A hospital in the US is testing a wireless sensor network that monitors patients’ vital signs even as they move about.
When the system at Barnes-Jewish Hospital in St Louis, Missouri, is fully operational, sensors will take blood oxygenation and heart-rate readings from at-risk patients once or twice a minute.
A base station will combine the sensor readings with data from the patients’ medical records and continually monitor them for signs of deterioration, automatically calling a nurse’s mobile phone if anything goes wrong.
The idea is to create a virtual intensive care unit (ICU) where the patients aren’t wired to beeping machines and instead are free to move about as they please, said the principal investigator of the trial, Dr Chenyang Lu of Washington University in St Louis.
Following an initial trial, a prototype network is undergoing a feasibility study at the hospital and the researchers are due to report on it in October.
The network is designed for a ’step-down’ hospital unit, which provides an intermediate level of care for patients who no longer require critical care but still need more than is available on the general medical units.
During the initial trial, consenting patients in the step-down unit wore a telemetry pouch around their necks and a pulse oximeter on a finger that measured heart rate and blood oxygenation.
The sensor nodes transmitted the oximeter data through relay nodes to a base station, where it was saved in a database and later examined to see if it could have been used to correctly identify patients whose condition was deteriorating.
Most patients exhibit changes in their vital signs hours before an adverse event, sometimes as much as six hours before. A wireless sensor network could monitor vital signs tens or hundreds of times more frequently than clinical staff.
A key challenge was ensuring the network never failed. The relay nodes were programmed as a self-organising mesh network, meaning that if one node dropped out, data packets took another path to the base.
The sensor and relay nodes both included a radio chip. The sensor nodes were battery powered and the relay nodes were energised by USB-to-power adapters plugged into electrical outlets.
To save power, a node turned on the radio only when it had a data packet to transmit and turned off the radio as soon as a relay node acknowledged receipt of the packet. The data was transmitted via the relay node that had the ’lowest-cost’ path to the base station.
The trial found that data was reliably received more than 99 per cent of the time but sensing reliability was much lower, at only 81 per cent. All three cases of clinical deterioration that happened during the trial were picked up by the sensors.
Failures could be caused by oximeters falling off, a patient wearing nail polish, which can block oximeter readings, or movement such as gesturing, which caused short bursts of failures.
To compensate for the common short bursts of failure, the scientists decided to take measurements at a rate higher than that specified by clinical needs. The system therefore raises an alarm if data fails to arrive for 10 or 15 minutes.