How sensors, ambient intelligence could revolutionize healthcare

Networks of radio-connected, intelligent sensors will propel the healthcare industry forward as increasing numbers of patients need care, researchers say. Two academic institutions recently shared details about how IoT-based technology might help mitigate clinical errors and improve caregiving in hospitals – an environment that’s under increased strain due to coronavirus cases – as well as at home.

The School of Engineering at Stanford University is exploring how a combination of electronic sensors and artificial intelligence could be installed in hospital rooms and elder care homes to help medical professionals monitor and treat patients more effectively.

“We are in a foot race with the complexity of bedside care,” said Arnold Milstein, a professor of medicine and director of Stanford’s Clinical Excellence Research Center (CERC), in an article posted on the school’s website. “By one recent count, clinicians in a hospital’s neonatal intensive care unit took 600 bedside actions, per patient, per day. Without technology assistance, perfect execution of this volume of complex actions is well beyond what is reasonable to expect of even the most conscientious clinical teams.”

Outfitted with sensors and AI technology, physical spaces can be designed to be reactive and empathetic to humans, according to Milstein, computer science professor Fei-Fei Li, and graduate student Albert Haque. “Passive, contactless sensors embedded in the environment can form an ambient intelligence that is aware of people’s movements and adapt to their continuing health needs,” the researchers wrote in an article in Nature.

Their research suggests a blend of low-cost active infrared and passive detectors that could be incorporated into the patient environment. For example, a hospital room might be outfitted with cameras for recognizing people and objects; Lidar depth sensors for measuring distance to objects; thermal sensors for night vision; radar and Wi-Fi for detecting motion and objects; and microphones for speech recognition and event awareness.

Potential use cases, according to Stanford Engineering, include computer-assisted monitoring of patient mobilization in intensive care units; tracking hospital-acquired infections; and automating surgical tool counts to prevent objects from being accidentally left in a patient.

Wireless radio monitoring

Researchers at Massachusetts Institute of Technology are working on a project that proposes using radio signals to observe people at home and chronical their everyday life, with one goal being to allow elderly people to age in place.

The use of radio signals instead of cameras or human observers is to allow for greater privacy. “… most people would have privacy concerns about deploying cameras at home, particularly in the bedroom and bathroom,” the researchers wrote in a paper published on the MIT CSAIL website. In addition, cameras don’t function well in the dark, and multiple cameras would be required to view different rooms in a home.

The MIT system, called RF-Diary, is designed to generate a transcript of a person’s life: The person is sleeping in the bed, and then gets up… and so on.

“In designing RF-Diary, we exploit the ability of radio signals to capture people’s 3D dynamics, and use the floormap to help the model learn people’s interactions with objects,” the team writes. Tracking and analyzing a person’s movements can be used to alert medical staff if a person skips their medications, for example, or falls.

The MIT paper, titled “In-Home Daily-Life Captioning Using Radio Signals,” is authored by Lijie Fan, Tianhong Li, Yuan Yuan, and Dina Katabi.