Related Experiment Video
Updated: Feb 14, 2026
Constructing and Visualizing Models using Mime-based Machine-learning Framework
Published on: July 22, 2025
Deconvoluting the Electrophysiological Signatures of Myocardial Ischemia using a Validated Machine Learning Framework
Ahmad Mahmood1, Kiel Jacqueline2, Joanne Lac3
1Royal Free London NHS Foundation Trust, London, England, UK.
Insights
Machine learning models can now distinguish the specific effects of hyperkalemia and acidosis on heart cell electrical activity during ischemia. This computational approach aids in understanding complex cardiac conditions and drug screening.
Area of Science:
- Computational biology
- Cardiovascular physiology
- Machine learning in medicine
Background:
- Myocardial ischemia involves complex changes like hyperkalemia, acidosis, and ATP depletion, altering cardiomyocyte electrophysiology.
- Discerning the individual impact of these factors on action potential (AP) changes is challenging.
- This study investigates machine learning's ability to differentiate these distinct ischemic patterns within a single AP.
Purpose of the Study:
- To develop and validate a machine learning model capable of deconvoluting distinct ischemic drivers affecting cardiomyocyte electrophysiology.
- To predict key physiological parameters like extracellular potassium ([K+]o) and intracellular pH (pHi) from action potentials.
- To assess the generalizability and robustness of the machine learning model across different computational frameworks.
Main Methods:
- A multi-target regression model was developed using the Luo-Rudy (1991) computational model of a ventricular cardiomyocyte.
- The model was trained to predict [K+]o and pHi under simulated ischemic conditions.
- The model's performance was evaluated on a test set and generalized to the Ten Tusscher (2006) framework.
Main Results:
- The model achieved high accuracy, with low mean squared errors for predicting [K+]o and pHi.
- The model accurately predicted [K+]o and pHi when applied to the Ten Tusscher (2006) model, demonstrating robustness.
- Feature importance analysis identified resting membrane potential (RMP) as the key predictor for [K+]o and action potential duration (APD) for pHi.
Conclusions:
- The developed machine learning approach successfully distinguishes individual ischemic drivers (hyperkalemia, acidosis) from action potential changes.
- This method offers potential for in silico drug screening and mechanistic analysis of myocardial ischemia.
- The findings highlight the distinct electrophysiological signatures associated with different ischemic factors.
Background:
Myocardial ischemia is a dynamic, complex process characterized by hyperkalemia, acidosis, and ATP depletion. While these three conditions alter cardiomyocyte electrophysiology, it is difficult to discern how much each one individually contributes to the resulting changes in action potential (AP). In this study, we test whether machine learning can deconvolute these distinct ischemic patterns within a single AP.
Methods:
We developed a multi-target regression model trained on data generated by the Luo-Rudy (1991) computational model of a ventricular cardiomyocyte, simulating a wide range of ischemic conditions. The model was designed to predict two continuous variables: extracellular potassium concentration ([K +]o) and intracellular pH (pHi).
Results:
The model achieved high accuracy on a held-out test set, with mean squared errors (MSE) below 0.25 for [K +]o and below 0.01 for pHi. To further generalize this model, we applied this trained model to a structurally distinct model, the Ten Tusscher (2006) framework. We were able to accurately predict [K +]o and pHi from APs, demonstrating that the learned principles are robust. A feature importance analysis revealed that resting membrane potential (RMP) was the strongest predictor for [K +]o, while action potential duration (APD) is most important for predicting pHi, underscoring these distinct cardiomyocyte electrophysiological patterns.
Conclusions:
Our approach can distinguish distinct ischemic drivers and has potential for in silico drug screening and mechanistic analysis.
Related Concept Videos
01:20Deconvolution
Deconvolution involves several mathematical techniques to derive the impulse response. One common approach is polynomial division. In this method, the input and output sequences are treated as coefficients of...
01:29Reliability and Validity
01:19Machines
A free-body diagram of the...
01:30Machines: Problem Solving II
01:15Data Validation
Key parameters for method validation include:
01:03Data Validation
Nursing assessment guides are generally based on holistic models rather than medical...