Is the Future of Healthcare Machine Learning Tools | Technology
|Is the Future of Healthcare Machine Learning Tools?|
Are Machine Learning Tools the Future of HealthCare?
Complex artificial intelligence programs promise to revolutionize medicine.
Terms like "machine learning," "artificial intelligence," and "deep learning" have become scientific buzzwords in recent years. But can these technologies be applied to save lives?
The answer to that is a resounding yes. Future developments in the health sciences may indeed depend on the integration of rapidly growing computing technologies and methods into medical practice.
Cosmos spoke with researchers from the University of Pittsburgh, Pennsylvania, USA, who have just published a paper in Radiology about using machine learning techniques to analyze large datasets of brain trauma patients.
Co-senior author Shandong Wu, an associate professor of radiology, is an authority on the use of machine learning in medicine. “Machine learning techniques have been around for several decades,” he explains. “But it was around 2012 that the so-called 'deep learning' technique matured. It attracted a lot of attention from the research field not only in medicine or health care, but also in other domains, such as autonomous cars and robotics.”
So what is deep learning? "It's kind of a multilayered neural network-based model that constantly mimics how the human brain works to process a large set of data to learn or distill information," Wu explains.
The key to the increased "maturity" of machine learning techniques in recent years is due to three interrelated developments, she says. These are the technical improvements in machine learning algorithms; developments in the hardware being used, such as improved graphics processing units; and the large volumes of readily available digitized data.
Machine learning techniques use data to "train" the model to perform better, and the more data, the better. "If you only have a small data set, then you don't have a very good model," Wu explains. "You may have very good questions or a good methodology, but you can't get a better model, because the model learns from a lot of data."
Although the medical data available is not as large as, say, social media data, there is still a lot to work with in the clinical setting.
Machine learning models and algorithms can inform clinical decision making, quickly analyzing massive amounts of data to identify patterns, says the paper's other co-senior author, David Okonkwo.
“Human beings can only process certain information. Machine learning enables orders of magnitude more information to be made available than an individual human being can process,” adds Okonkwo.
Okonkwo, a professor of neurological surgery, focuses on the care of patients with brain and spinal cord injuries, particularly those with traumatic brain injuries.
"Our goal is to save lives," says Okonkwo. “Machine learning technologies will complement human experience and wisdom to maximize decision-making for seriously injured patients.
“Although you don't see many examples today, this will change the way we practice medicine. We are very hopeful that machine learning and artificial intelligence will change the way we treat many medical conditions, from cancer to making pregnancy safer to solving COVID problems.”
But important safeguards must be put in place. Okonkwo explains that institutions such as the US Food and Drug Administration (FDA) must ensure that these new technologies are safe and effective before being used in real life or death scenarios.
Wu points out that the FDA has already approved about 150 tools based on artificial intelligence or machine learning. “Tools need to be further developed or evaluated or used with clinicians in clinical settings to really examine their benefit to patient care,” she says. “The tools are not there to replace your doctor, but to provide the tools and information to better inform doctors.”
Source: Cosmos Magazine, Direct News 99