Researchers Look to Combine AI and IR Sensing to Save Lives

Facebook X LinkedIn Email
STANFORD, Calif., Sept. 16, 2020 — Researchers at Stanford University are looking at AI and infrared sensing to save lives in smart hospitals and at-home care, specifically in a study that looks at 170 scientific papers to gather information on the field of “ambient intelligence” as it relates to health care. The effort aims to create smart hospital rooms equipped with AI systems to improve patient safety and outcomes.

Ambient technologies have many health benefits, but they can raise legal and regulatory issues, as well as privacy concerns that must be identified and addressed to win the trust of patients, providers, agencies, and institutions that pay health care costs, said Fei-Fei Li, co-director of the Stanford Institute for Human-Centered Artificial Intelligence.

“Technology to protect the health of medically fragile populations is inherently human-centered,” Li said. “Researchers must listen to all the stakeholders in order to create systems that supplement and complement the efforts of nurses, doctors, and other caregivers, as well as patients themselves.”

Graduate student Albert Haque, who compiled the papers cited in the article, said that the field is largely based on the convergence of two technological trends: the availability of infrared sensors inexpensive enough to build into high-risk caregiving environments, and the rise of machine learning systems as a way to use sensor input to train specialized AI applications in health care.

The infrared technologies are of two types. First is active infrared, the same type used by TV remote controls. However, instead of beaming invisible light in one direction like a TV remote, new active infrared systems use AI to compute how long it takes the invisible rays to bounce back to the source, like a light-based form of radar that maps the 3D outlines of a person or object.

The second type of infrared technology is passive detectors, which are used in night vision googles to create thermal images from the infrared rays generated by heat. In a hospital setting, a thermal sensor above an ICU bed would enable the governing AI to detect twitching or writhing beneath the sheets and alert clinical team members to impending health crises without constantly going from room to room.

The researchers have so far avoided using high-definition video sensors, as capturing video imagery could unnecessarily intrude on the privacy of clinicians and patients.

“The silhouette images provided by infrared sensors may provide data that is sufficiently accurate to train AI algorithms for many clinically important applications,” Haque said.

Monitoring via ambient intelligence systems in a home environment could also be used to detect clues of serious illness or potential accidents, and alert caregivers to make timely, necessary interventions. Researchers are developing activity recognition algorithms that can sift through infrared sensing data to detect changes in habitual behaviors and help caregivers acquire a more holistic view of patient well-being.

The research was published in Nature (

Published: September 2020
Infrared (IR) refers to the region of the electromagnetic spectrum with wavelengths longer than those of visible light, but shorter than those of microwaves. The infrared spectrum spans wavelengths roughly between 700 nanometers (nm) and 1 millimeter (mm). It is divided into three main subcategories: Near-infrared (NIR): Wavelengths from approximately 700 nm to 1.4 micrometers (µm). Near-infrared light is often used in telecommunications, as well as in various imaging and sensing...
artificial intelligence
The ability of a machine to perform certain complex functions normally associated with human intelligence, such as judgment, pattern recognition, understanding, learning, planning, and problem solving.
machine learning
Machine learning (ML) is a subset of artificial intelligence (AI) that focuses on the development of algorithms and statistical models that enable computers to improve their performance on a specific task through experience or training. Instead of being explicitly programmed to perform a task, a machine learning system learns from data and examples. The primary goal of machine learning is to develop models that can generalize patterns from data and make predictions or decisions without being...
Research & TechnologyBiophotonicsmedical caremedicalhospitalsmart hospitalinfraredinfrared imagingartificial intelligenceAImachine learningactivepassiveSensors & Detectors

We use cookies to improve user experience and analyze our website traffic as stated in our Privacy Policy. By using this website, you agree to the use of cookies unless you have disabled them.