100% Accurate AI Detects Heart Failure From Single Heartbeat
ACardiovascular diseases are the leading cause of death globally, alone in the United States about 610,000 people die of heart disease every year, that is one in every four deaths.
But with the help an impressive neural network system developed by researchers, this number can be pushed down very much in the future. Researchers have created a new AI-driven neural network that can detect heart failure with 100% accuracy through analysis of just one raw electrocardiogram (ECG) heartbeat.
The research was published in Biomedical Signal Processing and Control Journal, and it demonstrated, by the use of CNN how we can identify CHF nearly instantly by checking ECG data from just one heartbeat.
The research mainly focuses on uses a combination of advanced signal processing and machine learning tools on raw ECG signals, delivering 100% accuracy and to improves existing CHF detection methods which typically focused on heart rate variability that, whilst effective, are time-consuming and prone to errors.
The researchers use the Convolutional Neural Networks (CNN), the hierarchical neural networks which are highly effective in recognizing patterns and structures that form in the applied dataset.
Dr. Massaro said: “First, by assessing ECG directly, we confirm that with Artificial Intelligence it is possible to accurately detect CHF looking beyond heart rate variability analysis”.
“Thus, we have in general results that are more adherent to real behavior of affected heart. We focus on the detection of the pathology from 1 single heartbeat in excerpts of 5-min rather than in 24-hours recordings”.
“This aspect offers a valuable potential for prospects of rapid interventions; nonetheless it is also important to keep in mind that we are talking about severe CHF patients only at the moment.”
“We trained and tested the CNN model on large publicly available ECG datasets featuring subjects with CHF as well as healthy, non-arrhythmic hearts”.
“We trained and tested the model on publicly available ECG datasets, comprising a total of 490,505 heartbeats, to achieve 100% Congestive heart failure detection accuracy”.
“Our model delivered 100% accuracy: by checking just one heartbeat we are able to detect whether or not a person has heart failure. Our model is also one of the first known to be able to identify the ECG’ s morphological features specifically associated with the severity of the condition.”
Massaro suggests, the team’s system is currently reporting an incredible 100 percent accuracy rate, but the research is not without some limitations. Most importantly, the data used in the current study only consisted of ECG readings from either severe CHF patients or healthy subjects.
The researchers do note results may not be as accurate for patients with milder CHF, so more work certainly needs to be done to verify a broader spectrum of CHF diagnoses before the technology put into practice.
Going forward, Massaro hopes to extend the approach to largescale samples and other classes of CHF so that the technology can eventually be implemented in everyday healthcare systems and practices.
He added: “The application of organizational neuroscience, and specifically of neural network approaches to healthcare issues promises to open breakthrough frontiers for both clinical research and practice.”
“This is an important result because, with the increasing availability of wearable devices capturing interim ECG recordings (e.g., smart-watches), accurate CHF detection and prediction might be soon performed through devices people carry in everyday situations,” the researchers conclude in a newly published article.
Dr. Pecchia, President at European Alliance for Medical and Biological Engineering, explains the implications of these findings: “With approximately 26 million people worldwide affected by a form of heart failure, our research presents a major advancement on the current methodology.
Enabling clinical practitioners to access an accurate CHF detection tool can make a significant societal impact, with patients benefitting from early and more efficient diagnosis and easing pressures on NHS resources.”
The study was conducted by Dr. Sebastiano Massaro, Associate Professor of Organisational Neuroscience at the University of Surrey, has worked with colleagues Mihaela Porumb and Dr. Leandro Pecchia at the University of Warwick and Ernesto Iadanza at the University of Florence.