Posts Tagged ‘diagnosis’
IBM’s Watson Makes the Move From Answering Trivia Questions to Making Medical Diagnoses
What is...Toronto (General Hospital)?
on Jeopardy!, its massive databanks were filled with encyclopedias, novels, film scripts, and history books. These days, Watson is more into medical journals and misspelled Yahoo Answers blog posts about weird rashes and vague abdominal pains. Watson is maturing, and prepping for his first non-trivia, real-world application: medical diagnoses. He's all *sniff* grown up!
We've known medicine was to be the next step for Watson , but just recently, IBM gave a short demonstration of Watson's progress. Watson isn't the first attempt at an automated diagnosis program--we documented , and has been around for a few years--but Watson's incredible power, depth of knowledge, and ability to understand natural human language puts it in a totally different league. Diagnosing an ailment isn't really that much different from answering a trivia question; Watson takes in as much information as possible from the question, eliminating the potential answers as new information renders them impossible, and comes up with a list of likely answers. An example : "As more clues were unveiled - blurred vision, family history of arthritis, Connecticut residence - Watson's suggested diagnoses evolved from uveitis to Behcet's disease to Lyme disease. It gave the final diagnosis a 73 percent confidence rating."
While on Jeopardy!, Watson could only give one answer, but in medicine, it lists all possible answers, along with the percent likeliness. An 80% possibility of accuracy is enough for Watson to risk money on Jeopardy, but when working with possible diagnoses, that still leaves a one in five chance that the patient is afflicted with something else, so Watson is designed to divulge even the less likely answers.
Watson's human language recognition skills also allows it to input an entirely new sector of information: anecdotal evidence. Anecdotal evidence is not necessarily reliable, of course, but can still be extremely useful--it's worth noting that a patient's description of symptoms is anecdotal, and still very important to diagnosis. Watson is able to trawl through the internet, picking up the oodles of medical information out there and adding it to its memory banks. Being able to understand that, say, a "dry mouth" is the same as xerostomia can make legitimate use of all those confused forums.
Of course, Watson isn't designed to replace a doctor's diagnostic instincts. Instead, it's more like a futuristic reference book. There's simply too much information out there these days, in too many places and added too frequently, for any doctor to keep up. Watson could help keep track of all the new drugs, studies, journals, and anecdotal evidence.
Diagnosis systems using Watson are still likely a few years away, but IBM is working on ways to leverage Watson's abilities even to hospitals with budgets too small to afford a multimillion-dollar Watson of their own. iPad apps were mentioned as a distinct possibility--doctors could tap into an off-site Watson with an iPad, shoot off a few queries and receive an answer immediately. And as more medical data is digitized, Watson will only get stronger and more useful.
[]
New Handheld Melanoma Scanner Instantly Identifies Skin Cancers With Laser Light
Called the Verisante Aura, the device employs Raman spectroscopy to identify the molecular makeup of moles by changing the vibrational state of the molecular bonds in a skin growth. Shining a particular laser light on those bonds causes a shift in the kind of light that is reflected back to a sensor, and that shift belies exactly what kinds of molecules are there and in what concentration they exist.
The device then checks the spectral signature against a database containing examples of melanoma and other skin diseases. By simply shining some laser light on the skin, a doctor can get a near-instantaneous red or green light regarding whether a growth requires further diagnosis via biopsy.
It’s not a magic wand for diagnosis, and regulatory agencies could take issue with the fact that clinicians might rely too heavily on such a technology, which could produce false negatives or otherwise discourage doctors from requesting a biopsy when one might be advisable. But it could also greatly inform the process by which dermatologists identify potential problem areas and reduce the number of needless biopsies which—aside form causing a certain degree of physical pain—tie up laboratories and pile onto overall health care costs.
[]
Diagnosis of STDs Could Be As Quick As Peeing On A Chip And Putting It In Your Phone
While it’s still too early for the technology to really have taken shape, these nanotechnology chips would be similar to pregnancy tests. After putting urine or saliva on the chip, the user will receive results within minutes that tell them which STD, if any, they’ve contracted. Researchers hope that these confidential self-diagnosis devices would help encourage more people to get tested, without the embarrassment that accompanies seeing a doctor or going to a clinic.
Funders including the Medical Research Council have invested 4 million pounds into the technology’s development, which, if successful, could be a boon for promoting sexual health. Developers expect that the devices will one day be sold in vending machines in pharmacies, supermarkets and night clubs. Wouldn’t it just be easier to buy a condom?
[Guardian]
Cell Phone Accelerometer Tech Could Predict When a Horse Is About to Go Lame
Accelerometers, of course, are the tiny sensors that allow our phones to sense acceleration and orientation. They’re made of tiny piezoelectric sensors, three of which are arrange in right angles to one another. Each carries a tiny charge when compressed by a force like motion or gravity, giving it a keen sense of force in all three dimensions.
Healthy horses trot with symmetric gaits, and the researchers think an accelerometer placed at a horse’s center of gravity – along the top of its neck above the shoulders – should be able to detect an asymmetry in equestrian gaits. In a test on 12 healthy horses, the sensor accurately diagnosed their trots as symmetrical. The team now plans to run a tests on lame horses to see if deviations in that symmetry can be detected long before the eye can detect developing lameness.
If it works, the device could allow trainers to detect lameness before it worsens, getting them treatment before the condition becomes serious. If that works, it could be used to evaluate other gaits. Who knows? It might spawn a whole scientific field of racehorse evaluation rooted in objective math rather than hype, circumstance, and hope, taking all the fun out of your gambling problem.
[]
Darpa’s Genetic Diagnostic Suite Will Know You’re Sick Before You Do
The sensor detects changes in gene expression that occur in people exposed to viruses like the common cold, flu, or the respiratory syncytial virus.
Led by Dr. Geoffrey Ginsburg, director of Duke's Institute for Genome Science & Policy, the team identified 30 genetic markers that are activated by viruses. In some cases, the changes occurred hours or days before symptoms started.
This approach would let doctors and public-health officials make quick diagnoses before someone even appears sick. Current tests look for presence of the actual pathogen, but that takes longer and doesn't work until a person has symptoms, Ginsburg says.
The team started human trials last year, monitoring 80 people in four studies. Healthy people were exposed to three viral strains, and their blood, urine and saliva were then tested for specific gene signatures that would characterize illness, DangerRoom reports.
The next step is to analyze an ongoing study of Duke freshmen living in dorms. Participants were asked to file daily reports about their health and provide blood and other samples as requested, according to a
Darpa provided $19.5 million to fund the study, seeing potential in a system that can evaluate military personnel before they're deployed. An early-warning system could also help quarantine troops before they can infect others.
The research could lead to public-health benefits well beyond the military, however. The team also found that genetic signatures for viral infections are different from those triggered by bacterial infections. Definitive information about a patient's ailment can make antibiotic-resistant superbugs less likely, if fewer doctors prescribe antibiotics when they're not necessary.
What's more, public health agencies could use the technology to isolate outbreaks of influenza virus, possibly stemming pandemics before they can spread.