Diabetes


Jennifer Sun, MD: Why Ophthalmology Needs Machine Learning

#artificialintelligence

There are now more than 100 million Americans with diabetes or prediabetes, according to a recent estimate from the Centers for Disease Control and Prevention (CDC). Worldwide, about 8.3% of adults, or some 415 million people, are affected by the condition. For ophthalmologists, rising global incidence of diabetes means more cases of diabetic eye conditions like diabetic retinopathy (DR) and diabetic macular edema (DME). In turn, physicians and health systems must prepare to tackle unprecedented levels of ophthalmic disease burden among the growing number of patients with diabetes. That means they're going to need some help.


Researchers combine wearable technology and AI to predict the onset of health problems

#artificialintelligence

A team of Waterloo researchers found that applying artificial intelligence to the right combination of data retrieved from wearable technology may detect whether your health is failing. The study, which involved researchers from Waterloo's Faculties of Applied Health Sciences and Engineering, found that the data from wearable sensors and artificial intelligence that assesses changes in aerobic responses could one day predict whether a person is experiencing the onset of a respiratory or cardiovascular disease. "The onset of a lot of chronic diseases, including type 2 diabetes and chronic obstructive pulmonary disease, has a direct impact on our aerobic fitness," said Thomas Beltrame, who led the research while at the University of Waterloo, and is now at the Institute of Computing in University of Campinas in Brazil. "In the near future, we believe it will be possible to continuously check your health, even before you realize that you need medical help." The study monitored active, healthy men in their twenties who wore a shirt for four days that incorporated sensors for heart rate, breathing and acceleration.


AI, wearable technology collaborate to predict health problems

#artificialintelligence

Researchers from the University of Waterloo in Ontario, Canada, have developed artificial intelligence (AI) capable of using wearable-collected data to predict the onset of health problems. Findings were published Feb. 23 in the Journal of Applied Physiology. The study aimed to outline a possible foundation for wearable technology and AI could partner to predict illness. Researchers hope the technology pairing could assess changes in aerobic responses to identify the onset of respiratory or cardiovascular disease. "The onset of a lot of chronic diseases, including type 2 diabetes and chronic obstructive pulmonary disease, has a direct impact on our aerobic fitness," said first author Thomas Beltrame, of the Institute of Computing in University of Campinas in Brazil, and colleagues.


This tiny chip uses A.I. to control sugar levels for critical diabetes patients without nurses present

#artificialintelligence

For critically ill diabetes patients, making sure their blood sugar levels are correct is crucial. If they drop then glucose needs to be administered, but if they rise too high then insulin is required. Currently, this is done by nurses in hospitals, but one start-up has created an "artificial pancreas" that can automate the process, and it's a chip that's smaller than a thumbnail. Boston, MA.-based Admetsys has created a solution that can constantly monitor blood sugar levels in real time. It's artificial intelligence (AI) algorithm then triggers its software to either administer glucose or insulin via the drip that a patient is connected to.


Amazon is building a 'health & wellness’ team within Alexa as it aims to upend health care

USATODAY

The nucleus of Amazon's effort to upend the health-care market may very well be the Echo device in your living room. According to an internal document obtained by CNBC, Amazon has built a team within its Alexa voice-assistant division called "health & wellness," which includes over a dozen people and is being led by Rachel Jiang, who has spent the last five years at Amazon in various roles including advertising and video. The team's main job is to make Amazon's Alexa voice assistant more useful in the health-care field, an effort that requires working through regulations and data privacy requirements laid out by HIPAA (the Health Insurance Portability and Accountability Act), according to people familiar with the matter. The group is targeting areas like diabetes management, care for mothers and infants and aging, said the people, who asked not to be named because the work is confidential. Echo/Alexa opens up a new sales channel for Amazon.


