Artificial Intelligence is Completely Transforming Modern Healthcare


AI in medicine is changing healthcare as we know it. The introduction of deep learning systems is only possible by powerful computing capabilities; capabilities that Nvidia has made possible with their graphic processors.


Artificial intelligence is slowly making its way into the realm of modern healthcare. Google’s DeepMind is revolutionizing eye care in the United Kingdom, and IBM’s Watson is tackling cancer diagnostics on par with human physicians. Both AI systems use deep learning, a concept loosely mirroring how our own brains work by having AI software analyze exorbitant amounts of data and uncover patterns — which is particularly applicable in diagnostics.As medical imaging technology continues to take advantage of every new deep learningbreakthrough, the challenge is that the computing technology on which it relies must evolve just as quickly. A company called Nvidia is leading that charge under the guidance of Kimberley Powell, who is confident that Nvidia’s processors are not only meeting the deep learning standards of medical imagining, but also pushing the industry forward as a whole.

Nvidia’s hardware has established its silent but prominent role in deep learning’s marriage with medicine. Powell believes projects like their specialized computers, such as the DGX-1 a powerful deep-learning product, will become increasingly more common in hospitals and medical research centers. Strong computing power, like what the DGX-1 can provide, stands to increase the reliability of the diagnostic process; something that, in turn, would significantly boost the standard of care in developing countries.


While AI won’t be replacing doctors anytime soon, it will provide physicians with tools to more efficiently — and reliably — assess patients. AI is already involved in mining medical data, diagnosing medical images, studying genomics-based data for personalized medicine, and improving the lives of the disabled.

Thanks to NVIDIA’s DGX-1, hospitals can efficiently compare a single patient’s tests and history with data from a vast population of other patients. Some medical research centers and startupsare automating the analysis of MRIs, CT scans, and X-rays to assist physicians in making a diagnosis. Others are utilizing deep learning to create genetic interpretation engines to identify cancer-causing mutations in patient genomes, bringing to life the concept of personalized medicine.

However, while AI will no doubt continue to revolutionize medicine for years to come, physicians often find themselves perplexed by how to incorporate the technology into their regular practice. Only once AI is accepted, and fully integrated, into medicine will we see the full potential for the technology in terms of lending itself to more efficient and accurate diagnostics — from routine checkups to more specialized fields.

IBM’s Watson: A Healthcare Tool With Potential

IBM announced this week that it has partnered with 14 major cancer centers in the United States to use Watsonfor the analysis of patient-specific genetic data to guide therapy.

Use of Watson in healthcare was one of the earliest applications envisioned after its famous “Jeopardy!” victory. And the pace of news about Watson in medicine has definitely picked up.

@Point of Care, which made the list of our Best New Apps of 2014, uses Watson to help answer patient questions about multiple sclerosis. And Pathway Genomics plans to deliver personalized health advice based on a patient’s genetic profile using Watson.

In a demonstration of its commitment, IBM recently launched a 2000-person Watson Health unit that will focus entirely on applications in medicine. At the same time, the company also announced a collaboration with Apple that will brings Watson’s analytic power together with the piles of data being collected through HealthKit.

In this latest partnership, IBM will collaborate with some academic heavyweights: Ann & Robert H Lurie Children’s Hospital of Chicago; BC Cancer Agency; City of Hope; Cleveland Clinic; Duke Cancer Institute; Fred & Pamela Buffett Cancer Center in Omaha, Neb.; McDonnell Genome Institute at Washington University in St. Louis; New York Genome Center; Sanford Health; University of Kansas Cancer Center; University of North Carolina Lineberger Cancer Center; University of Southern California Center for Applied Molecular Medicine; University of Washington Medical Center; and Yale Cancer Center.

Watson will be used to analyze genetic data being captured on cancer patients and compare that information to databases of known genes, medical literature, and more. Based on available reports, use here seems to be very much in pilot stages, looking for ways that Watson could help deliver scalable decision support in this context. As described by IBM, partners will use a new Watson Genomic Analytics platform:

Partners involved in the program will use Watson Genomic Analytics, a new solution specifically designed for genomic analysis. Watson Genomic Analytics is a cloud-based service for evidence gathering and analysis. It looks for variations in the full human genome and uses Watson’s cognitive capabilities to examine data sources such as treatment guidelines, research, clinical studies, journal articles and patient information. The solution then provides a list of medical literature that is relevant to the case, along with drugs that have been identified in the literature. The patient’s doctor then reviews this information alongside underlying evidence to make more informed treatment decisions. Watson Genomic Analytics constantly gets smarter as the system learns from patient data.

