One of the most reliable measures of advancements in society is medical care. The better it is, the more successful a society tends to be as a whole.
Now, thanks to big data, we may be seeing advancements at a much faster rate than before.
Machine learning and medicine
Recently, a program was developed by researchers at the University of Arizona College of Medicine to collect patients’ data in order to create ‘personalised’ medication.
The technology, which has not been given a name, was created by collecting information such as DNA and RNA sequencing, proteomics, metabolomics and epigenetics from large data pools of people that have required medical treatment. The data was then split into groups according to the patients’ genetic makeup, and how well they responded to various medications.
By analysing this data, researchers were able to plot trends and generate an algorithm to predict how new patients will be affected by diseases – and how best to treat them, of course.
Developed by Associate Professor of Neurology Rui Chang and his colleague Eric Schadt, Dean for Precision Medicine at the Icahn School of Medicine, the innovative program has recently been licensed to INTelico Therapeutics, LLC: a startup company.
“With this technology, I’m excited to build an atlas of disease models to create a holistic way to “I am delighted to announce that I will be part of ChapmanBlack’s latest development, Scale.
With a focus on Embedded Systems, our mission is to create access to niche engineering talent for businesses who want to hire and grow their teams rapidly.
We will be placing permanent and interim candidates in companies across the globe, both in an individual capacity and as part of large projects with up to 250 hires.
Though I will now be working under the Scale name, I am still very much a part of ChapmanBlack and the SourceChain Group. Please get in touch to find out about how Scale can help engineer the future of your business.”
swipe through the disease data, and then, within each disease section, find the targets for that disease,” Dr. Chang said.
According to the University of Arizona, “With guidance from mentors-in-residence Mike Sember and Kevin McLaughlin, Chang gained valuable business advice through TLA’s I-Corps program, a six-week intensive course that teaches academic entrepreneurs about lean launch methodology and customer discovery.”
The I-Corps (Innovative Corps) was put in place specifically to aid people like Dr. Chang in their endeavours, and aims to take the impact of their research outside of the laboratory.
“Rui [Chang] has great energy and passion for his vision around harnessing computational power for improved drug application and patient care,” McLaughlin said. “It was a pleasure working with him and I wish him success.”
A work in progress
Though this is obviously a milestone in the journey towards implementing big data technology in mainstream medical care, plans to do so have been around for a long while now.
In March last year, Reuters reported that “Half of the world’s 1,800 clinical studies involving real-world or real-life data since 2006 have been started in the last three years, with a record 300 last year, according to a Reuters analysis of the U.S. National Institutes of Health’s clinicaltrials.gov website.”
More up to date figures have not been made available since then, but – given the trend – it’s likely that research based on ‘real life’ data sets has surged even further. This is partly due to the simple fact that data is more accessible than it used to be.
“It’s getting more expensive to do traditional clinical trial research, so the industry is looking at ways it can achieve similar goals using routinely collected data,” said Paul Taylor, a health informatics expert at University College London. “The thing that has made all this possible is the increasing digitisation of health records.
This ease of access has made way for developments that would not have been possible even a decade ago, and it might just catapult medical developments into a new era of enlightenment.
“Big data and machine learning can be essential in lowering the cost of drug discovery, moving the experiment from clinical researchers to a combination of AI, complex software, and powerful computers to minimize the time needed for clinical trials,” explains Inside Big Data. “This, in turn, would drastically decrease the amount of research necessary, lowering the costs significantly for manufacturers and, as a result, patients.”
Dr. Chang’s program is just one example of such developments.
Of course, there will be challenges ahead – namely “the need for standardization of data content, format, and clinical definitions, a heightened need for collaborative networks with sharing of both data and expertise and … a need to reconsider how and when analytic methodology is taught to medical researchers.”
What’s more, many have expressed concerns that new drugs mean new opportunities for pharmaceutical companies to slap a bigger price tag on products that haven’t actually been altered all that much.
Still, the potential benefits are incredible.
Medicine could not only become more effective, but also more accessible and adaptable. And the more data we have, the more accurate the process will become.