UPDATED 10:00 EDT / NOVEMBER 04 2016

BIG DATA

The curative power of patient stats: How data could reveal the cure for cancer

While hospitals have been capturing patient clinical data for many years, it’s only been recently that people started asking what would happen if, instead of destroying patient clinical information after a successful course of treatment, organizations research it and apply it to help future patients with similar medical issues. Given the huge amount of data, it would have been a daunting task not too long ago; however, with recent advances in technology that provide better data storage and research, it has become a much more feasible idea.

In fact, healthcare is one of the fastest-expanding IT markets, with companies investing in vertical solutions for the health sector, especially in the cloud. All of this big data-crunching is rapidly driving new medical innovations and treatments. Partners HealthCare, a Boston-based non-profit hospital and physicians network that includes Brigham and Women’s Hospital and Massachusetts General Hospital, two of the nation’s most prestigious teaching institutions, has taken on the task of retaining and researching this crucial data to provide better patient outcomes.

After an invigorating 10-mile bike ride to our Boston studio, Brent Richter, director of Enterprise Research at Partners Healthcare, spoke to theCUBE’s Dave Vellante (@dvellante) about Partners’ history in patient data, the IT infrastructure challenges of data capture and analysis, and the inspiring story of a very successful outcome for a patient.

Capturing crucial device data

About 10 years ago, Partners Healthcare started out with high-performance computing when they found it strategically important to support the research community across the hospitals. From there, other general services were built around storage, as well as more specific services for data maintenance and electronic data capture. As the organization built high-performance computing around genetics research, Partners Healthcare found a need to build a data science platform for investigators and clinical research groups to leverage analytics.

Vellante asked Richter if the data generated was coming primarily from Internet of Things devices.

“There are clinical devices, EEGS and EKGs that are developing a lot more sensitivity and capturing more breadth of data. We were seeing that explosion over the past 10 years, until today, where quite a lot of the instruments are imaging-based,” said Richter.

Monitoring data today is far more sensitive and contains more channels, as patient monitoring has moved from discrete to continuous, Richter explained. Even though that data was captured in the past, it was only saved for clinical use and was usually thrown away after 30 days. As the utility of that data became apparent and investigators wanted to leverage it for analytics and proof of concepts, they had a need to retain the data and research it further.

Data storage and accessibility to clinicians

Richter explained that in the past most digital patient data was stored in a clinical enterprise data warehouse, as well as a research patient data registry.

“What we were trying to capture was the data that was not in those data warehouses,” he said. Once the value of this capture data was realized, they needed to store it in a way that was much more accessible to researchers. Vellante asked for details about how that was done.

Richter explained that they based the IDEA (integrated data environment for analytics) platform within Partners on Dell/EMC technologies. It used to be called the Federation Business Data Lake, and now it is called Analytic Insights Module (AIM). The components consist of a large amount of disparate data, measured in petabytes; a virtual environment, based on VMware Inc.’s Vblock converged infrastructure; and then data science tools and data-based tools, such as MongoDB, Hadoop, Spark and Hortonworks. Once that is set up, setting up this data ingestion is providing a virtual machine (VM) to the emergency department and the data scientist or research group that is looking at this data.

Diffuse more data through the enterprise for better patient outcomes

The discussion moved to how exactly that data is being used to help patients.

The MGH Cancer Center has begun to sequence every tumor and patient that comes through its door. It is building up that data so it can understand what worked, in terms of treatment, for a cancer patient in the past and apply what had the best efficacy to a new cancer patient. Based on that genetic profile, based on the patient history and other diagnostic factors, it will be able to apply the best protocol for that cancer treatment.

In the past, for example, if a patient presented with lung cancer, a doctor would usually begin with a course of chemotherapy and radiation treatment, Richter explained. If that did not succeed, another course would be started; it was like this was for every patient. Now, before a course of treatment is begun, doctors look at the patient’s genetic profile to see if a specific drug worked or did not work in a former patient with a similar cancer presentation.

richter-graphic

Example of patient scans before and after treatment.

Richter offered the case of a cancer patient who presented with very far advanced small-cell carcinoma; it was metastatic throughout the patient’s entire body. After the researchers performed genetic sequencing, they realized that some of the tumor had the same genetic profile as a different type of tumor, one that reacts very well to a chemotherapy drug that is not usually prescribed for small-cell carcinoma. Based on this research, the doctors gave the new drug to the patient; two weeks after the patient began taking this drug, their cancer had shrunk to almost nothing.

“That shows you the power this data can provide,” said Richter, bringing a much more targeted, nuanced approach to cancer treatments.

Watch the full interview (30:00) below:

Photo by SiliconANGLE

Save


A message from John Furrier, co-founder of SiliconANGLE:

Your vote of support is important to us and it helps us keep the content FREE.

One click below supports our mission to provide free, deep, and relevant content.  

Join our community on YouTube

Join the community that includes more than 15,000 #CubeAlumni experts, including Amazon.com CEO Andy Jassy, Dell Technologies founder and CEO Michael Dell, Intel CEO Pat Gelsinger, and many more luminaries and experts.

“TheCUBE is an important partner to the industry. You guys really are a part of our events and we really appreciate you coming and I know people appreciate the content you create as well” – Andy Jassy

THANK YOU