To the 1 million global new amputees yearly (that’s one amputation every 30 second), the loss of a limb means that they have to adapt to a new world. Take India, one of the world’s most populated countries, for example. Only 3% of its buildings are adapted for accessibility, while the country counts more than half a million amputees. As part of this new adaptation process, amputees succumb to further injuries. Experts estimate that amputees fall at about 200 times the rate of healthy individuals; and seek medical attention comparable to the institutionalised elderly.
With aging populations, increased incidence of vascular diseases and trauma that lead to amputations, those numbers are likely to increase worldwide. Some countries like the U.S. could see their number of amputees nearly doubled by 2050.
But advances in prosthetics are helping to improve that world for amputees, even if the world around them does not necessarily improve. And these developments are happening fast. To get a clearer picture of what lies ahead, whom better to ask than a prosthetic wearer who develops robotic prostheses?
As such, we turned to György Lévay, Research Manager at Infinite Biomedical Technologies, who shared his insights into the present and future of prosthetics with us. From brain-controlled prostheses through A.I.-powered ones to supplementing healthy individuals with additional limbs, that future sounds like a wild one. So strap up as we dive into the latest advancements and into what’s next in the field of prosthetics.
From steampunk Egyptian mummies to cyberpunk brain-controlled prosthetics
Back in 2011, archeologists unearthed one of the oldest known prosthetic device; a wooden toe buried with Egyptian mummies some 3,000 years ago. While aesthetically it packs a steampunk look, this artificial toe was far from being a cosmetic item. After testing replicas, researchers found that they were indeed practical devices that helped in walking. While throughout the millennia the materials have changed, prosthetics only evolved in the recent decades with the advent of robotic prostheses.
In a seminal 2008 paper, researchers described how monkeys were able to control a mechanised arm with their brain activity. Controlling the prosthetic limb via electrodes implanted in their brains, it even allowed them to feed themselves fruits; that was a first with brain-controlled prostheses. Developments in subsequent years inched closer to human dexterity like the Modular Prosthetic Limb from 2011; and in 2020, patients with mind-controlled arm prosthesis were able to experience sensations of touch thanks to a new implant system.
With developments along those lines, it seemed like the future of this technology depended on battery life and robotic advancements. Now the narrative shifted to focus on how good of an artificial intelligence (A.I.) we can develop for prostheses. Indeed, A.I. could very well shape this field’s future. “In one way or another A.I. will be a part of advanced prostheses in the future,” György Lévay tells us. “Processing the amount of data running between our brain and limbs will require “smarter and smarter” algorithms as the technology advances.”
If you thought that the prosthetics field got all sci-fi with cyberpunk brain-controls, hold on as there’s more. Enter the age of the smart prosthesis as engineers couple A.I. with artificial limbs.
The age of smart prosthetics
The basis of incorporating A.I. in robotic prostheses is that the algorithm interprets nerve signals from the patient’s muscles that will allow for the prosthesis to be controlled more precisely. “A.I. has become a cornerstone of all externally powered (motor driven) upper limb prostheses R&D, but has been difficult to apply to lower limb prostheses,” Lévay says. However, a study published in Science Translational Medicine by a team of University of Michigan in March 2020 documents a new method to incorporate the technology with more types of prostheses.
Their new technique, based on regenerative peripheral nerve interface (RPNI), has surgeons use a small piece of muscle and wrap it around the end of the amputated nerve to produce amplified signals. Computational scientists on the team then apply machine learning algorithms to turn the signals into fine movements in a prosthetic. “The cool thing about this surgery is that it works on any type of amputation,” Cynthia Chestek, an author of the new study, told STAT. Participants were even able to use this smart prosthetic on their first try, Chestek added. They were able to perform fine motor controls such as picking up small toy blocks, making a fist and pinching fingers together.
“RPNI are being investigated heavily and have good potential to allow for more complex control capabilities,” confirms Lévay. Coupling A.I. with the process can give fine motor controls back to amputees. But he is quick to bring us back to the current state of affairs. “However these signals are relatively weak and currently require intramuscular electromyography (iEMG) sensors to be implanted. iEMG is a complicated, expensive and not yet widespread technology, which complicates the usability of RPNIs”. In fact, there are still several hurdles to be overcome before smart artificial limbs are commonplace.
Current limitations to the mass adoption of A.I. prosthetics
Firstly, many of the developments in the prosthetics field are proofs of concept. The A. I. prosthesis from the University of Michigan depends on a wired connection to a computer. “Everything that we’ve done so far has been six feet away from a computer cart [and people come in once or twice a week for the trial],” explained Cynthia Chestek. “We want people to be able to do this with an implantable device so we can move away from the cart”. There’s still work to be done before this concept leaves the lab.
Once it does leave the lab, the smart prosthesis will face another slowdown as it transitions to a company and seeks approvals from regulators like the FDA. Along with this transition comes the cost factor that could limit their adoption. “The use of A. I. increases the cost of a prosthetic device significantly (on the order of tens of thousands of dollars),” György Lévay tells The Medical Futurist.
This also extends to insurance structures. Artificial limb companies must demonstrate that value proposition so as to expand access to these devices. “The risks are in working with insurance companies to reimburse for these types of devices that are already very expensive and have a high degree of abandonment,” said Robert Armiger, project manager for amputee research at Johns Hopkins University’s Applied Physics Lab. “Insurance companies say, ‘we’re spending this much money on this device and people don’t wear it, and now you’re asking us to spend more money on a more advanced technology.”
Furthermore, there’s the science behind it all to consider. “Controlling a limb is very complicated; and we still have a limited understanding of how our brain manages to do it exactly,” György Lévay tells us. “The quality and complexity of the data; our lack of understanding of how exactly feedback mechanisms work in the human nervous system; and the uniqueness of individual neurological systems make it very difficult to train A. I. algorithms to predict human intent.” It is not only an engineering issue; it is a basic science issue, he adds.
A robotic hand(some) future
Without any doubt, there’s promise for amputees with advances in robotics, machine learning and prosthetics. With time, the costs of components will go down and these technologies will become integral parts of artificial limbs. These developments we hear of are incremental changes that will add up to improve future artificial limbs; improvements that will turn them into truly artificially intelligent limbs. We’re still years from seeing A. I.-limbs being commonplace but it’s a time to look forward to.
Given how A. I.-powered prostheses, with their abilities to be upgraded both on the hardware and software fronts, hold the potential to be superior to biological arms, we asked György Lévay if he thinks that such artificial limbs could be used in the future to augment the capacities of manual workers.
“I don’t believe we will ever see a time when people replace their biological limbs with mechanical ones,” he replied. “Primarily because our brain’s plasticity can support up to eight additional limbs; so why cut off anything if you can just add? Also, by the time we reach the point of scientific and technological advancement where it might be worth replacing a healthy limb (which is very far off), we would have to have the ability to augment that biological limb with exoskeletons or implants. However, by that time if we still have manual labourers that will mean humanity is in big trouble.”
Dr. Bertalan Mesko, PhD is The Medical Futurist and Director of The Medical Futurist Institute analyzing how science fiction technologies can become reality in medicine and healthcare. As a geek physician with a PhD in genomics, he is a keynote speaker and an Amazon Top 100 author.
Get access to exclusive content and analyses about the future of digital health on Patreon.com!