How AI is leading medical breakthroughs in antibiotics, cancer, and paralysis
While there is much understandable concern about the future of AI, there is also much to be excited about its current usage. One area of recent interest – and cause for much excitement – is medicine.
In the last few weeks alone, AI has been used to discover antibiotics for a superbug, demonstrated improved cancer detection, and helped a paralyzed man walk again.
Two weeks ago, a team of scientists from MIT and McMaster University used AI to find an antibiotic that can be used against A. baumannii, a bacteria said to cause ‘pneumonia, meningitis and infect wounds, all of which can lead to death.’
The bacteria is often found in hospitals, and it has been consistently resistant to antibiotics. Given its ability to find new ways to evolve, it’s been called a “superbug”.
While traditional research has been unsuccessful in finding an antibiotic. “Fortunately, machine learning methods allow for the rapid exploration of chemical space, increasing the probability of discovering new antibacterial molecules,” recent research states.
In this study, the scientists screened 7,500 molecules for those that prevented the growth of the bacteria, then trained a neural network with that data, and thereby discovered a new antibiotic.
After the WHO had listed antibiotics for this bacteria as a priority in 2017, this is a milestone success. The real excitement, however, is in antibiotic discovery more generally.
Jonathan Stokes, one of the scientists involved in the study, said, “AI methods afford us the opportunity to vastly increase the rate at which we discover new antibiotics, and we can do it at a reduced cost.” It's something, he says, that is "here to stay."
Published yesterday in the Radiology journal, a new study demonstrates that AI is more effective at predicting breast cancer in women than traditional prediction methods.
Vignesh A. Arasu, (M.D., Ph.D.), who led the study, says that:
“Recent advances in AI deep learning provide us with the ability to extract hundreds to thousands of additional mammographic features.”
The study was retrospective. Dr. Arasu used 2D mammograms showing no visible evidence of cancer from a study in 2016. Of the 324K women screened, a random 13K were selected, along with the 5K patients who were diagnosed with cancer in the following five years.
Using the original mammograms, five different AI algorithms were used to assign the patients a risk score, which was then compared to the traditional clinical risk score calculated by the Breast Cancer Surveillance Consortium (BCSC).
Because the study was retrospective, the study could deduce the accuracy of those predictions by comparing them with the reality of cancer development.
The study concludes that, “AI algorithms performed better than the BCSC risk model for predicting breast cancer risk at 0 to 5 years.”
A brain-spine interface (BSI) has been created to help a man – who has been paralyzed for twelve years – to begin to walk again.
The participant reports “that the BSI enables natural control over the movements of his legs to stand, walk, climb stairs and even traverse complex terrains.”
It’s a pretty incredible breakthrough.
The BSI works as a “digital bridge” between the brain and spinal cord, giving the individual control over his movements. Using bluetooth, signals from his brain can be picked up and used to make him move as he intended.
The role of AI is critical in this process.
Guillaume Charvet, head of the brain-computer interface (BCI) program at CEA, says:
“Thanks to algorithms based on adaptive artificial intelligence methods, movement intentions are decoded in real time from brain recordings.”
As the report states, the algorithm works to generate predictions - “the probability of the intention to move a specific joint", and "the amplitude and direction of the intended movement.” Through such prediction, the participant could walk, even if with the support of crutches.
Altogether, these very recent developments in AI are likely a small fragment of its capability to alleviate suffering, and improve quality of life. That is not to say that regulation is not necessary -- as the recent Whitehouse meeting showed us -- but to remind us of why we got excited about AI in the first place.
The HUMAN Protocol Foundation makes no representation, warranty, or undertaking, express or implied, as to the accuracy, reliability, completeness, or reasonableness of the information contained here. Any assumptions, opinions, and estimations expressed constitute the HUMAN Protocol Foundation’s judgment as of the time of publishing and are subject to change without notice. Any projection contained within the information presented here is based on a number of assumptions, and there can be no guarantee that any projected outcomes will be achieved.