vascular disease


Deception detection on the Bag-of-lies dataset

#artificialintelligence

Lie detection has been a topic of interest since the beginning of the 20th century, and since then a lot of different methods have been used to try to achieve this, such as changes in inspiration-expiration ratio, increases in systolic blood pressure, dilatation of the pupil size, heart rate, etc. Usually, when people think about lie detection, the most common method that comes to mind is the polygraph. This method combines various techniques to detect autonomic reactions which include changes in body functions that are not easily controlled by the conscious mind. However, still requires a large amount of training which is achieved by control questions where the answers are known to later compare how the subject reacts. Polygraph offers an accuracy of around 70% in the general population⁴, a number which is greater than trained humans can achieve by just looking at the person, however, this doesn't mean that this method is infallible since people have found ways to cheat the system by just training or by using drugs to suppress these reactions. In general, these methods usually have not offered as good results as to be used in court in most countries.


New AI partnership to develop cardiovascular medication

#artificialintelligence

British company Exscientia has been working with several pharmaceutical companies (including Sanofi, GlaxoSmithKline, and Roche), offering its artificial intelligence system to aid the drug discovery process. With the new announcement, Bayer are to back the project with €240 million ($266 million) over the course of three years. The focus of this digital transformation of the medication development process will be on the application of artificial intelligence to speed up the discovery of small molecule drug candidates. The drug candidates will have targets linked to oncology and cardiovascular disease. The deal between the two companies, as PharmaPorum reports, will see Bayer owning the rights to the compounds and Exscientia will receive royalties relating to future sales.


[Interview] How AI, robotics and digital technologies are transforming healthcare

#artificialintelligence

New Delhi: Advances in technology and medical research could mean seismic changes in the healthcare industry. Soon, cancer, heart disease, diabetes and other debilitating illnesses could be defeated - perhaps, 20 years from now (unbelievable as it may sound) - thanks to scientists, medical doctors and researchers who are working vigorously, making stupendous progress on all these fronts. Over the last decade, healthcare is one of the industries that has evolved the most, yet, we're going to see changes in the way diseases are being treated. It's evident that we're going to witness drastic changes in a number of dimensions - from robots in the role of healthcare professionals to smart technology and artificial intelligence tools that will improve the quality of care and population health. Dr Sanjay Pandey, Head - Andrology and Reconstructive Urology - Kokilaben Dhirubhai Ambani Hospital, Mumbai, spoke on how digital technology, robotics and AI are transforming the face of medicine.


Amazon Web Services at HIMSS20: Three key trends to watch

#artificialintelligence

Amazon Web Services (AWS) will have a large presence at the big HIMSS20 event (Booth 858), and it will be discussing a variety of technologies and issues with attendees. Among other things, AWS will be discussing three trends it has identified as important for HIMSS20 attendees: predicting patient health events, personalizing the consumer health journey, and promoting interoperability in healthcare. AWS says there is a renaissance in healthcare as more of its clients leverage machine learning technologies to uncover new ways to enhance patient care, improve health outcomes and, ultimately, save lives. "As the country moves toward value-based care, artificial intelligence and machine learning, paired with data interoperability, will improve patient outcomes while driving operational efficiency to lower the overall cost of care," said Dr. Shez Partovi, director of worldwide business development for healthcare, life sciences and genomics at AWS. "By enabling data liquidity securely and supporting healthcare providers with predictive machine learning models, clinicians will be able to seamlessly forecast clinical events, like strokes, cancer or heart attacks, and intervene early with personalized care and a superior patient experience." An example of work like this already underway is a machine learning model developed by Cerner and AWS that predicts congestive heart failure up to 15 months before clinical manifestation.


Top 10 AI-Powered Gadgets From World's Biggest Tech Show: CES 2020

#artificialintelligence

CES has always been an inclusive platform for hosting newer trends, innovative technologies, and smart home gadgetry. However, CES wouldn't be complete without the showcase of the most buzzed-about gadgets that are not only innovative but also weird. In this article, we list down the top ten whackiest gadgets from CES 2020. At CES 2020, popular Chinese wearable giant Huami announced its outdoor smartwatch known as Amazfit T-REX. Amazfit T-REX has an in-built AI health monitor, which comes affordable as well as durable.


