The alarm who cried wolf: Intel backs medical machine learning research
Academia is often a hotbed for the research that powers major industries, and that’s certainly been the case for the booming interest surrounding the Internet of Things (IoT). Insup Lee, the Cecilia Fitler Moore Professor in the Department of Computer and Information Science and Director of PRECISE Center at the University of Pennsylvania, has been granted a whopping $6 million to back efforts in the connected world.
The funding was granted by the National Science Foundation and Intel Corp. to support Lee’s work with regards to the “cyber-physical system” (CBS) of the Internet of Things.
The alarm who cried wolf
Lee and his team are currently working on Smart Alarm, a system to identify when medical device’s alarms are real or just glitches. Hospitals or healthcare facilities use a bevy of gadgets to monitor patients, including heart monitors, infusion pumps, ventilators and dialysis units, all of which have built in alarms to alert for potential dangers. The problem is false alarms and glitches, sending doctors and nurses incorrect alerts. This leads to “alarm fatigue,” which is when nurses and doctors ignore the alarm, thinking it’s not a real emergency. This is dangerous, as they could be ignoring a fatal health threat.
Lee is collaborating with Penn colleagues such as C. William Hanson III who is a professor in Anesthesiology and Critical Care, Sociology professor Ross Koppel, and John H. Chestnut Professor of Law Chris Yoo, to properly address the different technological, social and legal facets of the project.
The Smart Alarm project will utilize a method of machine learning able to dismiss faulty alarms to improve the accuracy of medical devices. The end goal of the project, aside from making medical devices more accurate, is to also enhance the security of these connected devices.
According to an abstract published in 2010, the Smart Alarm is “an architectural framework for the development of decision support modules for a variety of clinical applications.” From my understanding, a Smart Alarm is a device that will be able to analyze patient’s data such as vital signs and with the use of a learning algorithm, it will be able to discern when an alarm is real or not, by continuously monitoring whenever the alarm goes off and when it goes off.
Investing in connected health
There seems to be a growing trend of big tech companies investing in connected health. Huawei Technology Co. Ltd. is collaborating with the University Medical Centre Groningen (UMCG) in the Netherlands to develop an early warning device for infectious diseases in hospitals by utilizing information and communications technology (ICT).
Additionally, IBM’s recent acquisition of Merge Healthcare aims to create a database of images and health data from wearables, historical images, health records and other sources so the healthcare team can deliver a more personalized approach of care.
And earlier this year Google revealed that it is working on a wearable device that not only measures a patient’s vitals, but also allows the health team to deliver continuous care even after the patient goes home.
photo credit: Alarm via photopin (license)
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.
THANK YOU