Stanford Medicine, Google team up to harness power of data science for health care

Stanford Medicine will use the power, security and scale of Google Cloud Platform to support precision health and more efficient patient care.

- By Jennie Dusheck

Lloyd Minor, dean of the School of Medicine, says the collaboration with Google marks a "milestone for the future of patient care and research."    
Glenn Matsumura

Stanford Medicine and Google are working together to transform patient care and medical research through data science.

The new collaboration combines Stanford Medicine’s excellence in health-care research and clinical work with Google’s expertise in cloud technology and data science. Stanford’s forthcoming Clinical Genomics Service, which puts genomic sequencing into the hands of clinicians to help diagnose disease, will be built using Google Genomics, a service that applies the same technologies that power Google Search and Maps to securely store, process, explore and share genomic data sets.

Stanford Medicine includes the Stanford School of Medicine, Stanford Health Care and Stanford Children’s Health. Together, Stanford Medicine and Google will build cloud-based applications for exploring massive health-care data sets, a move that could transform patient care and medical research.

“Stanford Medicine and Google are committing to major investments in preventing and curing diseases that afflict ordinary people worldwide. We’re proud to be setting this milestone for the future of patient care and research,” said Lloyd Minor, MD, dean of the School of Medicine.

The agreement — considered key to Stanford Health Care’s development of the Clinical Genomics Service — makes Google Inc. a formal business associate of Stanford Medicine. As such, Google and Stanford will both comply with the Health Insurance Portability and Accountability Act, a federal law that regulates the privacy and security of medical information. HIPAA requires that Stanford Medicine patient data stored on Google Cloud Platform servers stay private. Patient information will be encrypted, both in transit and on servers, and kept on servers in the United States.

Cardiologist Euan Ashley says the new computing power will enable Stanford to make genetic testing a normal part of health care.    
Steve Fisch

Analyzing genetic data

With Google Genomics, Stanford Medicine will build its new Clinical Genomics Service on the Google Cloud Platform, expanding genomics research and establishing new methods of real-time data analysis for efficient patient care. “We are excited to support the creation of the Clinical Genomics Service by connecting our clinical care technologies with Google’s extraordinary capabilities for cloud data storage, analysis and interpretation, enabling Stanford to lead in the field of precision health,” said Pravene Nath, chief information officer for Stanford Health Care.

The Clinical Genomics Service will enable physicians at Stanford Health Care and Stanford Children’s Health to order genome sequencing for patients who have distinctive or unusual symptoms that might be caused by a wayward gene. The genomic data would then go to the Google Cloud Platform to join masses of aggregated and anonymous data from other Stanford patients. “As the new service launches,” said Euan Ashley, MRCP, DPhil, a Stanford associate professor of medicine and of genetics, “we’ll be doing hundreds and then thousands of genome sequences.”

The Clinical Genomics Service aims to make genetic testing a normal part of health care for patients. “Genetic testing is built into the whole system,” said Ashley. A physician who thinks a genome-sequencing test could help a patient can simply request sequencing along with other blood tests, he said. “The DNA gets sequenced and a large amount of data comes back,” he said. At that point, Stanford can use Google Cloud to analyze the data to decide which gene variants might be responsible for the patient’s health condition. Then a data curation team will work with the physician to narrow the possibilities, he said.

“This collaboration will enable Stanford to discover new ways to advance medicine to the benefit of Stanford patients and families,” said Ed Kopetsky, chief information officer at Lucile Packard Children’s Hospital Stanford and Stanford Children’s Health. “Together, Stanford Medicine and Google are making a major contribution and commitment in curing diseases that afflict children not just in our community, but throughout the world. It’s an extraordinary investment, and we’re proud to play such a large role in transforming patient care and research.”

Ashley noted that medicine mostly deals in small data, such as lab tests. But genomic studies, patient health records, medical images from MRI and CT scans, and wearable devices that monitor activity, gait or blood chemistry involve huge amounts of data that can allow doctors and researchers alike to analyze myriad aspects of patient health in ways that lead to improved medical decisions and products that are tailored to the patient — the essence of a precision health approach.

Focusing on precision health

“In the past few years, the amount of available data about health care has exploded,” said Minor. “While researchers are learning to integrate this big data, putting it to work for individual patients, in real time, is a huge challenge. Our collaboration with Google will help us to meet this challenge.”

This is the foundational work for bringing patient health information and other big data to the bedside.

Sam Schillace, vice president of engineering for industry solutions at Google Cloud Platform, said, “I’m excited because this agreement brings together expertise in three areas: data science, life science research and clinical care. The next decade of improvements in understanding and advancing health care is going to come from leaders in those three areas working together to build the next generation of platforms, tools and data.”

It’s all consistent with Stanford Medicine’s focus on precision health. “You could imagine that, going forward, potentially every patient could be sequenced,” said Michael Halaas, chief information officer for the School of Medicine. “The technology challenge we need to solve is how to derive useful insights from data and apply it directly to the care of a patient in near real time and also make progress on research.”

Halaas said the Stanford-Google agreement does more than provide Stanford with server space. “It’s not just stacks of servers,” he said. “It includes layers and layers of innovative technology. This agreement allows us to do the analytics in a way that is fast and secure.”

Minor said, “We’ll be working with Google to build innovative technology that will enable Stanford to lead in precision health, the goal of which is to anticipate and prevent disease in the healthy and precisely diagnose and treat disease in the ill.”

Data as the engine that drives research

Large-scale patient data is already helping answer research questions at Stanford. For example, Ami Bhatt, MD, PhD, an assistant professor of medicine and of genetics, is exploring changes in patient microbiomes that can precede symptoms of a disease such as cancer.

Another study is looking at alarm data from patient hospital rooms. The de-identified, or anonymized, data has been accumulating at Stanford’s adult and children’s hospitals for about 15 years, said Ashley, but until now no one has studied it. Hospitalized patients are typically hooked up to monitors that display their heart rate, blood-oxygen levels and other basic data, with alarms that go off if the measurements suggest something is wrong. The problem is that the alarms go off when nothing is wrong — sometimes when the patient just moves. Health-care providers often turn off the alarms so patients can rest and nurses can concentrate on people who need care. An artificial-intelligence approach in the works could use the alarm data to distinguish false alarms from real ones.

The analytics applications and virtual supercomputers available through Google Genomics could pave the way for other kinds of projects, as well. Working with Google’s engineers, Stanford researchers could make advances in visual learning that might, for example, enable computers to distinguish malignant tumors from benign ones in medical images.

The Stanford-Google collaboration is a critical step on the path to precision health, Minor said. “This is the foundational work for bringing patient health information and other big data to the bedside,” he said.

About Stanford Medicine

Stanford Medicine is an integrated academic health system comprising the Stanford School of Medicine and adult and pediatric health care delivery systems. Together, they harness the full potential of biomedicine through collaborative research, education and clinical care for patients. For more information, please visit med.stanford.edu.