A Sensorless Control System for an Implantable Heart Pump Using a Real-Time Deep Convolutional Neural Network

Abstract

Left ventricular assist devices (LVADs) are mechanical pumps, which can be used to support heart failure (HF) patients as bridge to transplant and destination therapy. To automatically adjust the LVAD speed, a physiological control system needs to be designed to respond to variations of patient hemodynamics across a variety of clinical scenarios. These control systems require pressure feedback signals from the cardiovascular system. However, there are no suitable longterm implantable sensors available. In this study, a novel realtime deep convolutional neural network (CNN) for estimation of preload based on the LVAD flow was proposed. A new sensorless adaptive physiological control system for an LVAD pump was developed using the full dynamic form of model free adaptive control (FFDL-MFAC) and the proposed preload estimator to maintain the patient conditions in safe physiological ranges. The CNN model for preload estimation was trained and evaluated through 10-fold cross validation on 100 different patient conditions and the proposed sensorless control system was assessed on a new testing set of 30 different patient conditions across six different patient scenarios. The proposed preload estimator was extremely accurate with a correlation coefficient of 0.97, root mean squared error of 0.84 mmHg, reproducibility coefficient of 1.56 mmHg, coefficient of variation of 14.44 %, and bias of 0.29 mmHg for the testing dataset. The results also indicate that the proposed sensorless physiological controller works similarly to the preload-based physiological control system for LVAD using measured preload to prevent ventricular suction and pulmonary congestion. This study shows that the LVADs can respond appropriately to changing patient states and physiological demands without the need for additional pressure or flow measurements.Index Terms-Convolutional neural network, left ventricular assist devices, deep learning, model free adaptive control, physiological control, sensorless control.

An Optimal H-Infinity Controller for Left Ventricular Assist Devices Based on a Starling-like Controller: A Simulation Study

“…Based on this concept, several physiological regulation control methods for VAD were proposed and validated in different clinical conditions. These include the flow rate control [11,12], pump differential pressure [13], aortic pressure [14], pulsatility index [15] or heart rate regulation [16], suction limit control [17], and aortic valve function [18]. On the other hand, controlling VAD pumps requires continuous flow and pressure sensors.…”

Big Data in cardiac surgery: real world and perspectives

“…These mathematical models are limited in their applicability because the need for pressure feedback signals from the cardiovascular system require suitable integrated long-term pressure sensors. To date, novel AI based controllers, real-time deep convolutional neural network-based, are tested to estimate left ventricular preload using LVAD flow analyses and a sensorless adaptive control system, trained and evaluated through a number of cross validation settings and physiologic situations in different patient and different conditions, resulting in accurate pre-load evaluation (root mean squared error of 0.84 mmHg, reproducibility coefficient of 1.56 mmHg, coefficient of variation of 14.44%, and bias of 0.29 mmHg for the testing dataset) [ 63 ]. The system was able to use LVAD data to measure preload and prevent ventricular suction and pulmonary congestion [ 64 ].…”

Improved Federal Test Procedure (FTP75) driving cycle performance for PMSM‐fed hybrid electric vehicles using artificial neural network

“…Recently, artificial intelligence (AI)-based control algorithms, which include fuzzy logic (FL), artificial neural network (ANN), 9,14,15 and adaptive neuro-fuzzy inference system (ANFIS), 16 are widely reported in the literature. FL controllers (FLCs) are easy to implement using linguistics rules by the user gained experience from past learning; it mimics the human perception.…”

“…Recently, ANN was also employed in biomedical instruments, which is reported as more reliable than conventional control schemes. 15 In this paper, an ANN controller is used in the adaption mechanism of MRAS, and a reference model of MRAS is formulated using the stator current variables. Once trained offline, ANNs allow faster parallel processing and ease of training, and are insensitive to parameter distortion.…”

“…Accetta et al 19 estimate the speed of the PMSM using a high‐frequency pulsating signal and ANN‐based variable band filter to improve the fraction hp motor drive performance. Recently, ANN was also employed in biomedical instruments, which is reported as more reliable than conventional control schemes 15 …”