Researchers say AI prescribes better treatment than doctors Reply

See on Scoop.itScience Communication from mdashf

Two Indiana University researchers have developed a computer model they say can identify significantly better and less-expensive treatments than can doctors acting alone. It’s just the latest evidence that big data will have a profound impact on our health care system.

 

How much better? They claim a better than 50 percent reduction in costs and more than 40 percent better patient outcomes.

 

The idea behind the research, carried out by Casey Bennett and Kris Hauser, is simple and gets to the core of why so many people care so much about data in the first place: If doctors can consider what’s actually happening and likely to happen instead of relying on intuition, they should be able to make better decisions.

 

In order to prove out their hypothesis, the researchers worked with “clinical data, demographics and other information on over 6,700 patients who had major clinical depression diagnoses, of which about 65 to 70 percent had co-occurring chronic physical disorders like diabetes, hypertension and cardiovascular disease.” They built a model using Markov decision processes — which predict the probabilities of future events based on those immediately preceding them — and dynamic decision networks — which extend the Markov processes by considering the specific features of those events in order to determine the probabilities. Essentially, their model considers the specifics of a patient’s current state and then determines the best action to effect the best possible outcome.

 

Specifically, Bennett and Hauser found via a simulation of 500 random cases that their model decreased the cost per unit of outcome change to $189 from the $497 without it, an improvement of 58.5 percent. They found their original model improved patient outcomes by nearly 35 percent, but that tweaking a few parameters could bring that number to 41.9 percent.

 

IBM has been banging this drum loudly, most recently with two new commercial versions of its Watson system — one of which is designed to determine the best-possible course of treatment for lung cancer patient by analyzing their situations against a library of millions of pages of clinical evidence and medical research.

 

So, although we won’t hear “Paging Dr. Watson” at the hospital anytime soon, there’s an increasingly high chance our doctors will retire to their offices with our charts and ask a computer system of some sort what might be wrong with us and how they might best fix it.

 

See on gigaom.com

Making homemade guns on a 3-D printer becomes so real that experts suggests stronger laws on gunpowder Reply

See on Scoop.itScience Communication from mdashf

With controversy swirling over gun-sale background checks, limiting the size of weapon magazines and retaining Second Amendment rights, the problem of making homemade guns with 3-D printers has become a matter of public concern. 

 Laws mean little if a determined criminal or a hobbyist teen wants to make plastic guns or extra-high capacity magazines, says Hod Lipson, Cornell University professor of engineering and a pioneer in 3-D printing. 

“With a homemade 3-D printer, you can print a gun using ABS plastic, the same material that LEGOS are made out of. You can even use nylon, and that’s pretty tough,” he says. “You won’t be able to make a sniper rifle with a 3-D printer and it won’t shoot 10 rounds a second, but the gun you can make could be dangerous. And a high-capacity magazine is nothing more than a strong plastic box with a spring. It’s trivial to print.”

 

Lipson and co-author Melba Kurman just published a new book, “Fabricated: The promise and peril of a machine that can make (almost) anything.” (Wiley, 2013.) The book includes a chapter on “3-D printing and the law,” which addresses the legal and ethical challenges raised by 3-D printed firearms. The book also explores 3-D printing’s impact on consumer safety, intellectual property, and ethics.

 

As Lipson and Kurman detail, three-dimensional printers are intended to do the world good. In industry, 3-D printers can make hard-to-find spare parts and complex new devices. Researchers are developing techniques to 3-D print tailored and personalized body parts like he

See on www.sciencedaily.com

MIT: A Cheap and Easy Plan to Stop Global Warming Reply

See on Scoop.itScience Communication from mdashf

Here is the plan. Customize several Gulfstream business jets with military engines and with equipment to produce and disperse fine droplets of sulfuric acid. Fly the jets up around 20 kilometers—significantly higher than the cruising altitude for a commercial jetliner but still well within their range. At that altitude in the tropics, the aircraft are in the lower stratosphere. The planes spray the sulfuric acid, carefully controlling the rate of its release. The sulfur combines with water vapor to form sulfate aerosols, fine particles less than a micrometer in diameter. These get swept upward by natural wind patterns and are dispersed over the globe, including the poles. Once spread across the stratosphere, the aerosols will reflect about 1 percent of the sunlight hitting Earth back into space. Increasing what scientists call the planet’s albedo, or reflective power, will partially offset the warming effects caused by rising levels of greenhouse gases.

