Learning Intelligent for Effective Sonography (LIFES) Model for Rapid Diagnosis of Heart Failure in Echocardiography

Abstract

Background: The accuracy of an artificial intelligence model based on echocardiography video data in the diagnosis of heart failure (HF) called LIFES (Learning Intelligent for Effective Sonography) was investigated. Methods: A cross-sectional diagnostic test was conducted using consecutive sampling of HF and normal patients’ echocardiography data. The gold-standard comparison was HF diagnosis established by expert cardiologists based on clinical data and echocardiography. After pre-processing, the AI model is built based on Long-Short Term Memory (LSTM) using independent variable estimation and video classification techniques. The model will classify the echocardiography video data into normal and heart failure category. Statistical analysis was carried out to calculate the value of accuracy, area under the curve (AUC), sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), and likelihood ratio (LR). Results: A total of 138 patients with HF admitted to Harapan Kita National Heart Center from January 2020 to October 2021 were selected as research subjects. The first scenario yielded decent diagnostic performance for distinguishing between heart failure and normal patients. In this model, the overall diagnostic accuracy of A2C, A4C, PLAX-view were 92,96%, 90,62% and 88,28%, respectively. The automated ML-derived approach had the best overall performance using the 2AC view, with a misclassification rate of only 7,04%. Conclusion: The LIFES model was feasible, accurate, and quick in distinguishing between heart failure and normal patients through series of echocardiography images. Keywords: Artificial intelligence, machine learning, echocardiography, heart failure.