New AI Algorithm Can Spot Unseen Heart Attack Symptoms

Researchers at Mount Sinai have created a new artificial intelligence algorithm that can identify slight changes within the heart and accurately predict an incoming heart attack symptoms or heart failure. The AI algorithm could learn how to identify subtle changes in electrocardiograms (also known as ECGs or EKGs) to predict whether a patient was experiencing heart failure.

Researchers implemented natural language processing programs to help the computer extract data from the written reports and enabling it to read over 700,000 electrocardiograms and echocardiogram reports obtained from 150,000 Mount Sinai Health System patients from 2003 to 2020. Data from four hospitals was used to train the computer, whereas data from a fifth one was used to test how the algorithm would perform in a different experimental setting.

“We showed that deep-learning algorithms can recognize blood pumping problems on both sides of the heart from ECG waveform data,” said Benjamin S. Glicksberg, PhD, Assistant Professor of Genetics and Genomic Sciences, a member of the Hasso Plattner Institute for Digital Health at Mount Sinai, and a senior author of the study published in the Journal of the American College of Cardiology: Cardiovascular Imaging. “Ordinarily, diagnosing these type of heart conditions requires expensive and time-consuming procedures. We hope that this algorithm will enable quicker diagnosis of heart failure.”

“However, recent breakthroughs in artificial intelligence suggest that electrocardiograms—a widely used electrical recording device—could be a fast and readily available alternative in these cases. For instance, many studies have shown how a “deep-learning” algorithm can detect weakness in the heart’s left ventricle, which pushes freshly oxygenated blood out to the rest of the body. In this study, the researchers described the development of an algorithm that not only assessed the strength of the left ventricle but also the right ventricle, which takes deoxygenated blood streaming in from the body and pumps it to the lungs.”

Although appealing, traditionally it has been challenging for physicians to use ECGs to diagnose heart failure. This is partly because there is no established diagnostic criteria for these assessments and because some changes in ECG readouts are simply too subtle for the human eye to detect,” said Dr. Nadkarni. “This study represents an exciting step forward in finding information hidden within the ECG data which can lead to better screening and treatment paradigms using a relatively simple and widely available test.”

Source: https://www.mountsinai.org/

How To Detect Heart Failure From A Single Heartbeat

Researchers have developed a neural network approach that can accurately identify congestive heart failure with 100% accuracy through analysis of just one raw electrocardiogram (ECG) heartbeat, a new study reports.

Congestive heart failure (CHF) is a chronic progressive condition that affects the pumping power of the heart muscles. Associated with high prevalence, significant mortality rates and sustained healthcare costs, clinical practitioners and health systems urgently require efficient detection processes.

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, to tackle these important concerns by using Convolutional Neural Networks (CNN) – hierarchical neural networks highly effective in recognising patterns and structures in data.

Published in Biomedical Signal Processing and Control Journal, their research drastically improves existing CHF detection methods typically focused on heart rate variability that, whilst effective, are time-consuming and prone to errors. Conversely, their new model uses a combination of advanced signal processing and machine learning tools on raw ECG signals, delivering 100% accuracy.

We trained and tested the CNN model on large publicly available ECG datasets featuring subjects with CHF as well as healthy, non-arrhythmic hearts. Our model delivered 100% accuracy: by checking just one heartbeat we are able 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 to the severity of the condition,”  explains Dr Massaro.  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.”

Source: https://www.surrey.ac.uk/

A self-powered heart monitor taped to the skin

Scientists in Japan have developed a human-friendly, ultra-flexible organic sensor powered by sunlight, which acts as a self-powered heart monitor. Previously, they developed a flexible photovoltaic cell that could be incorporated into textiles. In this study, they directly integrated a sensory device, called an organic electrochemical transistor—a type of electronic device that can be used to measure a variety of biological functions—into a flexible organic solar cell. Using it, they were then able to measure the heartbeats of rats and humans under bright light conditions.

Self-powered devices that can be fit directly on human skin or tissue have great potential for medical applications. They could be used as physiological sensors for the real-time  or the real-time monitoring of heart or brain function in the human body. However, practical realization has been impractical due to the bulkiness of batteries and insufficient power supply, or due to noise interference from the electrical supply, impeding conformability and long-term operation.

The key requirement for such devices is a stable and adequate energy supply. A key advance in this study, published in Nature, is the use of a nano-grating surface on the light absorbers of the solar cell, allowing for high photo-conversion efficiency (PCE) and light angle independency. Thanks to this, the researchers were able to achieve a PCE of 10.5 percent and a high power-per-weight ratio of 11.46 watts per gram, approaching the “magic number” of 15 percent that will make organic photovoltaics competitive with their silicon-based counterparts.

To demonstrate a practical application, sensory devices called organic electrochemical transistors were integrated with organic solar cells on an ultra-thin (1 μm) substrate, to allow the self-powered detection of heartbeats either on the skin or to record electrocardiographic (ECG) signals directly on the heart of a rat. They found that the device worked well at a lighting level of 10,000 lux, which is equivalent to the light seen when one is in the shade on a clear sunny day, and experienced less noise than similar devices connected to a battery, presumably because of the lack of electric wires.

According to Kenjiro Fukuda of the RIKEN Center for Emergent Matter Science, “This is a nice step forward in the quest to make self-powered medical monitoring devices that can be placed on human tissue. There are some important remaining tasks, such as the development of flexible power storage devices, and we will continue to collaborate with other groups to produce practical devices. Importantly, for the current experiments we worked on the analog part of our device, which powers the device and conducts the measurement. There is also a digital silicon-based portion, for the transmission of data, and further work in that area will also help to make such devices practical.

The research was carried out by RIKEN in collaboration with researchers from the University of Tokyo.

Source: http://www.riken.jp/