Are You a Developer or Data Scientist?

Find optimized frameworks and libraries,1 take AI courses, and explore community projects built on Intel® platforms.

Visit the Intel® Developer Zone ›

Develop and test your AI workloads for free on the latest Intel® hardware with integrated, optimized frameworks, tools, and libraries.

Visit the Intel® DevCloud ›

Promoting Health for All with Artificial Intelligence

Technology can enrich the life of every person, especially when it has the potential to help prevent, treat, and cure disease. Intel is working with leaders in the ecosystem to revolutionize health and life sciences, whether it’s accelerating drug discovery to speed pharmaceutical development or improving healthcare access and affordability. The use of artificial intelligence (AI) in healthcare—including computer vision, machine learning, and deep learning—plays a critical role in this goal. Combined with a strong infrastructure for data management, AI can help researchers and health systems quickly gather insights from massive amounts of data that were previously inaccessible due to data silos.

How Is AI Being Used in Healthcare?

AI can make it possible for automated systems to evaluate medical images for anomalies, monitor patient vital signs at scale, and alert clinicians to intervene when needed. It helps improve operational and clinical workflows and integrate data from many different sources so that clinicians can make more-informed decisions. Researchers are tapping AI to assist in drug discovery, targeted therapeutics, and infectious disease management. Other examples of AI in healthcare and life sciences include lab automation, robotics, and AI-enabled telemedicine.

Benefits of AI in Healthcare

AI improves productivity by automating tasks and can help clinicians with fast, accurate diagnoses and treatment.2 Artificial intelligence in radiology can reduce the compute time needed to generate images. In population health, machine learning can help identify the likelihood of hospital readmission. AI in pharmaceuticals development can lead to the discovery of new drugs. AI can also make it possible to ingest data from multiple sources, like medical records and vital signs, and identify patterns that are difficult for humans to spot.

Intel AI in Healthcare and Life Sciences

Intel’s work in AI is helping health industry experts address some of the most pressing challenges today. These include:

  • Precision medicine – AI can make sense of unstructured and structured health data, such as genomics data sets, that are crucial to advancing precision medicine, an approach to care centered on the patient’s unique genome and health information.
  • Clinical systems – AI can help transform raw data into new insights that inform treatment plans at every stage of the patient’s journey. It can also support care-at-a-distance strategies, such as telehealth and robotics, applied across inpatient and outpatient environments.
  • Pharmaceutical processes – AI can play a major role in drug development, transforming compound discovery.
  • Medical imaging – AI can enhance medical image quality and assist clinicians in evaluating images quickly and accurately.

Intel offers a range of flexible, scalable, open hardware to fit every compute need, from low-power VPUs to high-performance CPUs. And software tools like the Intel® Distribution of OpenVINO™ toolkit remove the complexity of working with different hardware back ends, so you can write code once and deploy it everywhere.

Use Cases for AI in Healthcare and Life Sciences

Artificial intelligence in medicine, pharmaceutical research, and other areas of healthcare can help improve patient care as well as overall population health.² Today, deep learning and machine learning in healthcare are streamlining workloads for clinicians, informing personalized treatment plans, and enhancing patient experiences.

AI in Medical Imaging

From reducing the compute time needed to generate images from CT scans to performing real-time inference on endoscopic cameras, AI is streamlining workflows and enhancing care.

Explore AI in medical imaging

Precision Medicine

With precision medicine, clinicians use genomic analytics alongside other patient data to customize care and provide the right treatment for each individual.

Learn more about precision medicine

See Intel® Select Solutions for Genomic Analytics

Predictive Analytics

Predictive analytics can help health systems understand trends, anticipate when and where care will be needed, and improve their population health strategies.

Read about predictive analytics in healthcare

Lab Automation

Computer vision and other types of AI are enabling both speed and accuracy in lab automation.3 Patients can receive their diagnoses fast and new drugs can be tested quickly, leading to breakthroughs in pharmaceutical development.

Read about lab automation

AI-Enabled Robotics

In hospitals and care facilities, robots are assisting with surgery, streamlining supply delivery and disinfection, and helping providers give more direct attention to patients.

Explore robotics in healthcare

AI in Telemedicine

AI-enabled telemedicine can help clinicians provide timely care and improve outpatient monitoring. Examples include personalized reminders, condition checks based on monitoring data, and dynamic prompts during virtual visits.

Learn about telemedicine

GE Healthcare Accelerates MRI Imaging with AI

GE Healthcare’s Artificial Intelligence Prescription (AIRx) automates some of the manual steps involved in MRI scanning. It also provides a consistent scan alignment to help physicians monitor a patient over several months. Using software optimizations, including the Intel® Distribution of OpenVINO™ toolkit, GE Healthcare reduced the inference time of AIRx from 2.85 seconds to 0.659 seconds on an Intel® Xeon® processor-based platform without the additional cost of accelerators.4

Read the story ›

Customer Success Stories


Philips Healthcare Accelerates Algorithms for Magnetic Resonance Imaging (MRI)

Philips Healthcare uses the Intel® Distribution of OpenVINO™ toolkit and the Intel DevCloud for the Edge to speed compressed sensing workloads for their MRI scanners on Intel® Xeon® Scalable processors with the custom extensions feature of the toolkit.

