December 06, 2010
We’re going to step outside of high-performance computing applications in the cloud for a moment to take a look at how big data is forcing a particular industry to look beyond on-site computing and storage resources. No matter what the applications look like, this is becoming one of the first reasons why some industries are looking to cloud computing—not simply for on-demand cycles, but because the infrastructure challenges are too great to contend with without such an option.
For those in the field of medical imaging, mandated restrictions on data retention longevity, accessibility and backup of the massive amounts of data they collect create some serious big data problems. With an explosion in data—and no end in sight on that front—cloud computing and storage become the final frontier.
This marks an important use case since the requirements for storage, access and compliance meld together to paint a complicated picture of how clouds are necessitated and managed in the scope of such demands.
Federal and state laws can mandate that any imaging facility or hospital system must keep imaging results for the lifespan of a patient plus an additional five years. What this means is that smaller hospitals or facilities are being forced to store vast amounts of data that increases far faster than it is purged—a fact that is complicating costs and accessibility for any number of institutions or imaging outlets.
According to the Huntzinger Management Group, “As more medical specialties jump on board with Picture Archiving and Communication Systems (PACS), such as ophthalmology, pathology and internal medicine, new systems will expand to accommodate unique department needs, and data requirements will escalate even further”
The group goes on to note, “It is not uncommon for medical centers to have more than 500 TB of data to manage, and in the majority of cases, hospitals retain medical records for perpetuity. The rationale being that legal storage requirements for various components of the medical record (such as clinical lab data or radiology images vary considerably), thus making it easier for hospitals to store all of their data forever rather than researching and complying with the individual patchwork of storage requirements”
Patrick Boyle from IBM stated, “We are hearing from CIOs, radiologists and others familiar with the business that the cost and complexity of storage management of medical images has been exploding over the past several years. It has reached a point that our customers are finding it enormously difficult not only to manage the exposure from a clinical standpoint on the exploding volumes of data.”
Due to the high costs of storing massive amounts of data, all of which needs to be available in a manner that is available for instant access, the on-demand solution seems like an ideal fit. Managing the infrastructure required to house such volumes is no reasonable, in other words.
“Because of the way the data is used in the clinical setting, it’s one thing to store it, it’s another thing to make sure it’s backed up, that it safely secured from the outside world. That the data will be stored for multiple years becomes a big people management issue of how do you take care of all that data and make sure that it’s safe and available over a long period of time.”
The needs of medical institutions are going far beyond general storage of the massive datasets they need to keep on hand, often permanently as they are granted new opportunities to work with digital patient data.
Due to innovations in applications on multiple devices as well as more streamlined healthcare IT processes, this data can be accessed via the cloud instantly (versus old systems, including paper document and CD-archived materials) and made use of to analyze information and deliver more robust patient information that can be dynamically updated.
As more healthcare facilities see the cloud as an opportunity for relieving some of their data burdens, so too are some seeing the cloud as offering an ideal platform for collaboration and exchange.
As Garry Choy of General Hospital in Boston said during a recent interview, “Numerous vendors are releasing cloud-based solutions to enable on-demand access of imaging data from anywhere, such as teleradiology setups and mobile applications for smartphone access.”
Choy’s hospital, like other larger institutions across the United States are looking at refining their old system of sharing images via CD (often mailed) through cloud-based collaboration platforms.
Here’s another point that puts the benefits of cloud computing with big datasets in context—dealing with complex technology is not what radiologists do outside of their own equipment and domain-specific daily activities. Asking them to relearn complicated input and access systems can cause delays and problems, however refining this process via a simple user interface that acts as a gateway to cloud-stored information creates a more streamlined process.
Furthermore, some of the complexity that is removed creates the possibility for medical imaging specialists to access and do some of their work outside of the clinical setting—a major benefit for those who are on-call and require access to patient data immediately.
As “Today most radiologists can only access JPEG image files from home, but cloud computing can turn a home PC into a PACS. This is important not only because it enables radiologists to provide better service when working outside the hospital, but also because the time is coming when radiologists will commonly be remote employees and can work where they like.”
The Security and Compliance Questions
Electronic medical records have already gone to the cloud in many larger institutions, but of course, this begs the question—is patient data, despite the lengthy HIPPA and other compliance and security measures required, really going to be safe in the cloud? If so, how will the regulatory environment keep pace with the changes in technology?
As DICOM Grid, provider of a cloud-based platform for medical imaging use noted in a recent release, “Currently, imaging studies are stored in expensive proprietary silos and the most common form of data sharing is to hand-deliver or mail CSs, which can create security breaches.”
While there are countless security-inspired discussions that need to take place before we start thinking about home access to sensitive patient data, there is nonetheless the possibility (eventually, anyway) for a revolution in where and how healthcare operates—at least certain aspects of it. If the process can be refined to improve patient health, clinical access and action, and at the same create a more sustainable working paradigm we are, indeed, in new, better times ahead.
For now, the field of medical imaging is demonstrating one of the more practical use cases of cloud computing for large datasets, simply by showing that when the data gets to be too much to handle, if the cloud's the only option, then vendors and regulators alike will work with healthcare institutions to bring something to market that is viable, secure and compliant.
Without such solutions (and more are needed, especially those with an emphasis on interoperability) hospitals will end up extending precious resources just to keep up with ever-growing data versus focusing on their core goal of delivering sound healthcare.
May 16, 2013 |
When it comes to cloud, long distances mean unacceptably high latencies. Researchers from the University of Bonn in Germany examined those latency issues of doing CFD modeling in the cloud by utilizing a common CFD and its utilization in HPC instance types including both CPU and GPU cores of Amazon EC2.
May 10, 2013 |
Australian visual effects company, Animal Logic, is considering a move to the public cloud.
May 10, 2013 |
Program provides cash awards up to $10,000 for the best open-source end-user applications deployed on 100G network.
May 08, 2013 |
For engineers looking to leverage high-performance computing, the accessibility of a cloud-based approach is a powerful draw, but there are costs that may not be readily apparent.
05/10/2013 | Cleversafe, Cray, DDN, NetApp, & Panasas | From Wall Street to Hollywood, drug discovery to homeland security, companies and organizations of all sizes and stripes are coming face to face with the challenges – and opportunities – afforded by Big Data. Before anyone can utilize these extraordinary data repositories, however, they must first harness and manage their data stores, and do so utilizing technologies that underscore affordability, security, and scalability.
04/02/2012 | AMD | Developers today are just beginning to explore the potential of heterogeneous computing, but the potential for this new paradigm is huge. This brief article reviews how the technology might impact a range of application development areas, including client experiences and cloud-based data management. As platforms like OpenCL continue to evolve, the benefits of heterogeneous computing will become even more accessible. Use this quick article to jump-start your own thinking on heterogeneous computing.