Patients key to making sense of medical data
As big data unfolds, health care analytics world remains fractured, siloed
By Brian Eastwood |
March 1, 2016
Robert Gentlemen, vice president of computational biology at genetics testing company 23andMe
From brain activity to muscle performance, the human body produces two terabytes worth of data in a given day. This data provides valuable insight into body and mind activity, said Ben Schlatka, vice president of corporate development and co-founder of
—but no physician today is willing or able to process that much information.
With so many companies trying to provide data analytics services to the health care industry, Schlatka and his fellow panelists spoke about how important it is for firms to build a viable business model.
Schlatka, whose business builds wearable chips that collect data from implantable medical devices, said MC10 is trying to use the growing amount of data produced by implantable devices to establish long-term relationships with individual patients.
Working with such disparate data sources presents challenges, however. Schlatka said many health care companies have built walls around their devices, applications, and data sets.
One solution to the data access problem could be to bypass the disparate enterprise information technology systems and go straight to the source of that data: patients themselves.
“Patients are the ones who hold the master key that can open a lot of doors,” said Kim.
For example, the company surveyed customers with the genetic marker P603R, which had been thought to be a link to colon or pancreatic cancer, and found that no one with that marker had either type of cancer, Gentleman said. That was a relief to those with that marker who thought they were bound to get colon or pancreatic cancer, he said.
At a basic level, 23andMe asked customers a single question—“Are you a morning person?”–and was able to tie the answer to a standard circadian rhythm gene, Gentleman said.
It’s not groundbreaking science, he said, but asking a simple question with a lot of hard data behind it can address a key element of medical research: "What are the simple questions we can ask that we can get reliable data on ... so we don't have to get blood or have a complicated experience?"