Detection of cardiac amyloidosis using machine learning on routine echocardiographic measurements

• Published in: Open heart 2024-12, Vol.11 (2), p.e002884
• Main Authors: Chang, Rachel Si-Wen, Chiu, I-min, Tacon, Phillip, Abiragi, Michael, Cao, Louie, Hong, Gloria, Le, Jonathan, Zou, James, Daluwatte, Chathuri, Ricchiuto, Piero, Ouyang, David
• Format: Article
• Language: English
• Subjects: Accuracy; Aged; Amyloidosis; Amyloidosis - diagnosis; Amyloidosis - diagnostic imaging; Amyloidosis - physiopathology; Artificial intelligence; Cardiac arrhythmia; Cardiomyopathies - diagnosis; Cardiomyopathies - diagnostic imaging; Cardiomyopathies - physiopathology; Cardiomyopathy, Restrictive; Cardiovascular disease; Coronary vessels; Deep learning; Diabetes; Diagnostic Imaging; Echocardiography; Echocardiography - methods; Ejection fraction; Feature selection; Female; Heart failure; Heart Failure and Cardiomyopathies; Humans; Hypertension; Machine Learning; Male; Middle Aged; Original Research; Patients; Performance evaluation; Predictive Value of Tests; Pulmonary arteries; Reproducibility of Results; Retrospective Studies; Statistical analysis; Ultrasonic imaging; Vein & artery diseases
• ISSN: 2053-3624; 2398-595X; 2053-3624
• DOI: 10.1136/openhrt-2024-002884

BackgroundCardiac amyloidosis (CA) is an underdiagnosed, progressive and lethal disease. Machine learning applied to common measurements derived from routine echocardiogram studies can inform suspicion of CA.ObjectivesOur objectives were to test a random forest (RF) model in detecting CA.MethodsWe used 3603 echocardiogram studies from 636 patients at Cedars-Sinai Medical Center to train an RF model to predict CA from echocardiographic parameters. 231 patients with CA were compared with 405 control patients with negative pyrophosphate scans or clinical diagnosis of hypertrophic cardiomyopathy. 19 common echocardiographic measurements from echocardiogram reports were used as input into the RF model. Data was split by patient into a training data set of 2882 studies from 486 patients and a test data set of 721 studies from 150 patients. The performance of the model was evaluated by area under the receiver operative curve (AUC), sensitivity, specificity and positive predictive value (PPV) on the test data set.ResultsThe RF model identified CA with an AUC of 0.84, sensitivity of 0.82, specificity of 0.73 and PPV of 0.76. Some echocardiographic measurements had high missingness, suggesting gaps in measurement in routine clinical practice. Features that were large contributors to the model included mitral A-wave velocity, global longitudinal strain (GLS), left ventricle posterior wall diameter end diastolic (LVPWd) and left atrial area.ConclusionMachine learning on echocardiographic parameters can detect patients with CA with accuracy. Our model identified several features that were major contributors towards identifying CA including GLS, mitral A peak velocity and LVPWd. Further study is needed to evaluate its external validity and application in clinical settings.