How artificial intelligence can be used for aneurysm follow-up – Tech Check News

#artificialintelligence

In the Aortic session at this year's Controversies and Updates in Vascular Surgery meeting (CACVS; 23–25 January, Paris, France), Stéphan Haulon and Dominique Fabre will discuss the rise of artificial intelligence (AI), informing delegates how this technology could be the solution for aortic aneurysm follow-up. Here, they give a summary of their key points. AI applied to medicine has been growing exponentially in recent years, according to the number of scientific publications in the field.


Active Learning Applied to Patient-Adaptive Heartbeat Classification

Neural Information Processing Systems

While clinicians can accurately identify different types of heartbeats in electrocardiograms (ECGs) from different patients, researchers have had limited success in applying supervised machine learning to the same task. The problem is made challenging by the variety of tasks, inter- and intra-patient differences, an often severe class imbalance, and the high cost of getting cardiologists to label data for individual patients. We address these difficulties using active learning to perform patient-adaptive and task-adaptive heartbeat classification. When tested on a benchmark database of cardiologist annotated ECG recordings, our method had considerably better performance than other recently proposed methods on the two primary classification tasks recommended by the Association for the Advancement of Medical Instrumentation. Additionally, our method required over 90% less patient-specific training data than the methods to which we compared it.


Opinion: When the mind gives out before the machine

#artificialintelligence

Margaret Munro is a Vancouver-based journalist. My father was preparing breakfast when his blood pressure dropped and he blacked out. Keeling over backward, he hit his head so hard it punched a hole in the wall. "Good thing I didn't hit the stud," he said in the emergency room at Nanaimo Regional General Hospital. He was stable, but the wobbly lines running across a monitor wired to his chest showed the critical state of his 92-year-old heart. It had been repaired before, but now doctors offered something more – a pacemaker to keep it beating steadily. Hundreds of thousands of Canadians have the ingenious devices, and many of them, like my father, likely had them implanted without considering all the implications. A cardiologist stayed late, after his scheduled surgeries, to wire Dad's heart with a German-designed Biotronik pacemaker that would restore a healthy heart rhythm. The procedure, done under local anesthetic, took less than 30 minutes.


Identifying Patients at Risk of Major Adverse Cardiovascular Events Using Symbolic Mismatch

Neural Information Processing Systems

Cardiovascular disease is the leading cause of death globally, resulting in 17 million deaths each year. Despite the availability of various treatment options, existing techniques based upon conventional medical knowledge often fail to identify patients who might have benefited from more aggressive therapy. In this paper, we describe and evaluate a novel unsupervised machine learning approach for cardiac risk stratification. The key idea of our approach is to avoid specialized medical knowledge, and assess patient risk using symbolic mismatch, a new metric to assess similarity in long-term time-series activity. We hypothesize that high risk patients can be identified using symbolic mismatch, as individuals in a population with unusual long-term physiological activity.


Selecting Optimal Decisions via Distributionally Robust Nearest-Neighbor Regression

Neural Information Processing Systems

This paper develops a prediction-based prescriptive model for optimal decision making that (i) predicts the outcome under each action using a robust nonlinear model, and (ii) adopts a randomized prescriptive policy determined by the predicted outcomes. The predictive model combines a new regularized regression technique, which was developed using Distributionally Robust Optimization (DRO) with an ambiguity set constructed from the Wasserstein metric, with the K-Nearest Neighbors (K-NN) regression, which helps to capture the nonlinearity embedded in the data. We show theoretical results that guarantee the out-of-sample performance of the predictive model, and prove the optimality of the randomized policy in terms of the expected true future outcome. We demonstrate the proposed methodology on a hypertension dataset, showing that our prescribed treatment leads to a larger reduction in the systolic blood pressure compared to a series of alternatives. A clinically meaningful threshold level used to activate the randomized policy is also derived under a sub-Gaussian assumption on the predicted outcome.