Wearable devices can be used to detect the early signs of diabetes using an artificial intelligence (AI) network called DeepHeart and developed by Cardiogram, a study has found. Some 32m people in the US have diabetes, while a further 70m people are thought to be living with so-called pre-diabetes, according to GlobalData figures. With 88 percent of people who are pre-diabetic unaware of their condition, and one in four cases of diabetes going undiagnosed, DeepHeart could provide an easy and affordable means of diagnosing a condition with ever-increasing societal importance. The combination of AI and smart watches is another win for tech giants Apple and Google, as they continue to explore the realm of digital health. Apple's intentions to become a key player in the healthcare space are clear.

In a new study conducted with the UCSF Department of Medicine, a neural network developed by a startup called Cardiogram was able to detect diabetes with nearly 85 percent accuracy, just by looking at people's heart beats over time. As always, the study didn't require any fancy medical hardware -- just Apple Watches, Fitbits, Android Wear devices, and other wearables with heart rate sensors. "It's the hardest thing I've ever worked on, but the most rewarding," Cardiogram co-founder Brandon Ballinger told Engadget. Cardiogram has conducted similar studies in the past, like when it trained that neural network -- DeepHeart -- to search for telltale signs of strokes in a pool of roughly 6,000 users. This undertaking required even more work.

Before modern chemistry brought doctors blood and urine tests for diagnosing diabetes, they had to rely on their taste buds. Sweet-tasting pee has long been the disease's telltale biomarker; mellitus literally means honey. Too much sugar in your bodily fluids means your metabolism has gone haywire--either your cells aren't making insulin or they're not responding to it. But a little over a decade ago, a group of researchers discovered a less obvious link. One of the complications of diabetes is nerve damage, and in the cardiovascular system that damage can cause irregular heart rates.

The world's most valuable company crammed a lot into the tablespoon-sized volume of an Apple Watch. There's GPS, a heart-rate sensor, cellular connectivity, and computing resources that not long ago would have filled a desk-dwelling beige box. The wonder gadget doesn't have a sphygmomanometer for measuring blood pressure or polysomnographic equipment found in a sleep lab--but thanks to machine learning, it might be able to help with their work. Research presented at the American Heart Association meeting in Anaheim Monday claims that, when paired with the right machine-learning algorithms, the Apple Watch's heart-rate sensor and step counter can make a fair prediction of whether a person has high blood pressure or sleep apnea, in which breathing stops and starts repeatedly through the night. Both are common--and commonly undiagnosed--conditions associated with life-threatening problems, including stroke and heart attack.

Your Apple Watch can tell if you have hypertension or sleep apnea -- with the help of Cardiogram's deep neural network, DeepHeart, that is. The app-maker and the UCSF Health lab have conducted a study proving that wearables can suggest the presence of hypertension and sleep apnea with 82 percent and 90 percent accuracy, so long as they come equipped with heart rate sensors and accelerometers. According to Cardiogram, heart rate sensors can detect both conditions, because your body's autonomic nervous system connects your heart with the brain, stomach, esophagus, liver, intestines, pancreas and blood vessels. The company needed data to be able to train its AI to recognize heart rate patterns that denote the presence of the conditions, though, so it recruited 6,115 of its app's users to participate in an online study with the UCSF Health lab. Cardiogram managed to collect 30 billion sensor measurements composed of the subjects' heart rate and step counts, which it then fed to its AI.

The world's most valuable company crammed a lot into the tablespoon-sized volume of an Apple Watch. There's GPS, a heart-rate sensor, cellular connectivity, and computing resources that not long ago would have filled a desk-dwelling beige box. The wonder gadget doesn't have a sphygmomanometer for measuring blood pressure or polysomnographic equipment found in a sleep lab--but thanks to machine learning, it might be able to help with their work. Research presented at the American Heart Association meeting in Anaheim Monday claims that when paired with the right machine-learning algorithms, the Apple Watch's heart-rate sensor and step counter can make a fair prediction of whether a person has high blood pressure, or sleep apnea, in which breathing stops and starts repeatedly through the night. Both are common--and commonly undiagnosed--conditions associated with life-threatening problems, including stroke and heart attack.

The Google Pixel 2 is this week's biggest Android release by far, but if you're not up for new hardware, then turn your attention to the Play Store instead: There are plenty of fresh apps and games worth scoping out over the weekend. Game of Thrones: Conquest is an all-new game based on the hit HBO fantasy series, and it leads our latest Five to Try roundup. Also worth a look right now are the Google Pixel-esque Lawnchair Launcher, charming puzzle adventure Love You to Bits, heart-tracking app Cardiogram for Android Wear, and the silly touchscreen fun of Mmm Fingers 2. It might be a while before we get the eighth season of Game of Thrones, but you can kill time till then with the new Game of Thrones: Conquest game for Android. Based on the popular fantasy phenomenon, Conquest lets you become a lord in Westeros and build your own house, waging war as you interact with familiar characters from the series and capture more than 120 seats of power. In practice, it looks like a lot of busywork--tapping buttons to build things or execute actions, and then waiting for the timers to run down.

The Apple Watch has been found to detect a heart condition that affects some 2.7 million people in the US, a new study has revealed. By pairing the smartwatch's heart rate sensors with artificial intelligence, researchers developed an algorithm capable of distinguishing an irregular heartbeat, known as atrial fibrillation, from a normal heart rhythm - and with 97 percent accuracy. Atrial fibrillation, although easily treatable, has been difficult to diagnose and the team believes their work could pave the way for new methods to identify the abnormality. The Apple Watch has been found to detect a heart condition that affects some 2.7 million people in the US, a new study has revealed. The algorithm was accurate 97 percent of the time using the smartwatch's heart rate sensor (stock) University of California, San Francisco, in collaboration with the app Cardiogram, trained a deep neural network with heart readings from 6,158 Cardiogram users.

According to a study conducted through heartbeat measurement app Cardiogram and the University of California San Francisco, the Apple Watch is 97 percent accurate in detecting the most common abnormal heart rhythm, when paired with an AI-based algorithm. The study involved 6,158 participants recruited through the Cardiogram app on Apple Watch. Most of the participants in the UCSF Health eHeart study had normal EKG readings. However, 200 of them had been diagnosed with paroxysmal atrial fibrillation (an abnormal heartbeat). Engineers then trained a deep neural network to identify these abnormal heart rhythms from Apple Watch heart rate data.

Dennis Anselmo was glad he used an Apple Watch -- it saved his life when it spotted a dangerous heart condition. A range of studies already exist that prove Apple Watch can identify heart problems, but when its data is coupled with deep learning systems it can achieve much more. Having already built the world's most accurate wearable heart monitor, Apple's sensor development teams must now be exploring new sensor technologies. There have been claims these include a non-invasive diabetes sensor. We know the company's commitment to the sector runs deep.