Read the case study

TGen Applies High Performance Computing to Genetic Research

The next phase of personalized medicine will rely on AI to increase the speed and efficiency of genomic analytics. The Translational Genomics Research Institute (TGen) built a high performance computing (HPC) cluster optimized for life sciences and powered by Intel® Xeon® Scalable processors and Intel® Optane™ memory.

Read the customer story

GE Healthcare Helps Staff Triage Life-Threatening Cases

GE Healthcare embedded an AI algorithm on X-ray imaging devices to help flag critical cases and alert radiologists for immediate triage. The Intel® Distribution of OpenVINO™ toolkit improved algorithm performance, speeding the time to analyze an X-ray from more than three seconds to less than one second.1, 5

Read the customer story

Akara Prototypes AI-Powered Disinfection Robot

As a proof of concept, Akara developed an autonomous virus-killing robot prototype to disinfect contaminated surfaces in hospitals using UV light. The robot is powered by an Intel® Movidius™ Myriad™ X VPU to navigate around people. Akara’s goal is to help hospitals sanitize rooms and equipment, aiding in the fight against COVID-19.

Read the story

Cerner Patient Observer Centralizes Inpatient Monitoring

Frontline nursing staff often have many patients to tend to, all with varying needs. The Cerner Patient Observer allows a technician at a central station to monitor patients in multiple locations to help prevent falls. The solution features an Intel® RealSense™ camera for 3D depth sensing, even in the dark.

Learn more

Develop and Deploy AI Systems


Find documentation and real-world examples of how healthcare systems and researchers have adopted and integrated AI into their workflows.

Accelerating Innovation in the AI Ecosystem

Intel® AI: In Production

AI at the edge enables real-time use cases in healthcare and life sciences. Learn about how Intel’s partners and solutions for health and life sciences are making it possible through Intel® IoT RFP Ready Kits and Intel® IoT Market Ready Solutions.

Visit Intel® AI: In Production for Health and Life Sciences

Intel® AI Builders

Intel® AI Builders brings together independent software vendors (ISVs), system integrators, original equipment manufacturers (OEMs), and enterprise end users. Members gain access to technical enablement resources and comarketing opportunities to help drive edge-to-cloud AI adoption.

Visit Intel® AI Builders

Intel® IoT RFP Ready Kits

These RFP-ready bundles of hardware, software, and support help make it possible to develop innovative solutions in healthcare and life sciences. They have been tested in the field and are designed to grow with customer needs.

See Intel® IoT RFP Ready Kits

Intel® Select Solutions for AI

These workload-optimized solution configurations can be deployed in a range of healthcare and life sciences use cases, including genomics analytics.

View Intel® Select Solutions for AI

Intel® IoT Market Ready Solutions

Made possible by Intel’s partner ecosystem, these end-to-end IoT solutions are optimized for data-intensive workloads. Solutions are adaptable, vetted, and ready for implementation.

Learn about Intel® IoT Market Ready Solutions

Find AI Solutions for Healthcare and Life Sciences


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 dates shown in configurations and may not reflect all publicly available updates. See backup for configuration details. No product or component can be absolutely secure.

Intel® technologies may require enabled hardware, software, or service activation.

Intel does not control or audit third-party data. You should consult other sources to evaluate accuracy. Your costs and results may vary.

Información sobre productos y desempeño

1Intel® compilers may or may not optimize to the same degree for non-Intel microprocessors for optimizations that are not unique to Intel® microprocessors. These optimizations include SSE2, SSE3, and SSSE3 instruction sets and other optimizations. Intel does not guarantee the availability, functionality, or effectiveness of any optimization on microprocessors not manufactured by Intel. Microprocessor-dependent optimizations in this product are intended for use with Intel microprocessors. Certain optimizations not specific to Intel® microarchitecture are reserved for Intel microprocessors. Please refer to the applicable product user and reference guides for more information regarding the specific instruction sets covered by this notice.
2“The potential for artificial intelligence in healthcare,” June 2019, Future Healthcare Journal, ncbi.nlm.nih.gov/pmc/articles/PMC6616181/.
3

“Ventajas y limitaciones de la automatización total de laboratorio: visión general”, química clínica y medicina de laboratorio (CCLM), febrero de 2019, degruyter.com/view/periodishs/cclm/57/6/article-p802.xml.

4Configurations: Original model was trained using TensorFlow 1.6 for Python 2.7 without Intel® optimizations and converted by GE Healthcare to OpenVINO™ 2018 R4. Hardware and configurations used for testing: GE Gen6-P image compute node 3.10.0-862.el7.x86_64; processor: Intel® Xeon® processor E5-2680 v3; speed; 2.5 GHz; cores: 12 cores per socket, Docker container has access to 22 CPU cores; sockets: two; RAM: 96 GB (DDR4); hyperthreading: enabled; security updates: Spectre and Meltdown updates applied. Software used for testing: TensorFlow version: 1.6 without Intel® MKL-DNN optimizations; Gcc version: 2.8.5; Python version: 2.7; OpenVINO™ version: 2018 R4 (model server v0.2); OS: HeliOS 7.4 (Nitrogen).
5System test configuration disclosure: Intel® Core™ i5-4590S CPU @ 3.00 GHZ, x86_64, VT-x enabled, 16 GB 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 the Intel® Distribution of OpenVINO™ toolkit optimized TF model resulting in a total inferencing time of 0.913 seconds.