Cardiology/Vascular Diseases


AI estimates a person's risk of dying from heart disease in the next 30 days

Daily Mail - Science & tech

Scientists in the US are using artificial intelligence (AI) to gauge a patient's risk of dying from heart disease. A team from the Massachusetts Institute of Technology created a system called RiskCardio. The technology was made for patients with acute coronary syndrome (ACS), which covers a range of conditions that suddenly reduce blood flow to the heart. RiskCardio works off just 15 minutes of a patient's'raw electrocardiogram (ECG) signal', which records the heart's rhythm and electrical activity. It then draws on a sample of ECG data to sort that particular patient into a'risk category'.


Automated and Interpretable Patient ECG Profiles for Disease Detection, Tracking, and Discovery

#artificialintelligence

The ECG remains the most widely used diagnostic test for characterization of cardiac structure and electrical activity. We hypothesized that parallel advances in computing power, machine learning algorithms, and availability of large-scale data could substantially expand the clinical inferences derived from the ECG while at the same time preserving interpretability for medical decision-making. We identified 36 186 ECGs from the University of California, San Francisco database that would enable training of models for estimation of cardiac structure or function or detection of disease. We segmented the ECG into standard component waveforms and intervals using a novel combination of convolutional neural networks and hidden Markov models and evaluated this segmentation by comparing resulting electrical intervals against 141 864 measurements produced during the clinical workflow. We then built a patient-level ECG profile, a 725-element feature vector and used this profile to train and interpret machine learning models for examples of cardiac structure (left ventricular mass, left atrial volume, and mitral annulus e-prime) and disease (pulmonary arterial hypertension, hypertrophic cardiomyopathy, cardiac amyloid, and mitral valve prolapse).


Artificial Intelligence Can Now Gauge Your Risk of Cardiovascular Death

#artificialintelligence

The benefits of AI in the health care spectrum are truly life-changing… and quite literally saving lives. Finally, some non-scary artificial intelligence (AI) news that won't scare the living bejeezus out of you: artificial intelligence has proven to be a key feather in the transformative cap of health care We are benefitted by AI when it can trumpet the need for preventative interventions by predicting such health threats as catching type 1 diabetes and helping predict breast cancer, along with its role in automated operations and precision surgery. Yes, the benefits of AI in the health care spectrum are truly life-changing… and quite literally saving lives. Researchers at MIT's Computer Science and Artificial Intelligence Laboratory (CSAIL) are using machine learning to estimate the risk of cardiovascular death. The system, RiskCardio, focuses on patients who have survived an acute coronary syndrome (ACS) and can better predict the risk of death caused by cardiovascular issues that block or reduce blood flow.


Artificial Intelligence (AI) Stats News: AI Is Actively Watching You In 75 Countries

#artificialintelligence

Recent surveys, studies, forecasts and other quantitative assessments of the impact and progress of AI highlighted the strong state of AI surveillance worldwide, the lack of adherence to common privacy principles in companies' data privacy statement, the growing adoption of AI by global businesses, and the perception of AI as a major risk by institutional investors. Using just the first fifteen minutes of a patient's raw electrocardiogram (ECG) signal, the tool produces a score that places patients into different risk categories. Patients in the top quartile were nearly seven times more likely to die of cardiovascular death when compared to the low-risk group in the bottom quartile. U.S. AI and machine learning startups raised $6.62 billion so far in 2019, and international startups raised $6.79 in the same period. The global total for all of 2018 was $19.5 billion [Crunchbase News] The North America AI chip market is estimated to reach $30.62 billion in 2027, up from $2.5 billion in 2018 [ResearchAndMarkets] The Asia Pacific AI chip market is estimated to reach $22.27 billion in 2027, up from $1.03 billion in 2018 [ResearchAndMarkets] "An AI-equipped surveillance camera would be not a mere recording device, but could be made into something closer to an automated police officer"--Edward Snowden "When you get into the millions, you can really start to generate the levels at which humans stop understanding the correlations, and the machines start to understand the correlations"--Ricky Knox, co-founder and CEO, Tandem Bank "As AI gets better at performing the routine tasks traditionally done by humans, only the hardest ones will be left for us to do. But wrestling with only difficult decisions all day long is stressful and unpleasant"--Fred Benenson, former vice president of data, Kickstarter "AI can do things previously unimaginable with the volume, velocity, variety and veracity of big data. It can deliver an edge given the information intensity of all of the processes in asset management"--Amin Rajan, CEO, Create-Research "By 2025, a quarter of all miles driven will be driven by on-demand services"--Amy Wyron, vice president of business solutions, Gett


