Enhancing Heart Failure Care: Deep Learning-Based Activity Classification in Left Ventricular Assist Device Patients

Abstract

Accurate activity classification is essential for the advancement of closed-loop control for left ventricular assist devices (LVADs), as it provides necessary feedback to adapt device operation to the patient’s current state. Therefore, this study aims at using deep neural networks (DNNs) to precisely classify activity for these patients. Recordings from 13 LVAD patients were analyzed, including heart rate, LVAD flow, and accelerometer data, classifying activities into six states: active, inactive, lying, sitting, standing, and walking. Both binary and multiclass classifiers have been trained to distinguish between active and inactive states and to discriminate the remaining categories. The models were refined by testing several architectures, including recurrent and convolutional layers, optimized via hyperparameter search. Results demonstrate that integrating LVAD flow, heart rate, and accelerometer data leads to the highest accuracy in both binary and multiclass classification. The optimal architectures featured two and three bidirectional long short-term memory layers for binary and multiclass classifications, respectively, achieving accuracies of 91% and 84%. In this study, the potential of DNNs has been proven for providing a robust method for activity classification that is vital for the effective closed-loop control of medical devices in cardiac care.