Can big data cure cancer?

Topics:

Tech Culture

Many companies are squeezing every last algorithmic drop out of big data to help them make more informed decisions, accessing and analyzing voluminous flows of structured and unstructured market data to guide the optimal allocation of resources. This same promise now beckons for medical research.

Sadly, many health care institutions are lagging in this regard, although many are trying to change the status quo. The same is true of the health care industry as a whole, which has yet to establish clear standards for sharing patient electronic medical records for research purposes. As Dr. Clifford Hudis, current president of the American Society of Clinical Oncology (ASCO) and chief of the Breast Cancer Medicine Service at Memorial Sloan-Kettering Cancer Center in New York City says, “Medicine is astonishingly archaic functionally.”

Hudis, who is also a professor of medicine at the Weill Medical College of Cornell University, notes that while medical science has advanced in the laboratory at a pace comparable to businesses using computers, medical interactions with patients — often still done by putting pen to paper — remains rooted in 19th century practices.

“As doctors, we write down our observations, but we have not pulled all these disparate data points together to make references, draw conclusions and make decisions,” he says. “Even with revolutionary electronic medical records, in many cases we’ve simply electronified the old systems. Medicine has yet to catch up with the business world and its use of big data.”

Nevertheless, Hudis cites progress being made on an institution-by-institution basis, which he eventually hopes will coalesce into greater industry-wide use of big data. “Two years ago, ASCO launched a project to see if doctors would volunteer data on their patients with breast cancer so we could gather and interpret it for research purposes,” he notes. “We had hoped for 30,000 medical records and got 176,000 within six months. Even though there are millions of Americans with breast cancer, this suggests enough of a body of doctors willing to provide what’s needed.”

A clear hope

Among the health care institutions aiming big data at cancer and other serious diseases is the University of Pittsburgh Medical Center. UPMC is two years into a five-year enterprise analytics effort and already sees big data’s potential to accelerate scientific discoveries and to make good on the promise of more personalized medicine.

With the foundational architecture of UPMC’s new enterprise data warehouse solidly in place, researchers have been able to electronically integrate the clinical and genomic information on 140 breast cancer patients. “One of the first questions we asked was, ’Is there a difference, a unique difference between pre-menopausal and post-menopausal breast cancer?’” says Adrian Lee, Ph.D., a renowned expert in the molecular and cellular biology of breast cancer, and director of the Women’s Cancer Research Center at the university’s Cancer Institute. “We are interested in this question from a research standpoint because we are moving toward personalized medicine, and personalized medicine is all about finding subgroups of patients who have a specific type of disease for which we could develop novel therapies.”

Getting (more) personal

By capturing data on a multitude of cancer patients and analyzing their tumors in depth through sequencing and other techniques, this information can help researchers characterize the various tumors. This, in turn, allows them to create more targeted therapies per characterized tumor. The overarching goal, Lee says, “is to accumulate data on as many cancer patients as possible, analyze and quantify this data and then share it internationally with collaborative groups.”

The greatest impediment to the research has been the sheer volume of data: billions of measurements and combinations of measurements on a disease-by-disease basis. “For this data to be predictive, we need to aggregate it all in a single place,” he explains. “This requires new computational algorithms and super computers.”

He is sanguine that both are soon forthcoming, noting remarkable technological advancements like social media, cloud computing and mobility in the past 10 years. “Medicine will soon see a fundamental transformation in how we practice,” he says. “Health care will become very personal. Rather than a particular drug for everyone to take for a particular disease, the drug itself will be particular — to you.”

Already, big data is proving to be of big value to medical research. With regard to the project involving the 140 patients who were previously treated for breast cancer, Lee says that UPMC researchers have discovered “intriguing molecular differences” in the makeup of pre-menopausal vs. post-menopausal breast cancer. “While understanding those differences will require more research, the findings eventually could provide a roadmap for developing targeted therapies. One should not assume that the therapies for pre-menopausal breast cancer are automatically the same for post-menopausal,” he says.

Through predictive analytics, he adds, “We can better understand these diseases and pre-emptively treat them, ultimately on a more personalized basis.”

Related Articles