Controlling Arrhythmia to Prevent Sudden Death due to Heart Failure

A large population of people suffer from heart problems that can aggravate into sudden heart failure. Meanwhile, 50% of all people who die from heart problems experience sudden onset of heart rhythmic problem. Disturbance in the heart’s electrical rhythm problem is known as arrythmia. The electrical rhythm of the heart is also closely related to contraction of heart cells responsible for pumping blood. However, researchers have struggled to understand the onset of sudden disturbances in electrical rhythms that cause abrupt heart failure.

 A research conducted at the University of Bristol finds potential pathways of preventing sudden heart failure. The Medical Research Council (MRC) funded the research that is published in Proceedings of the National Academy of Sciences (PNAS) journal.

 Change in Voltage

 The researchers assert that varying the time for voltage change can help in preventing fatal electrical disturbances. Besides, changing the time course can also help towards improving the cardiac contraction of the heart.

Cardiac arrhythmias occur due to early after-depolarizations (EADs) at the cellular level. However, the cause of heart failure after the occurrence of arrythmia remains unknown. The researchers find that a sodium-calcium exchange in the heart muscle can oppose the action of EADs. This can in turn help in reducing the risk of sudden heart failure in individuals.

 Release of Ca2+

The researchers assert that the prime focus of cardiologists should be on improving the release of Ca2+. Release of Ca2+ can help in restoring repolarisation of AP phase-1. The researchers suggest a completely different approach to tackle heart arrythmia that can cause sudden heart failure. The findings of the research shall compel scientists to test new lines of drugs. The relevance of preventing heart failure in cardiology is behind the growing popularity of the research.

Convolutional Neural Networks to Detect Heart Failure with 100% Accuracy

A new AI neural network technique could help in identifying congestive heart failure (CHF) with 100% accuracy. The technique could predict the possibility of heart failure by looking at a single beat on the electrocardiograph. The use of neuroscience techniques is an integral part of medical research. However, fool-proof diagnosis through neural techniques is an unprecedented feat. The new technique, based on convolutional neural networks (CNN), could change that. This technique could be the first success of the medical fraternity in predicting heart failures with 100% accuracy.

Need for Improved Diagnosis

Congestive heart failure is a major cause of high mortality rate across several regions. The condition is characterized by extreme pain and discomfort. This is because the heart muscle loses its ability to pump blood in the event of a congestive heart failure. In addition, these factors necessitate the development of sound systems for preventing and diagnosing heart failure.

The new research was headed by Dr. Sebastiano Massaro from the University of Survey. The Biomedical Signal Processing and Control journal published the findings of the research. The research has paved way for improved diagnostic procedures for CHF. Current methods are based on heart-rate variability that increases the chances of error. Furthermore, these methods are obsolete and time-consuming for the medical staff.

Overcoming Limitations of Current Techniques

Current-day techniques for cardiac diagnosis require a detailed study of the electrocardiogram (ECG) report. The new CNN model uses machine learning tools and advanced signal processing to study ECG patterns. The use of these technologies ensures 100% accuracy of results. The researchers tested the CNN model on subjects with CHF, whilst considering their ECG dataset history. Additionally, the CNN model can help in gauging the severity of the condition.

Cardiologists are expected to embrace quick-diagnostic techniques without much ado. This propensity shall help in popularizing convolutional neural network models for the healthcare fraternity.