Started by bayonetbrant, January 09, 2017, 11:08:31 AM
0 Members and 1 Guest are viewing this topic.
QuoteThanks to AI, computers can now see your health problemsBy Megan Molteni Published January 14, 2017Patient Number Two was born to first-time parents, late 20s, white. The pregnancy was normal and the birth uncomplicated. But after a few months, it became clear something was wrong. The child had ear infection after ear infection and trouble breathing at night. He was small for his age, and by his fifth birthday, still hadnt spoken. He started having seizures. Brain MRIs, molecular analyses, basic genetic testing, scores of doctors; nothing turned up answers. With no further options, in 2015 his family decided to sequence their exomesthe portion of the genome that codes for proteinsto see if he had inherited a genetic disorder from his parents. A single variant showed up: ARID1B.The mutation suggested he had a disease called Coffin-Siris syndrome. But Patient Number Two didnt have that diseases typical symptoms, like sparse scalp hair and incomplete pinky fingers. So, doctors, including Karen Gripp, who met with Twos family to discuss the exome results, hadnt really considered it. Gripp was doubly surprised when she uploaded a photo of Twos face to Face2Gene. The app, developed by the same programmers who taught Facebook to find your face in your friends photos, conducted millions of tiny calculations in rapid successionhow much slant in the eye? How narrow is that eyelid fissure? How low are the ears? Quantified, computed, and ranked to suggest the most probable syndromes associated with the facial phenotype. Theres even a heat map overlay on the photo that shows which the features are the most indicative match.In hindsight it was all clear to me, says Gripp, who is chief of the Division of Medical Genetics at A.I. duPont Hospital for Children in Delaware, and had been seeing the patient for years. But it hadnt been clear to anyone before. What had taken Patient Number Twos doctors 16 years to find took Face2Gene just a few minutes.Face2Gene takes advantage of the fact that so many genetic conditions have a tell-tale facea unique constellation of features that can provide clues to a potential diagnosis. It is just one of several new technologies taking advantage of how quickly modern computers can analyze, sort, and find patterns across huge reams of data. They are built in fields of artificial intelligence known as deep learning and neural netsamong the most promising to deliver AIs 50-year old promise to revolutionize medicine by recognizing and diagnosing disease.Genetic syndromes arent the only diagnoses that could get help from machine learning. The RightEye GeoPref Autism Test can identify the early stages of autism in infants as young as 12 monthsthe crucial stages where early intervention can make a big difference. Unveiled January 2 at CES in Las Vegas, the technology uses infrared sensors test the childs eye movement as they watch a split-screen video: one side fills with people and faces, the other with moving geometric shapes. Children at that age should be much more attracted to faces than abstract objects, so the amount of time they look at each screen can indicate where on the autism spectrum a child might fall.In validation studies done by the tests inventor, UC San Diego researcher Karen Pierce,1 the test correctly predicted autism spectrum disorder 86 percent of the time in more than 400 toddlers. That said, its still pretty new, and hasnt yet been approved by the FDA as a diagnostic tool. In terms of machine learning, its the simplest test we have, says RightEyes Chief Science Officer Melissa Hunfalvay. But before this, it was just physician or parent observations that might lead to a diagnosis. And the problem with that is it hasnt been quantifiable.A similar tool could help with early detection of Americas sixth leading cause of death: Alzheimers disease. Often, doctors dont recognize physical symptoms in time to try any of the diseases few existing interventions. But machine learning hears what doctors cant: Signs of cognitive impairment in speech. This is how Toronto-based Winterlight Labs is developing a tool to pick out hints of dementia in its very early stages. Co-founder Frank Rudzicz calls these clues jitters, and shimmers: high frequency wavelets only computers, not humans, can hear.Winterlights tool is way more sensitive than the pencil and paper-based tests doctors currently use to assess Alzheimers. Besides being crude, data-wise, those tests cant be taken more than once every six months. Rudziczs tool can be used multiple times a week, which lets it track good days, bad days, and measure a patients cognitive functions