Cardiac Phase Space Tomography: A novel method of assessing coronary artery disease utilizing machine learning

• Published in: PloS one Vol. 13; no. 8; p. e0198603
• Main Authors: Stuckey, Thomas D., Gammon, Roger S., Goswami, Robi, Depta, Jeremiah P., Steuter, John A., Meine, Frederick J., Roberts, Michael C., Singh, Narendra, Ramchandani, Shyam, Burton, Tim, Grouchy, Paul, Khosousi, Ali, Shadforth, Ian, Sanders, William E.
• Format: Journal Article
• Language: English
• Published: United States Public Library of Science 08.08.2018; Public Library of Science (PLoS)
• Subjects: Algorithms; Angiography; Artificial intelligence; Cardiology; Cardiovascular disease; Care and treatment; Clinical medicine; Computer and Information Sciences; Consent; Contrast media; Coronary artery; Coronary artery disease; Coronary heart disease; Coronary vessels; Diagnosis; Diagnostic imaging; Diagnostic systems; Disease control; Engineering and Technology; Feature extraction; Genetic algorithms; Genomics; Heart; Heart diseases; Intubation; Learning algorithms; Machine learning; Mathematical models; Medical imaging; Medicine; Medicine and Health Sciences; Methods; Neural networks; Pain; People and Places; Pharmacology; Physical Sciences; Radiation; Radioactivity; Research and Analysis Methods; Stenosis; Thorax; Tomography; North Carolina; Canada; Atlanta Georgia; Georgia; Toronto Ontario Canada; United States > US
• ISSN: 1932-6203; 1932-6203
• DOI: 10.1371/journal.pone.0198603

Artificial intelligence (AI) techniques are increasingly applied to cardiovascular (CV) medicine in arenas ranging from genomics to cardiac imaging analysis. Cardiac Phase Space Tomography Analysis (cPSTA), employing machine-learned linear models from an elastic net method optimized by a genetic algorithm, analyzes thoracic phase signals to identify unique mathematical and tomographic features associated with the presence of flow-limiting coronary artery disease (CAD). This novel approach does not require radiation, contrast media, exercise, or pharmacological stress. The objective of this trial was to determine the diagnostic performance of cPSTA in assessing CAD in patients presenting with chest pain who had been referred by their physician for coronary angiography. This prospective, multicenter, non-significant risk study was designed to: 1) develop machine-learned algorithms to assess the presence of CAD (defined as one or more ≥ 70% stenosis, or fractional flow reserve ≤ 0.80) and 2) test the accuracy of these algorithms prospectively in a naïve verification cohort. This report is an analysis of phase signals acquired from 606 subjects at rest just prior to angiography. From the collective phase signal data, features were extracted and paired with the known angiographic results. A development set, consisting of signals from 512 subjects, was used for machine learning to determine an algorithm that correlated with significant CAD. Verification testing of the algorithm was performed utilizing previously untested phase signals from 94 subjects. The machine-learned algorithm had a sensitivity of 92% (95% CI: 74%-100%) and specificity of 62% (95% CI: 51%-74%) on blind testing in the verification cohort. The negative predictive value (NPV) was 96% (95% CI: 85%-100%). These initial multicenter results suggest that resting cPSTA may have comparable diagnostic utility to functional tests currently used to assess CAD without requiring cardiac stress (exercise or pharmacological) or exposure of the patient to radioactivity.