Intel Helps Power Edge Analytics in Healthcare

Discover how intelligence everywhere is providing the tools to help health IT make strides.

With the help of Intel® technologies, healthcare providers can use edge computing and analytics to convert data into new insights to help improve patient outcomes while delivering financial and operational value.

Edge Computing Drives Healthcare Advances

Modern health systems, hospitals, and providers are deploying new tools and building exciting new care models to better serve patients. These strategies focus on clinical decision support (CDS), helping provide clinicians with timely, filtered, and patient-specific information they can use to enhance care.

Over the last few years, this pursuit has seen a growing number of medical devices introduced to healthcare environments. These range from tablets and wearables to health monitors and artificial intelligence (AI)-powered imaging systems.

Wearables can give clinicians a timely status of key patient vitals such as heart rate and blood pressure, alerting medical staff to issues before they become problems. Health monitors can aid remote care by collecting patient data and triggering actions based on the results—for example, monitoring blood glucose levels and sending that information to a companion device such as an insulin pump to dispense the insulin. AI-powered imaging models can detect potential concerns in X-rays, prioritizing those images for radiologist or physician review.

The potential of these emerging innovations is profound, leading to better clinician workflows, lower costs, and improved patient care. But these edge devices have something else in common: they all generate data.

As a result, healthcare systems and providers must decide how to manage and make the best use of these unprecedented volumes of data. With bandwidth expense, access, and privacy in mind, what data should be sent to the cloud and what data is better managed locally?

Edge computing brings data processing, analytics, and storage closer to the source of data generation—for example, an on-premise server at a hospital or a mobile device at a patient’s home. Edge computing works as a complement to the cloud, allowing IT decision-makers to choose where to best place workloads along the compute spectrum. This strategy can help health systems optimize the collection, storage, and analysis of data—which, for the average hospital, has reached 50 petabytes each year.1

Combining Cloud and Edge Computing

In recent years, health systems and providers largely relied on the cloud for storing, analyzing, and processing data. With help from Intel, the health and life sciences industry is now forging a new data management strategy that strategically employs the cloud or edge computing based on needs, costs, and benefits. For example, it might make sense to limit the transmission of readings from patient wearables to the cloud, sending only summary totals reported at a prescribed interval.

Conversely, for systems that capture larger operational or financial data, the cloud will likely remain the preferred path as a means for forecasting organization-wide costs, purchasing and billing schedules, and supply-chain demands.

In addition, keeping personal or sensitive data on premise enables health systems and providers to comply with strict data handling and privacy requirements. This includes those outlined in the Health Insurance Portability and Accountability Act of 1996 (HIPAA). HIPAA now also includes the Federal privacy protections for individually identifiable health information as mandated by Congress in response to proliferating digital technology.

Intel® Technologies for Edge Computing

With a comprehensive suite of products and technologies, Intel powers edge computing, edge AI, and connectivity from edge to cloud to better capture, analyze, and synthesize health data. Through a broad portfolio of hardware and software building blocks and tools, Intel helps simplify the process of getting the right intelligence where it is most needed.

Intel® QuickAssist Technology (Intel® QAT) is one technology that boosts performance on either edge or cloud servers. Developed to accelerate compute-intensive operations, Intel QAT2 enables compression and decompression of medical imagery, including MRIs and CT scans, as well as video, such as footage from surgery.

Intel® Virtualization Technology (Intel® VT) represents a portfolio of technologies that make virtualization practical by eliminating performance overheads and helping improve security. With Intel® Virtualization Technology (Intel® VT), multiple applications can run on one server. As a result, health systems and providers can more effectively prioritize critical traffic, reduce the burden on IT, and help lower costs.

By enabling analytics and AI from edge to cloud, Intel furthers the healthcare industry’s pursuit of superior CDS, faster diagnoses, and improved patient monitoring and recovery.

Clinical Edge Computing Applications

Intel brings a broad ecosystem of industry partners and collaborators to the pursuit of edge computing solutions in healthcare. Intel is working with partners on solutions that support multiple edge devices, applications, and services on a single common platform that works with existing cloud and data center resources.

In two recent examples, Intel collaborated with partners to employ edge computing and edge analytics to bring new clinical value to providers.

Use of the Intel® Distribution of OpenVINO™ toolkit resulted in improved algorithm performance, helping GE Healthcare accelerate pneumothorax detection on the Optima XR240amx X-ray system by more than 3x.2

AI-Enabled Imaging

GE Healthcare turned to Intel for support in the development of its Critical Care Suite, a set of AI algorithms built to detect critical findings on a chest X-ray, including a life-threatening lung condition called pneumothorax. Intel helped optimize the Critical Care Suite algorithms using the Intel® Distribution of OpenVINO™ toolkit.

