healthcare technology

Deep learning is helping to make prosthetic arms behave more naturally.

 

 

Each year, more than 150,000 people have a limb amputated after an accident or for various medical reasons. Most people are then fitted with a prosthetic device that can recognize a limited number of signals to control a hand or foot, for example.

But Infinite Biomedical Technologies, a Baltimore startup company and another firm are taking advantage of better signal processing, pattern recognition software and other engineering advances to build new prosthetic controllers that might give amputees an easier life.

 

The key is boosting the amount of data the prosthetic arm can receive, and helping it interpret that information. “The goal for most patients is to get more than two functions, say open or close, or a wrist turn. Pattern recognition allows us to do that,” says Rahul Kaliki, CEO of Infinite. “We are now capturing more activity across the limb.”

 

Kaliki’s team of 14 employees are building the electronics that go inside other companies’ prosthetic arms. Infinite’s electronic control system, called Sense, records data from up to eight electrodes on his upper arm. Through many hours of training on the company’s tablet app, the device can detect the intent encoded in Rubin’s nerve signals when he moves his upper arm in a certain way. Sense then instructs his prosthetic hand to assume the appropriate grip.

 

read the original unedited story at  at https://www.wired.com/story/bionic-limbs-learn-to-open-a-beer/

 

 

 

It might not be long before algorithms routinely save lives—as long as doctors are willing to put ever more trust in machines.

 

An algorithm that spots heart arrhythmia shows how AI will revolutionize medicine—but patients must trust machines with their lives.

 

A team of researchers at Stanford University, led by Andrew Ng, a prominent AI researcher and an adjunct professor there, has shown that a machine-learning model can identify heart arrhythmias from an electrocardiogram (ECG) better than an expert.

 

The automated approach could prove important to everyday medical treatment by making the diagnosis of potentially deadly heartbeat irregularities more reliable. It could also make quality care more readily available in areas where resources are scarce.

 

The work is also just the latest sign of how machine learning seems likely to revolutionize medicine. In recent years, researchers have shown that machine-learning techniques can be used to spot all sorts of ailments, including, for example, breast cancer, skin cancer, and eye disease from medical images.

 

more at : https://www.technologyreview.com/s/608234/the-machines-are-getting-ready-to-play-doctor/