Healthcare is about as touchy an industry as there is. The sensitivity of personal data; lines and lines of security and compliance rules; the scary high stakes of patients’ health and lives. Can artificial intelligence unravel the big ball of red tape and bring digital efficiency to hospitals, research centers, insurers, etc.?

“There are 1.2 billion medical documents that are generated every year in the U.S.,” said Dr. Vasi Philomin (pictured, right), general manager of machine learning and AI at Amazon Web Services Inc. These documents contain information that could help professionals diagnose and treat patients, launch clinical trials, and more — if they could parse it.

The sheer volume of documents is hard enough for humans to manage. Then there is the fact that lots of the data, such as clinical notes, is unstructured. In fact, 80 percent of those 1.2 billion documents are unstructured text, according to Philomin.

Last year, Amazon launched Comprehend, an analytics service for unstructured text. By user demand, it just released Amazon Comprehend Medical geared for the language in medical documents. “To make sense of that is going to enable our customers to do some really amazing things,” Philomin said.

Philomin and Dr. Taha Kass-Hout (pictured, left), senior leader of healthcare and AI at AWS, spoke with John Furrier (@furrier) and Dave Vellante (@dvellante), co-hosts of theCUBE, SiliconANGLE Media’s mobile livestreaming studio, during AWS re:Invent in Las Vegas. They discussed Amazon’s efforts to drive data analytics and AI into healthcare. (* Disclosure below.)

Racing to trial and tip-toeing around HIPAA

A search on ClinicalTrials.gov turns up more than 290,000 open clinical trials, according to Philomin. “We know that most of these clinical trials don’t end up meeting their recruiting goals, because it’s very hard to figure out which patients fit the clinical trial that you’re actually trying to perform,” he said.

Combing all the documents necessary to match them is too tedious without AI, according to Kass-Hout. “Patients often times have Harry Potter’s worth of clinical notes done on them,” he stated.

Amazon Comprehend Medical helps narrow the process of picking trial participants from months to seconds, he added.

ACM is “HIPAA eligible,” Philomin said. “It’s a stateless service. What that means is nothing gets stored. The data is not used to improve the models or anything like that. The only person that can actually see the data is the customer,” he said.

AWS hopes this will wind around some blocks HIPAA’s historically put before data analytics in healthcare, Philomin concluded.

Watch the complete video interview below, and be sure to check out more of SiliconANGLE’s and theCUBE’s coverage of AWS reInvent. (* Disclosure: Amazon Web Services Inc. sponsored this segment of theCUBE. Neither Amazon nor other sponsors have editorial control over content on theCUBE or SiliconANGLE.)

Photo: SiliconANGLE