AI-controlled sensors can improve patient outcomes in smart hospitals, Stanford says

Ambient intelligence refers to the interdisciplinary effort of creating smart hospital rooms and homes equipped with AI systems that can perform multiple functions to improve patient outcome.

It is important for hospitals to address legal, regulatory and privacy issues raised by increased use of automated healthcare processes.

Electronic sensors and artificial intelligence could help health professionals monitor and treat vulnerable patients in ways that improve the outcome without invading privacy, Stanford University said in a statement.

A team of researchers reviewed the field of 'ambient intelligence' in healthcare - an interdisciplinary effort to create smart hospital rooms equipped with AI systems that can do a range of things to improve patient outcomes.

AI tools can unobtrusively monitor impending health crises in the elderly. Devices could prompt in-home caregivers, remotely located clinicians and patients themselves to make timely, life-saving interventions.

Sensors and AI can immediately alert clinicians and patient visitors when they fail to sanitize their hands before entering a hospital room.

Ambient technologies have potential benefits, but can also raise legal, regulatory and privacy issues that need to be addressed to win the public's trust, the University read.

The field is based on the availability of infrared sensors, and the rise of machine learning systems as a way to use sensor input to train specialized AI applications in health care.

Infrared alert sensors are being tested to see if it can reduce the number of infections caused by other patients in hospitals when visitors fail to adhere to infection prevention protocols, Stanford said.

Another type of infrared technology are passive detectors that allow night vision goggles to create thermal images from the infrared rays generated by body heat. The 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.

Constant monitoring of ambient technologies systems in the home environment can help spot clues of serious or potential illnesses, especially in the elderly.

Researchers are developing activity recognition algorithms that can sift through infrared sensing data to detect changes in habitual behaviors, and help caregivers get a more holistic view of patient well-being.​