate a clinically relevant sensitivity and specificity for the identification of significant CAD specific to perfusion regions (LAD, LCX, and RCA).