Cognitive Machine-Learning Algorithm for Cardiac Imaging: A Pilot Study for Differentiating Constrictive Pericarditis From Restrictive Cardiomyopathy. (June 2016)

• Record Type: Journal Article
• Authors: Sengupta, Partho P.; Huang, Yen-Min; Bansal, Manish; Ashrafi, Ali; Fisher, Matt; Shameer, Khader; Gall, Walt; Dudley, Joel T.
• Is Part Of: Circulation. Volume 9:Number 6(2016)
• Publication Date: 2016-06
• Subjects: big data -- cardiovascular imaging -- cognitive tools -- machine learning -- phenomics -- precision medicine -- speckle tracking echocardiography; Cardiovascular system -- Imaging -- Periodicals; Heart -- Imaging -- Periodicals; 616.1075405
• DOI: 10.1161/CIRCIMAGING.115.004330
• Languages: English
• ISSNs: 1941-9651

Abstract

Abstract : Background—: Associating a patient's profile with the memories of prototypical patients built through previous repeat clinical experience is a key process in clinical judgment. We hypothesized that a similar process using a cognitive computing tool would be well suited for learning and recalling multidimensional attributes of speckle tracking echocardiography data sets derived from patients with known constrictive pericarditis and restrictive cardiomyopathy. Methods and Results—: Clinical and echocardiographic data of 50 patients with constrictive pericarditis and 44 with restrictive cardiomyopathy were used for developing an associative memory classifier–based machine-learning algorithm. The speckle tracking echocardiography data were normalized in reference to 47 controls with no structural heart disease, and the diagnostic area under the receiver operating characteristic curve of the associative memory classifier was evaluated for differentiating constrictive pericarditis from restrictive cardiomyopathy. Using only speckle tracking echocardiography variables, associative memory classifier achieved a diagnostic area under the curve of 89.2%, which improved to 96.2% with addition of 4 echocardiographic variables. In comparison, the area under the curve of early diastolic mitral annular velocity and left ventricular longitudinal strain were 82.1% and 63.7%, respectively. Furthermore, the associative memory classifier demonstrated greater accuracy and shorter learning curves than other machine-learning approaches, with accuracy asymptotically approaching 90% after a training fraction of 0.3 and remaining flat at higher training fractions. Conclusions—: This study demonstrates feasibility of a cognitive machine-learning approach for learning and recalling patterns observed during echocardiographic evaluations. Incorporation of machine-learning algorithms in cardiac imaging may aid standardized assessments and support the quality of interpretations, particularly for novice readers with limited experience. Abstract : Supplemental Digital Content is available in the text.