Adaptive cardiac resynchronization therapy device based on spiking neurons architecture and reinforcement learning scheme

Rami Rom, Jacob Erel, Michael Glikson, Randy A. Lieberman, Kobi Rosenblum, Ofer Binah, Ran Ginosar, David L. Hayes

Research output: Contribution to journalArticlepeer-review

Abstract

Spiking neural network (NN) architecture that uses Hebbian learning and reinforcement-learning schemes for adapting the synaptic weights is implemented in silicon and performs dynamic optimization according to hemodynamic sensor for a cardiac resynchronization therapy (CRT) device. The spiking NN architecture dynamically changes the atrioventricular (AV) delay and interventricular (VV) interval parameters according to the information provided by the intracardiac electrograms (IEGMs) and hemodynamic sensors. The spiking NN coprocessor performs the adaptive part and is controlled by a deterministic algorithm master controller. The simulated cardiac output obtained with the adaptive CRT device is 30% higher than with a nonadaptive CRT device and is likely to provide improvement in the quality of life for patients with congestive heart failure. The spiking NN architecture shows synaptic plasticity acquired during the learning process. The synaptic plasticity is manifested by a dynamic learning rate parameter that correlates patterns of hemodynamic sensor with the system outputs, i.e., the optimal AV and VV pacing intervals.

Original languageEnglish
Pages (from-to)542-550
Number of pages9
JournalIEEE Transactions on Neural Networks
Volume18
Issue number2
DOIs
StatePublished - Mar 2007

Keywords

  • Artificial neural network (ANN)
  • Cardiac resynchronization therapy (CRT)
  • Integrate-and-fire model (I&F)
  • Intracardiac electrograms (IEGMs)

Fingerprint

Dive into the research topics of 'Adaptive cardiac resynchronization therapy device based on spiking neurons architecture and reinforcement learning scheme'. Together they form a unique fingerprint.

Cite this