Cardiology/Vascular Diseases


Three Ways AI Will Improve Hospital Outcomes

#artificialintelligence

Google is developing tools to analyze large volumes of electronic health records (EHRs) and identify patient groups at risk of cardiac arrest, illness relapse, or other events, therefore reducing the likelihood of emergency hospital visits and inpatient stays. In Paris, a group of public hospitals is applying data analytics and machine learning to predict times of high patient volumes, allowing facilities to adjust resources in response to admission trends. Other market players are exploring AI algorithms and analytics for health applications including genomic-based precision medicine, cancer treatment protocols, wearable health device monitoring, and clinical trial enrollment. IBM's Watson Health analyzed cancer center data to identify potential treatments previously not considered by doctors; another Watson technology used at a neurological institute helped identify five new genes associated with ALS.


How can machine learning help your organization?

#artificialintelligence

Examples include systems that automatically replenish inventory based on weather patterns and historical trends, or that optimize truck routes using Google API data on traffic. That means moving the understanding of data--including predictive analytics--from executive dashboards to core business processes. This data is analyzed against historical patterns for thousands of other patients and include outcomes of those data patterns, such as a heart attack or stroke. In this case, the machine learning system takes only three data sets into account: traffic, weather, and route data.



Cardiologist-Level Arrhythmia Detection With Convolutional Neural Networks

@machinelearnbot

Each record is annotated by a clinical ECG expert: the expert highlights segments of the signal and marks it as corresponding to one of the 14 rhythm classes. We collect a test set of 336 records from 328 unique patients. For the test set, ground truth annotations for each record were obtained by a committee of three board-certified cardiologists; there are three committees responsible for different splits of the test set. For each record in the test set we also collect 6 individual annotations from cardiologists not participating in the group.


Algorithm spots dodgy hearts better than an expert doctor

#artificialintelligence

A team of researchers at Stanford University, led by Andrew Ng, a prominent AI researcher and an adjunct professor there, has shown that a machine-learning model can identify heart arrhythmias from an electrocardiogram (ECG) better than an expert. The automated approach could prove important to everyday medical treatment by making the diagnosis of potentially deadly heartbeat irregularities more reliable. The Stanford team trained a deep-learning algorithm to identify different types of irregular heartbeats in ECG data. Eric Horvitz, managing director of Microsoft Research and both a medical doctor and an expert on machine learning, says others, including two different groups from MIT and the University of Michigan, are applying machine learning to the detection of heart arrhythmias.


Artificial intelligence creates 3D hearts to predict patient survival

#artificialintelligence

Machine-learning has predicted death risk in people with serious heart disease faster and more accurately than current methods. New software, developed by scientists at Imperial College London, has created virtual 3D hearts of each patient that replicate the way the organ contracts with each beat. The technology has been tested on patients with pulmonary hypertension, a condition that leads to heart failure if not treated appropriately. In the new study, scientists used artificial intelligence or'machine learning' to predict survival in patients better and more quickly than current methods.


How artificial intelligence will impact the future of healthcare

#artificialintelligence

"IBM's Watson read 25 million scientific papers in a week." Quartz Magazine reported on an AI called AtomNet that promises to develop new drug treatments for dangerous diseases like Ebola and multiple sclerosis. Computer-assisted coding isn't exactly a form of artificial intelligence, but some in the industry promised that it would improve coder productivity and efficiency using a spell checker-like system called NLP. By auditing all charts prior to billing, eValuator acts as a highly skilled AI auditor, flagging any charts that are likely to have mistakes.


Machine learning mines EHRs to predict heart failure

#artificialintelligence

"Model performance was most strongly influenced by the diversity of data, basic feature construction and the length of the observation window," wrote Kenny Ng, research staff member in the Center for Computational Health and first author of the study. "In raw form, EHR data are highly diverse, represented by thousands of variants for disease coding, medication orders, laboratory measures, and other data types. The model performed best when window length was below two years, the training data set at least 4,000 patients, data were diverse as possible and data were confined to patients with more than 10 meetings with physicians in two years. First, the approach and methods need to be validated on larger patient data sets from multiple healthcare systems and additional disease targets to better understand the generalizability of the data characteristic impacts on predictive modeling performance," wrote Ng et al.


How can machine learning help your organization?

#artificialintelligence

Examples include systems that automatically replenish inventory based on weather patterns and historical trends, or that optimize truck routes using Google API data on traffic. That means moving the understanding of data--including predictive analytics--from executive dashboards to core business processes. This data is analyzed against historical patterns for thousands of other patients and include outcomes of those data patterns, such as a heart attack or stroke. In this case, the machine learning system takes only three data sets into account: traffic, weather, and route data.


Inspector gadget: how smart devices are outsmarting criminals

The Guardian

Richard Dabate told police a masked intruder assaulted him and killed his wife in their Connecticut home. Detectives suspected foul play and obtained data from Bates's Amazon Echo device. Smart cars, fridges, doorbells, watches, phones, Fitbits, sneakers, televisions, gaming consoles, coffee makers, Pacemakers – a fast proliferating list – all can monitor, record and be used as evidence. "I think everyone realises – good guys, bad guys, cops, robbers – that everything is being videotaped or tracked somehow," Andy Kleinick, the head of the Los Angeles police department's cyber crimes section, and a supervisor for the secret service's LA electronic crimes task force, said in an interview.