Machine learning algorithms to automate differentiating cardiac amyloidosis from hypertrophic cardiomyopathy

Background: Cardiac amyloidosis has poor prognosis, high mortality and is often misdiagnosed as hypertrophic cardiomyopathy, leading to delayed diagnosis. Objective: Machine learning combined speckle tracking echocardiography was proposed to automate differentiating two conditions. Methods: A total of 74 patients with pathologically confirmed cardiac amyloidosis and 64 patients of hypertrophic cardiomyopathy were enrolled from June 2015 to November 2018. Machine learning models utilizing traditional and advanced algorithms were established and determined the most significant predictors. The performance was evaluated by receiver operating characteristic curve (ROC) and area under the curve (AUC). Results: With clinical and echocardiography data, all models showed great discriminative performance (AUC > 0.9). Compared with logistic regression (AUC=0.91), machine learning such as support vector machine (AUC=0.95, P=0.477), random forest (AUC= 0.97, P=0.301) and gradient boosting machine (AUC= 0.98, P=0.230) demonstrated varying degrees of improvement of predicting cardiac amyloidosis. With speckle tracking echocardiography, the predictive performance of the voting model was similar to that of LightGBM (AUC were 0.86 for both), while the AUC of XGBoost was slightly lower (AUC=0.84). In 5-fold cross validation, the voting model was more robust globally and superior to the single model in some test sets. Conclusions: Data-driven machine learning had shown admirable performance in differentiating two conditions and could automatically integrate abundant variables to identify the most discriminating predictors without making preassumptions. In the era of big data, automated machine learning will help to better identify patients with cardiac amyloidosis, and to timely and effectively intervene, thus improving the outcome.