AI detects congestive heart failure with one heartbeat

#artificialintelligence

A new study has reported success in identifying severe heart failure in 100% of cases using a single heartbeat recording from an electrocardiogram (ECG). Medically, the condition called congestive heart failure (CHF) refers to a chronic loss of pumping power in the heart which is progressive. It is fairly common, causes significant illness and disability, and pushes up the costs of medical care. It affects about 26 million people around the world, and is more common in the elderly. It causes a considerable number of deaths, with about 40% mortality among the most severe cases.


Pfizer launches pilot with home robot Mabu to study patient response to AI

#artificialintelligence

Pharmaceutical giant Pfizer today announced plans to launch a one-year pilot program with robotics company Catalia Health, maker of Mabu, a home robot that coaches patients on health and prescription drugs. Mabu uses voice interactions powered by conversational AI to assess a user's mood, record data, manage symptoms, and provide helpful information. The robot then supplies information back to medical professionals -- like caregivers or clinicians -- such as the frequency of medication usage or questions the robot was unable to answer. Mabu is also able to supply personalized responses and deploy affective computing to predict a user's emotional state. The robot is designed to help ensure patients take their medication and adjust to any drastic lifestyle changes resulting from an affliction, CEO Cory Kidd told VentureBeat in an interview.


Can clinical audits be enhanced by pathway simulation and machine learning? An example from the acute stroke pathway

#artificialintelligence

NHS England describes clinical audit as a way of identifying whether healthcare is being provided in accordance with agreed standards and where improvements could be made to improve outcomes for patients.1 Audits may be local or national. In England the Healthcare Quality Improvement Partnership (HQIP), on behalf of the National Health Service (NHS), is responsible for overseeing and commissioning more than 30 clinical audits, which form the National Clinical Audit Programme.2 These collect and analyse data supplied by local clinicians. The national audit covering stroke is the Sentinel Stroke National Audit Programme (SSNAP).3 Stroke is a leading cause of death and disability worldwide, with an estimated 5.9 million deaths and 33 million stroke survivors in 2010.4


AI Can Detect Heart Failure With 100% Accuracy By Hearing Just A Single Heartbeat

#artificialintelligence

In the recent past, it's become easier to detect heart conditions with technology. The Apple Watch has become pretty good at detecting arrhythmia for instance. But some researchers have been developing AI to detect heart problems, and one team may have the best version yet. According to a recent study published in the Biomedical Signal Processing and Control Journal, a team of researchers from the Universities of Surrey, Warwick and Florence have a new neural network that can detect cardiac anomalies from a single heartbeat with 100% accuracy. Their AI can quickly and accurately detect congestive heart failure (CHF) by analyzing one heartbeat on an electrocardiogram (ECG).


Machine-learning derived model can help predict risk of heart failure for diabetes patients

#artificialintelligence

Heart failure is an important potential complication of type 2 diabetes that occurs frequently and can lead to death or disability. Earlier this month, late-breaking trial results revealed that a new class of medications known as SGLT2 inhibitors may be helpful for patients with heart failure. These therapies may also be used in patients with diabetes to prevent heart failure from occurring in the first place. However, a way of accurately identifying which diabetes patients are most at risk for heart failure remains elusive. A new study led by investigators from Brigham and Women's Hospital and UT Southwestern Medical Center unveils a new, machine-learning derived model that can predict, with a high degree of accuracy, future heart failure among patients with diabetes.


AI can gauge the risk of dying from heart conditions

#artificialintelligence

The approach is based on the notion that greater variability between heartbeats reflects greater risk. Scientists trained the machine learning system using historical data for patient outcomes. If a patient survived, their heartbeats were deemed relatively normal; if a patient died, their heart activity was considered risky. The ultimate risk score comes by averaging the prediction from each set of consecutive heartbeats. There's plenty of work to be done, including refining the training data to account for more ages, ethnic backgrounds and genders.