Computers in Biology and Medicine 2024

Fast creation of data-driven low-order predictive cardiac tissue excitation models from recorded activation patterns 

Article Link

Authors

Biophysical models are inherently complex. They try to describe all the underlying ionic mechanisms to get a complete picture of the inner workings of an excitable cardiac cell (cardiomyocyte). However, when looking at patient data, we usually only have one variable or parameter that we can measure at a single time (an ECG or a voltage map). This makes creating personalised models very difficult. Here, an alternative approach is proposed where only the key characteristics of wave propagation are described based on a single variable (voltage). By cleverly expanding and unfolding the state space, it is possible to quickly create a simplified model that is personalized and that captures and predicts wave propagation accurately.

Figure: graphical abstract describing the methods used to create predictive cardiac excitation models,.

The quick and easy creation of fast in-silico models of excitable media is, for instance, needed for patient-specific predictions in diagnostics and decision making in cardiac electrophysiology. We presented a model creation pipeline that not only generates new models quickly, but also only requires data from one easily measurable spatio-temporal variable. These data may, for instance, be an optical voltage mapping recording of the electrical waves in cardiac muscle tissue controlling the heart beat. We used exponential moving averages and compute standard deviations to extract additional states from this one variable to span a sparse discretised state space. To this augmented state space, we fit a simple polynomial model to predict the evolution of this one state variable. For optical voltage mapping data of human atrial myocyte monolayers, the data-driven model is able to describe the excitation and recovery of the system, as well as wave propagation. The data-driven model is also able to predict spiral waves only based on data from focal waves. In contrast to conventional models, with our model creation pipeline new models can be generated in a matter of hours from experiment to fitting, rather than months or years.

Highlights

Journal info

Article type:  Original article
Impact factor: 6.698
ISSN: 0010-4825 (print); 1879-0534 (online) 

Computers in Biology and Medicine is a medium of international communication of the revolutionary advances being made in the application of the computer to the fields of bioscience and medicine. The Journal encourages the exchange of important research, instruction, ideas and information on all aspects of the rapidly expanding area of computer usage in these fields. The Journal focuses on such areas as (1) Analysis of Biomedical Systems: Solutions of Equations; (2) Synthesis of Biomedical Systems: Simulations; (3) Special Medical Data Processing Methods; (4) Special Purpose Computers and Clinical Data Processing for Real Time, Clinical and Experimental Use; and (5) Medical Diagnosis and Medical Record Processing. Also included are the fields of (6) Biomedical Engineering; and (7) Medical Informatics as well as Bioinformatics. The journal is expanding to include (8) Medical Applications of the Internet and World Wide Web; (9) Human Genomics; (10) Proteomics; and (11) Functional Brain Studies.