The toolkit provided computer vision and deep learning inference tools, including convolutional image-based classification models optimized for the Intel® processors used in GE Healthcare imaging systems. Use of the toolkit and AI helped medical staff identify and triage images that show a likelihood of pneumothorax, equipping radiologists to better prioritize viewing.

By improving the algorithm performance, Intel helped GE Healthcare accelerate pneumothorax detection on the Optima XR240amx X-ray system by more than 3x.3

Remote Care

Intel worked with HARMAN to advance another promising area in healthcare: reliable remote care. The companies developed a remote patient monitoring solution that enables access to health data by connecting a wide array of medical and non-medical devices.

The HARMAN Remote Care Platform (RCP), which uses an Intel® architecture-based gateway, builds on Intel’s cutting edge platform for remote patient monitoring. Applications include patient care services, chronic disease management, and patient health programs. The platform is also designed to help enable continuous care for patients and elderly at home while helping minimize costs.

The benefits from edge computing-based remote care could be significant. A 2015 study found a 50 percent reduction in 30-day readmissions and up to a 19 percent decrease in 180-day readmission among patients who received remote care.4 The bottom line stands to benefit as well with estimates suggesting that telemedicine alone could help cut U.S. employer healthcare costs by as much as $6 billion annually.5

Edge Analytics in Healthcare Powers Improved Patient Outcomes

It is a new world for health systems and providers, one driven and enabled by a proliferation of exciting new mobile and point-of-care devices. Intel is uniquely positioned to help them harness the power of these edge devices, as well as the provider’s existing cloud strategy, to enhance CDS and care.

Through industry knowledge, technology, and a broad ecosystem, Intel equips providers to extract actionable value from their data. McKinsey estimates current healthcare data could help lead to more than $300 billion annually in reduced costs alone.6 Edge computing and edge analytics will only grow in their impact as they bring new opportunities to grow operational, clinical, and financial value across the care continuum.

We’re Here to Help


Ready to talk with Intel about your next technology project needs?

Related Content

Find more resources on edge analytics in healthcare and the Intel® technologies that help power them.

AI Transforms X-Ray Imaging

GE Healthcare’s Critical Care Suite embeds AI on the X-ray device to help detect life-threatening conditions in seconds.

Read the story

Predictive Analytics for Healthcare

Explore how predictive analytics is helping health systems and providers improve patient care and help reduce costs.

Discover how

Accelerating Advancements in Precision Medicine

See how providers are using precision medicine to improve patient care and outcomes.

Read more

Creating the Future of Healthcare

See how innovations like AI and VR are changing healthcare from cancer treatment to medical imaging.

Learn more

Notices and Disclaimers

Software and workloads used in performance tests may have been optimized for performance only on Intel® microprocessors.

Performance tests, such as SYSmark and MobileMark, are measured using specific computer systems, components, software, operations and functions. Any change to any of those factors may cause the results to vary. You should consult other information and performance tests to assist you in fully evaluating your contemplated purchases, including the performance of that product when combined with other products. For more complete information visit www.intel.com/benchmarks.

Performance results are based on testing as of the date in the configurations and may not reflect all publicly available security updates. See configuration disclosure for details. No product or component can be absolutely secure.

Product and Performance Information

1Bresnick, Jennifer. “Desire for Predictive Analytics Outpaces Hospital Investment,” Health IT Analytics, September 8, 2016: healthitanalytics.com/news/desire-for-predictive-analytics-outpaces-hospital-investment.
2

Intel® technologies' features and benefits depend on system configuration and may require enabled hardware, software or service activation. Performance varies depending on system configuration. No product or component can be absolutely secure. Check with your system manufacturer or retailer or learn more at https://www.intel.ca.

3System test configuration disclosure: Intel® Core™ i5-4590S CPU @ 3.00GHZ, x86_64, VT-x enabled, 16GB memory, OS: Linux magic x86_64 GNU/Linux, Ubuntu 16.04 inferencing service docker container. Testing done by GE Healthcare, September 2018. Test compares TensorFlow model total inferencing time of 3.092 seconds to the same model optimized by Intel® Distribution of OpenVINO™ toolkit optimized TF model resulting in a total inferencing time of 0.913 seconds
5“Current Telemedicine Technology Could Mean Big Savings,” MarketWatch, August 2014: https://www.marketwatch.com/press-release/current-telemedicine-technology-could-mean-big-savings-2014-08-11.
6“Using It or Losing It?: The Case for Data Scientists Inside Health Care,” NEJM Catalyst, May 4, 2017: catalyst.nejm.org/case-data-scientists-inside-health-care