over time. The product is still in beta, but is currently being piloted by medical professionals in Canada, the US, and France.If this all feels a little scarily sci-fi to you, its useful to remember that doctors have been trusting computers with your diagnoses for a long time. Thats because machines are much more sensitive at both detecting and analyzing the many subtle indications that our bodies are misbehaving. For instance, without computers, Patient Number Two would never have been able to compare his exome to thousands of others, and find the genetic mutation marking him with Coffin-Siris syndrome.But none of this makes doctors obsolete. Even Face2Genewhich, according to its inventors, can diagnose up to half of the 8,000 known genetic syndromes using facial patterns gleaned from the hundreds of thousands of images in its databaseneeds a doctor (like Karen Gripp) with enough experience to verify the results. In that way, machines are an extension of what medicine has always been: A science that grows more powerful with every new data point.1UPDATE 3:00 pm Eastern 1/9/17 This story has been updated to correct Dr. Pierces relationship to RightEye; she is the author of the GeoPref Autism Test, which was licensed and further developed for commercialization by RightEye. An earlier version of this story incorrectly cited Dr. Pierce as RightEyes inventor
Quote from: bayonetbrant on January 15, 2017, 10:34:40 AMarchitecture in Antarcticahttp://www.bbc.com/news/magazine-38574003?SThisFB
Quote from: MetalDog on January 18, 2017, 09:04:08 PMRussian space agency and NASA teaming up on possible mission to Venus:http://www.space.com/35333-russia-nasa-venus-mission-venera-d.html
Quote from: MetalDog on January 19, 2017, 06:28:06 PMThank you O0 I love reading about space, but I'm not a big science fiction fan. Go figure. However, I happen to think that there's life in a lot of places in the universe. The problems are time and distance. That's why I believe that man will need to colonize our own solar system first before we can get anywhere else.
Quote from: MetalDog on January 22, 2017, 12:58:06 AMThanks, E. I have no basis in my belief other than sheer numbers. Billions of Galaxies? There HAS to be life out there. Whether it looks like us or not, I don't know. Might be. Might not. But the Mars rover just found mud remains and where there's mud remains, there was water and...you know the rest.I've stated this on site before, I truly believe in order to survive, man is going to have to colonize the solar system. Whether it's on space stations orbiting planets, in habitats on moons or planets or some combination. But it needs to happen. The human race is going to suck the planet Earth dry if we don't find alternate ways to live in harmony with the environment. And part of that is going to be learning to get resources off planet. At least mineral ones to begin with.
Quote from: Pete Dero on January 22, 2017, 06:06:10 AMQuote from: MetalDog on January 22, 2017, 12:58:06 AMThanks, E. I have no basis in my belief other than sheer numbers. Billions of Galaxies? There HAS to be life out there. Whether it looks like us or not, I don't know. Might be. Might not. But the Mars rover just found mud remains and where there's mud remains, there was water and...you know the rest.I've stated this on site before, I truly believe in order to survive, man is going to have to colonize the solar system. Whether it's on space stations orbiting planets, in habitats on moons or planets or some combination. But it needs to happen. The human race is going to suck the planet Earth dry if we don't find alternate ways to live in harmony with the environment. And part of that is going to be learning to get resources off planet. At least mineral ones to begin with.It is very difficult to create life. But like you said with billions of galaxies each having billions of stars life should exist elsewhere.I really hope we find it soon so we can get rid of that religious idea that the universe was build for mankind.Some scientist think we can even find some form of life in our solar system (in the ice on the poles of Mars, in subsurface seas on moons of Jupiter, ...)About colonization I feel different : we abuse one planet, so instead of cleaning that one we just move to the next one to do the same thing there.We can get minerals by mining asteroids without the need to live there. I do support the scientific reasons to go to other planets.We still have about 4 billion years before our sun goes into its red giant period so there is some time left ... The fact that Earth seems destined to support human life is logical. If some parameters were different we wouldn't be here to even think about all this.