Computers Shown To Be Better Than Docs At Diagnosing, Prescribing Treatment 198
Lucas123 writes "Applying the same technology used for voice recognition and credit card fraud detection to medical treatments could cut healthcare costs and improve patient outcomes by almost 50%, according to new research. Scientists at Indiana University found that using patient data with machine-learning algorithms can drastically improve both the cost and quality of healthcare through simulation modeling.The artificial intelligence models used for diagnosing and treating patients obtained a 30% to 35% increase in positive patient outcomes, the research found. This is not the first time AI has been used to diagnose and suggest treatments. Last year, IBM announced that its Watson supercomputer would be used in evaluating evidence-based cancer treatment options for physicians, driving the decision-making process down to a matter of seconds."
Mycin (Score:5, Informative)
In the early 1970s, Mycin [wikipedia.org] achieved 69% accuracy of prescribing a "correct" treatment for a patient's condition, which was deemed better than human specialists.
The linked articles don't seem to include the absolute accuracy that it achieves, just the relative accuracy against doctors. I wonder if we've come any further than the basic expert system rules allowed 40 years ago.
Re:Interesting (Score:2, Informative)
Sadly, so are most general doctors.
Re:Mycin (Score:5, Informative)
Came here to mention this. Medical "expert systems" (a class of AI) have existed, and been better than humans at some things, for literally decades. However, you almost never hear about them anymore. With the vast advances in processing power, miniaturization, and power usage, we can today build pocketable devices that tremendously exceed the capabilities of something like Mycin. With the improvements in sensor technology, we can feed those systems more and better data than ever before. With widely available wireless Internet connectivity plus incredible storage densities, we can provide these systems with all the info they could ever need. With the advances in the science of AIs over the last four decades, we can make these systems "smarter" than was possible before. Finally, with the plummeting cost of such electronics, we can make such systems affordable to middle-class individuals, rather than exclusively to large and well-funded organizations.
Yet, they almost non-existent. We have a few smartphone apps that scratch the surface of what's possible. We have dedicated machines like continuous glucose monitors for diabetics, but they have very little in the way of smarts and no versatility. We have concepts and pseudo-prototypes of "medical tricorders" and such sci-fi devices, but they aren't generally set up to make recommendations. We have online web applications where users can input symptoms and be told what they might be, but those systems have no personal background or history of the user's health, and rely on the user measuring and providing data themselves.
Why haven't these things been combined?