Google sets sights on frontier of artificial intelligence: curing blindness

#artificialintelligence

Scientists in Google's health division are developing technology they believe can help doctors better diagnose, treat and prevent vision impairment caused by diabetic retinopathy -- a common eye disease among diabetics that can lead to blindness. The technology is a cloud-based algorithm that analyzes photographic images of the eye for signs of the disease and grades the severity of the problem. Signs include abnormal growth of blood vessels in the back of the eye that causes scarring and detachment of the retina. The algorithm is being tested in clinical trials and has not been approved by federal regulators. It is considered a medical device and would have to be approved by the U.S. Food and Drug Administration to be used in clinical care.


Voice Technology and AI: Powering Patient Experience & Expectations

#artificialintelligence

Understanding changes in patient experiences is an important facet towards enhancing patient engagement and centricity. It's clear that new digital devices and AI are changing the way that patients search for medical information on the internet, based on discussions at the recent PanAgora's Pharma Customer Experience Summit in New Jersey. Voice is the new digital experience. With the rise of novel Voice User Interface (VUI) household products, such as Amazon Alexa and Google Home and VUI integration in smart devices, Murray Izenwasser, VP of Digital Transformation and CMO of AAJ Technologies, discussed the big opportunity such devices offer to better connect patients with the biopharmaceutical industry. Izenwasser demonstrated that VUI device adoption has seen a faster market penetration rate compared to smart phones, TV, radio, and the Internet.


FDA Approved IDx-DR AI That Helps Doctors Diagnose Eye Disease

#artificialintelligence

US Food and Drug Administration (FDA) has approved IDx-DR AI; an artificial intelligence diagnostic device that doesn't need a specialized doctor to interpret the results and can detect a form of eye disease by looking at photos of the retina. IDx-DR is part of a growing trend of algorithms learning how to spot and diagnose disease. The best or say the unique part of this AI is, it is autonomous i.e there is no specialist looking over the system, which means it makes the clinical decision on its own, which again means that this technology can be used by a nurse or doctor who's not an eye specialist. In one clinical trial, this IDx-DR AI system was given more than 900 images and this system has correctly detected retinopathy about 87 percent of the time, moreover, it could correctly identify those who didn't have the disease about 90 percent of the time, which is appreciative in the field of artificial intelligence. For your info; Diabetic retinopathy is the most common vision complication people with diabetes, but is still fairly rare -- there are about 200,00 cases per year.


On Learning Sparsely Used Dictionaries from Incomplete Samples

arXiv.org Machine Learning

Most existing algorithms for dictionary learning assume that all entries of the (high-dimensional) input data are fully observed. However, in several practical applications (such as hyper-spectral imaging or blood glucose monitoring), only an incomplete fraction of the data entries may be available. For incomplete settings, no provably correct and polynomial-time algorithm has been reported in the dictionary learning literature. In this paper, we provide provable approaches for learning - from incomplete samples - a family of dictionaries whose atoms have sufficiently "spread-out" mass. First, we propose a descent-style iterative algorithm that linearly converges to the true dictionary when provided a sufficiently coarse initial estimate. Second, we propose an initialization algorithm that utilizes a small number of extra fully observed samples to produce such a coarse initial estimate. Finally, we theoretically analyze their performance and provide asymptotic statistical and computational guarantees.


FDA Approves AI That Can Analyze Your Eyes

#artificialintelligence

IDx-DR is a software program that can detect a certain type of eye disease from photos of a human retina, and it was just approved by the US Food and Drug Administration (FDA). This is a huge win for artificial intelligence (AI) and MedTech development: this is the first time the FDA has approved an AI-powered diagnostic device that doesn't require a doctor to interpret the results. Diabetic retinopathy is an eye disease in which an excess of blood sugar damages blood vessels located in the back of the eye. It's the most common vision malady for people afflicted with diabetes, with about 200,000 new cases occurring per year. After photos of a patient's retina are taken with a special retinal camera, IDx-DR's algorithm verifies that the picture quality is good enough to use for analysis.