Science & Enterprise subscription

Follow us on Twitter

  • A new book by David Warmflash, MD tells about interactions and experiences of humans with the moon, from legends an… https://t.co/GMGaQb5ipQ
    about 3 hours ago
  • New post on Science and Enterprise: Early Space Bio-Experiments Detailed in New Book https://t.co/MGKafYjKnw #Science #Business
    about 3 hours ago
  • A start-up enterprise is developing computer chips designed to run artificial intelligence, or A.I., applications b… https://t.co/eMjzRJFxIZ
    about 4 hours ago
  • New post on Science and Enterprise: A.I. Chip Start-Up Raises $23M in Early Funds https://t.co/3YOa0YPC0r #Science #Business
    about 4 hours ago
  • A new enterprise is starting-up to develop treatments that target cancer-causing proteins considered unreachable wi… https://t.co/g6t4Hg2kbR
    about 24 hours ago

Please share Science & Enterprise

UC San Francisco, Intel Partner on Health Analytics

Networked devices

(Gerd Altmann, Pixabay)

19 January 2017. Intel Corporation and University of California in San Francisco are developing a data analytics platform that harnesses artificial intelligence to help front-line clinicians make better decisions for their patients. Financial and intellectual property aspects of the agreement between Intel and UC-San Francisco were not disclosed.

The agreement aims to advance big data analytics for health care to overcome obstacles from medical data stored in complex and diverse data sets, managed on multiple incompatible platforms. In addition, the number, variety, and complexity of data sources are increasing, which include genomic sequencing and mobile devices with wearable sensors, adding further to the data integration challenge. These obstacles, say the parties, slow the process of integrating data into a usable forms for physicians, often making the information they need difficult to access.

Intel and UC-San Francisco say they plan to develop an “information commons” that integrates data sufficiently from these diverse sources to enable the use of artificial intelligence techniques, such as deep learning to gain greater insights. Deep learning is a form of machine learning that makes it possible for systems to discern underlying patterns in relationships, and build those relationships into knowledge bases applied to a number of disciplines.

While deep learning and artificial intelligence are advancing in other fields, such as driverless vehicles, their applications in health care are so far limited. Michael Blum, director of UC-San Francisco’s Center for Digital Health Innovation, notes in a university statement that that these techniques can be applied to critical medical tasks and issues such as analyzing images, predicting health risks, and preventing hospital readmissions.

“Deep learning environments are capable of rapidly analyzing and predicting patient trajectories utilizing vast amounts of multi-dimensional data,” says Blum. “By integrating deep learning capabilities into the care delivered to critically injured patients, providers will have access to real-time decision support that will enable timely decision making in an environment where seconds are the difference between life and death.”

UC-San Francisco and Intel plan to create algorithms adapting deep learning concepts applied to health care decisions. Those models will be written on advanced, but commercially-available technology platforms that support data collection and annotation, and algorithm development and testing. The university expects the platform will accommodate large data sets, and eventually support advancements such as neural network and other complex models simulating human organisms.

Intel aims to gain more insights into health care analytical requirements that can help the company better design technologies for this industry. In addition, the company expects to apply these deep learning algorithms to more complex analytical challenges in health care as well as other industries.

Read more:

*     *     *

Please share Science & Enterprise ...
error

Comments are closed.