Dynamic detection and reversal of myocardial ischemia using an artificially intelligent bioelectronic medicine

Abstract

Myocardial ischemia is spontaneous, frequently asymptomatic, and contributes to fatal cardiovascular consequences. Importantly, myocardial sensory networks cannot reliably detect and correct myocardial ischemia on their own. Here, we demonstrate an artificially intelligent and responsive bioelectronic medicine, where an artificial neural network (ANN) supplements myocardial sensory networks, enabling reliable detection and correction of myocardial ischemia. ANNs were first trained to decode spontaneous cardiovascular stress and myocardial ischemia with an overall accuracy of ~92%. ANN-controlled vagus nerve stimulation (VNS) significantly mitigated major physiological features of myocardial ischemia, including ST depression and arrhythmias. In contrast, open-loop VNS or ANN-controlled VNS following a caudal vagotomy essentially failed to reverse cardiovascular pathophysiology. Last, variants of ANNs were used to meet clinically relevant needs, including interpretable visualizations and unsupervised detection of emerging cardiovascular stress. Overall, these preclinical results suggest that ANNs can potentially supplement deficient myocardial sensory networks via an artificially intelligent bioelectronic medicine system.

Importance of timing optimization for closed-loop applications of vagus nerve stimulation

“…There are now several studies investigating the potential of closed-loop VNS for treating cardiovascular conditions (Ganzer et al 2022 ; Tosato et al 2006 ; Ottaviani et al 2022 ; Ferrari et al 2011 ). For instance, closed-loop stimulation in a porcine model used the RR interval to power VNS parameters, with physiological changes being maintained up to a few minutes (Tosato et al 2006 ).…”

“…Myocardial ischemia is involved in several cardiovascular conditions, where there is a prolonged imbalance of myocardial oxygen supply and demand (Buja 2005 ). One recent study has demonstrated the feasibility of providing closed-loop VNS during myocardial ischemia events triggered by a machine learning model (Ganzer et al 2022 ). In a subset of experiments, myocardial ischemia was induced by a high dose infusion of catecholamines leading to correlates of myocardial ischemia, including ST segment depression and arrythmias.…”

“…Implanted vagus nerve stimulation (VNS) is utilized for a number of applications, including improving cardiovascular function (Ganzer et al 2022 ; Kong et al 2012 ; Sabbah et al 2011 ; Tosato et al 2006 ; Tsutsumi et al 2008 ; Ugalde, et al 2014 ; Vaseghi et al 2017 ; Yamaguchi et al 2018 ), reducing excessive inflammation (Koopman et al 2016 ; Marsal et al 2021 ), epilepsy (Elliott et al 2011a ; Elliott et al 2011b ; Alexopoulos et al 2006 ; Bauer et al 2016 ), and promoting neural plasticity for enhancing motor rehabilitation (Dawson et al 2021a ; Ganzer et al 2018 ; Kilgard et al 2018 ; Kimberley et al 2018 ; Pruitt et al 2016 ; Redgrave et al 2018 ). Although VNS has been used clinically for more than 30 years, it is not fully understood exactly when VNS should be delivered in relation to disease events (e.g., a seizure) or disease progression (e.g., subclinical or clinical disease) for yielding optimized therapeutic outcomes.…”

Artificial Intelligence and Medicine: A literature review

“…Dynamic detection and reversal of myocardial ischemia using an artificially intelligent bioelectronic medicine (Ganzer et al 2022) This research is a proof-of-concept of an Artificial Neural Network (ANN) supplementing the Myocardial Sensory Networks in reliably detecting Myocardial Ischemia through the decoding of cardiovascular pathophysiological features along with the reversal of the Myocardial Ischemia by ANN-controlled Vagus Nerve Stimulation (VNS).…”

Triboelectric nanogenerators for smart agriculture

“…With the rapid growth and development of big data, 1,2 artificial intelligence, 3–5 Internet of Things (IoT), 6–8 and cloud computing 9 in recent decades, the agriculture field has undergone a radical transformation and entered the era of smart agriculture. While traditional agriculture mainly analyzes and summarizes the growth of crops through visual inspection or working experience, smart agriculture mainly monitors information in agricultural production activities, such as pH, environmental temperature, and humidity in real‐time through distributed sensors 10–15 .…”