See on www.technologyreview.com

Birds’ UV Vision has arisen independently more than 14 times during evolution Reply

See on Scoop.itScience Communication from mdashf

Birds depend on their color vision for selecting mates, hunting or foraging for food, and spotting predators. Until recently, ultraviolet vision was thought to have arisen as a one-time development in birds. But a new DNA analysis of 40 bird species shows the shift between violet (shorter wavelengths on the electromagnetic spectrum) and ultraviolet vision has occurred at least 14 times.

 

“Birds see color in a different way from humans,” study co-author Anders Ödeen, an animal ecologist at Uppsala University in Sweden, told LiveScience. Human eyes have three different color receptors, or cones, that are sensitive to light of different wavelengths and mix together to reveal all the colors we see. Birds, by contrast, have four cones, so “they see potentially more colors than humans do,” Ödeen said.

 

Birds themselves are split into two groups based on the color of light (wavelength) that their cones detect most acutely. Scientists define them as violet-sensitive or ultraviolet-sensitive, and the two groups don’t overlap, according to Ödeen. Birds of each group would see the same objects as different hues.

 

The study researchers sequenced the DNA from the 40 species of birds, from the cockatiel to the whitebearded manakin. They extracted DNA from the bases of feather quills, blood, muscle or other tissue. From that DNA, the scientists reconstructed the proteins that make up the light-sensitive pigments in the birds’ eyes. Differences in the DNA revealed which birds were sensitive to violet light versus ultraviolet.

 

“That change is very simple, apparently,” Ödeen said. “It just takes a single mutation” in the DNA sequence. While that change may seem insignificant, it can be compared to the difference humans see between red and green. Why the bird lineages switched their color sensitivity — essentially species of a certain branch on the family tree evolved to have the reverse type of vision — is still something of a mystery. The ability to attract mates while still evading predators could be one reason. Ultraviolet light might also provide higher contrast that makes finding food easier. Other factors are environmental — open spaces have more UV light than do forests, for example. Ultimately, the color sensitivity may be a result of other changes that affect the amount of ultraviolet light the birds’ eyes receive.

mdashf‘s insight:

the suckers are real dreamers and visionaries 

See on news.discovery.com

Protein ‘filmed’ while unfolding at atomic resolution Reply

See on Scoop.itScience Communication from mdashf

When proteins get “out of shape”, the consequences can be fatal. They lose their function and in some cases form insoluble, toxic clumps that damage other cells and can cause severe diseases such as Alzheimer’s or Parkinson’s. Researchers at the Max Planck Institute for Biophysical Chemistry and the German Center for Neurodegenerative Diseases in Göttingen – in collaboration with Polish colleagues – have now “filmed” how a protein gradually unfolds for the first time. By combining low temperatures and NMR spectroscopy, the scientists visualized seven intermediate forms of the CylR2 protein while cooling it down from 25°C to – 16°C. Their results show that the most instable intermediate form plays a key role in protein folding. The scientists’ findings may contribute to a better understanding of how proteins adopt their structure and misfold during illness.

See on www.kurzweilai.net

An amazing invisible truth about Wikipedia hiding inside Wikipedia’s GeoTag Information Reply

See on Scoop.itScience Communication from mdashf

A large number of Wikipedia articles are geocoded. This means that when an article pertains to a location, its latitude and longitude are linked to the article. As you can imagine, this can be useful to generate insightful and eye-catching infographics.

 

A while ago, a team at Oxford built this magnificent tool to illustrate the language boundaries in Wikipedia articles. This led me to wonder if it would be possible to extract the different topics in Wikipedia.

 

This is exactly what I managed to do in the past few days. I downloaded all of Wikipedia, extracted 300 different topics using a powerful clustering algorithm, projected all the geocoded articles on a map and highlighted the different clusters (or topics) in red. The results were much more interesting than I thought. For example, the map on the left shows all the articles related to mountains, peaks, summits, etc. in red on a blue base map.  The highlighted articles from this topic match the main mountain ranges exactly.

 

See on olihb.com