There’s clearly a lot of potential here. However, its also important to recognize that it’s still just “potential.” In a nice piece in the New York Times, Mayo Clinic physician Dr. Michael Joyner talks about how the promise of the Human Genome Project was, to some extent, stymied by the insights it gave us into the complexity of the most prevalent diseases.

That said, Watson is certainly a novel tool in medicine with an incredibly wide range of possible applications. These partnerships will help drive the thoughtful development and rigorous evaluation that will lead to Watson-based tools that can move use from novelty to improved outcomes for our patients.

IBM’s Watson to Guide Cancer Therapies at 14 Centers

‘Humans alone can’t do it,’ oncologist says.

Fourteen U.S. and Canadian cancer institutes will use International Business Machines Corp’s Watson computer system to choose therapies based on a tumor’s genetic fingerprints, the company said on Tuesday, the latest step toward bringing personalized cancer treatments to more patients.

Oncology is the first specialty where matching therapy to DNA has improved outcomes for some patients, inspiring the “precision medicine initiative” President Barack Obama announced in January.

But it can take weeks to identify drugs targeting cancer-causing mutations. Watson can do it in minutes and has in its database the findings of scientific papers and clinical trials on particular cancers and potential therapies.

Faced with such a data deluge, “the solution is going to be Watson or something like it,” said oncologist Norman Sharpless of the University of North Carolina Lineberger Cancer Center. “Humans alone can’t do it.”

It is unclear how many patients will be helped by such a “big data” approach, however. For one thing, in many common cancers old-line chemotherapy and radiation will remain the standard of care and genomic analysis may not make a difference.

Cloud-based Watson will be used at the centers – including Cleveland Clinic, Fred & Pamela Buffett Cancer Center in Omaha and Yale Cancer Center – by late 2015, said Steve Harvey, vice president of IBM Watson Health. The centers pay a subscription fee, which IBM did not disclose.

Oncologists will upload the DNA fingerprint of a patient’s tumor, which indicates which genes are mutated and possibly driving the malignancy. Watson, recognized broadly for beating two champions of the game show Jeopardy! in 2011, will sift through thousands of mutations and try to identify which is driving the tumor, and therefore what a drug must target.

Distinguishing driver mutations from others is a huge challenge. IBM spent more than a year developing a scoring system so Watson can do that, since targeting non-driver mutations would not help.

“Watson will look for actionable targets,” Harvey said, matching them to approved and experimental cancer drugs and even non-cancer drugs (if Watson decides the latter interfere with a biological pathway driving a malignancy).

But Watson has trouble identifying actionable targets in cancers with many mutations. Although genetic profiling is standard in melanoma and some lung cancers, where drugs such as Zelboraf (vemurafenib) from the Genentech unit of Roche Holding AG target the driver mutation, in most common tumors traditional chemotherapy and radiation remain the standard of care.

“When institutions do genetic sequencing, only about half the cases come back with something actionable,” Harvey said, often because it is impossible to identify the driver mutation or no targeted therapy exists.

IBM’s Watson to help fight cancer

IBM's Watson
Using Watson should speed up the treatment process for cancer patients

IBM supercomputer Watson is to help determine the best treatments for a common type of brain cancer.

Watson will analyse glioblastoma patients’ DNA and correlate the results with available relevant medical data.

New York Genome Center president Robert Darnell said tremendous progress had been made in understanding the genetic drivers of cancer in the past 10 years.

And the project would “improve outcomes for patients with deadly diseases by providing personalised treatment”.

IBM Research director John E Kelly said: “It’s like big data on steroids.

“Watson can do in seconds what would take people years. And we can get it down to a really personal level.

“This is the proverbial needle in the haystack and the haystack is enormous.”

Watson uses artificial intelligence to examine huge amounts of data and can also understand human language. Rather than being programmed to spot patterns it “learns” about connections between different types of data. It is hoped that it will continue to “learn” as it processes new patient information and new medical research.

Diagram A cancer mutation on a cell protein pathway from genome sequencing

IBM Global Technology and Analytics vice-president Stephen Harvey said: “What we’re really talking about is taking a process that takes three weeks to three months for research organisations to complete today and to boil that down, using Watson technology, in to less than three minutes.”

Watson is already being used by doctors and nurses at the Memorial Sloan-Kettering Cancer Center, in New York, to help make decisions about lung cancer treatment.

Watson has become smaller and faster over the years. What started as a system the size of an average bedroom is now the size of three stacked pizza boxes. It is also available via the cloud, meaning it can be accessed from anywhere.

It can process 500GB of information – equivalent to a million books – every second.

And it has proved its abilities. In 2011 it appeared on the Jeopardy game show answering general knowledge questions, without being connected to the internet.

Pitted against the two biggest winners of the trivia quiz show, despite a few stumbles it eventually walked away with the $1m (£605,000) prize.

%d bloggers like this: