There’s new research by ITMO University, Russia on the Implementation of Indoor Positioning Methods: Virtual Hospital Case. The paper describes how positioning can be used to discover typical pathways, queues and bottlenecks in healthcare scenarios. The researchers implemented and compared two ways to mitigate noise in Bluetooth beacon RSSI data.
The probabilistic and neural network methods both use past recorded data to compare with new data. This is known as fingerprinting. The neural network method is less complex when there’s need to scale to locating many objects. The researchers tested the methods at the outpatient department of the cardio medical unit of Almazov National Medical Research Centre.
Comparison of the methods showed they give approximately the same error of between 0.96m and 2.11m. However, the neural network-based approach significantly increased performance.
Due to the pandemic, hospitals and care facilities have been experiencing greater patient numbers leading to pressures to accelerate digital transformation to increase efficiency. At BeaconZone, these are the main reasons customers have been using locating systems:
To save time searching for equipment, particularly highly mobile equipment such as wheelchairs
To monitor the location and temperature of medicines
To monitor the location of hospital porters
To track the location of vulnerable patients
To audit the visiting of care givers to patients
However, there are many more areas suitable for increasing efficiency and safety:
Tracking expensive assets such as beds and medical devices
Tracking rental/borrowed equipment to ensure they are returned on time to avoid unintended costs
Staff distress SOS for increased safety
Hygiene management, for example, on hand washing stations
Inventory counts and stock checks
Analysis of workflows to detect choke points and streamline processes
Production of key metrics such as time being spent with patients, patient throughput and wait times
Time saved improving the above activities leads to more time being spent with patients and hence potentially saved lives.
Here are some considerations if you are comparing solutions:
Tag costs – Prefer commodity rather than proprietary hardware to reduce costs and allow 2nd sourcing to reduce future risk
Real time – Prefer systems that detect continuously over those that rely on error-prone manual scanning
Scalable – Prefer software systems that will scale financially, particularly in large hospitals
Ongoing costs – Prefer systems that have known future system costs – ideally with a one-off licence rather than varying subscription.
One final tip. It’s our experience that healthcare providers under-estimate the human element in attempting to implement new systems. There are often internal problems as to who will be responsible for a) purchasing, b) installing and c) running new systems. Work these out and agree up-front before embarking on these transformative changes so as to prevent your project becoming blocked.
Beacons were used to determine the location of participants in an observational Autism Spectrum Disorder (ASD) clinical trial designed to assess social behaviour. Beacons were placed by the participants or caregivers in separate rooms in the household and a smartwatch used to detect the beacons as the participant moved from room to room. A smartphone app was used to map each beacon with each room.
A key aspect of the study is that it was conducted with no participant training and without the supervision of a technical person.
The study also provides a comparison with prior work and a comparison of locating technologies:
The researchers provide some good practice guidelines for using beacons for indoor locating:
Set the beacons to have the same transmission power to allow the signals to be comparable
Beacons should be placed in an open area in each room that is close to the activity centre of the room to minimize interference
Beacons should ideally have line of sight and face toward the participant and not considerably higher than the receiving smartwatch
The study achieved an accuracy of 97.2% proving that beacons have the potential to provide deep insights into in-home behaviour. This provides more objective data than would be the case with commonly used questionnaire-based studies.
James Bayliss, a final year industrial design student at Loughborough University, has designed a smart mobility aid that uses beacons. It’s allows people with dementia to live safely in their own home for longer.
The system, called ‘AIDE’, comprises of a walking stick that works with Bluetooth beacons situated around the home.
It tracks the person’s movement and uses machine learning software to detect behaviours and actions that are out of the ordinary. The system also provides reminders to the person to help re-orient them if they have a confused episode.
There’s recent research into using Bluetooth beacons to measure human gait speed. The ability to walk can be used as a core indicator of health in aging and disease. For example, it can enable early detection of cognitive diseases such as dementia or Alzheimer’s disease.
device: A four-character descriptor for the smartwatch that performed the scan.
timestamp: The time stamp at which the scan was received.
user: The id of the user that was performing the experiment.
direction: A number (0 or 1) indicating the direction of the walk.
walk_id: A number that identifies each walk.
speed: The actual speed of the user, in $m/s$.
It database contains RSSI measurements from different wearable devices and different BLE beacons, corresponding to 382 walks performed by 13 actors. The open source code used is available on GitHub.
Wake Up Radio (WUR) uses a very low power device that senses a radio signal to switch other devices, in this case a Bluetooth LE transmitter. A AS3930 WUR senses a signal in the range 110-150 kHz and switches a Texas Instruments Bluetooth CC2640R2 LaunchPad board.
The idea is that usually Bluetooth LE advertises every say 100ms to 1000ms and this is wasteful on battery power if the advertising is only needed for short periods of time. The paper assesses the feasibility of using WUR to turn advertising on and off to save battery power. While this is in in the context of wearables, the authors don’t mention much more regarding what might switch the beacons to advertise, other than:
The transmitter of this wake-up signal, which is usually a less restricted device, might be integrated with the communication infrastructure or deployed as an independent system element
The authors later mention healthcare so perhaps wearable beacons might only transmit when needed in particular areas.
It’s also mentioned that WUR can mitigate against the problem of interference when many Bluetooth devices advertise at the same time. This problem is rare and requires a very large number of devices. The authors later mention healthcare but this is unlikely to be a problem. A warehouse with thousands of assets might be a more realistic scenario. In this case, you could envisage wanting a Bluetooth beacon only transmitting when invited to do so.
The paper has some useful charts showing usual Bluetooth power use over time (without WUR):
You can see the periodic advertising which isn’t regular due to the 10ms long pseudo-random delay between advertisements. This is the part of the Bluetooth standard that helps ensure two device that collide usually don’t do so the next time they advertise. In between advertising, the power use a very low 0.3 µW.
The paper shows that energy consumption of the system as a function of the number of wake-ups in a period of time and the maximum application-level latency:
The paper concludes that the WUR approach can be more energy efficient when the desired latency for data delivery is below 2.11s. Even though the consumption of the WUR is low, it unfortunately exceeds the level of a BLE only system sleep mode by almost two orders of magnitude.
In our opinion the researchers are trying to improve on something that is already very low power. In between advertising, power use is extremely low. A CR2477 battery in a Bluetooth wearable can advertise periodically for up to 3 years. Also, for the wearable scenario, it’s more normal to use a low power accelerometer to only have the wearable transmit when moving. This way the battery lasts an extremely long time that’s limited more by the physical lifetime of the battery (5 to 10 years) rather than battery consumption.
A paper (pdf) explains how it uses a novel multi-hop system to track targets using mobile sensors. The multi-hop approach extends the sensing area and reduces the deployment cost.
The system uses a particle filter which analyses the temporal and spatial information of the targets to achieve 4.37m and 9.46m tracking error in a campus and a shopping mall respectively.
Bluetooth can be used as a way of connecting wearables and equipment to other devices. When equipment and people are Bluetooth-enabled, asset tracking and wayfinding become possible. Staff can quickly locate valuable hospital assets and patients in need for urgent care.
Another reason for using Bluetooth is reliability. The article mentions Bluetooth’s adaptive frequency hopping (AFH) that makes communication more reliable in noisy wireless environments. You can read more about the technical aspects in our post on Bluetooth LE on the Factory Floor.
A further reason for using Bluetooth, particularly Bluetooth LE, is low power. Stand-alone devices can work on coin-cell batteries for many years.
The final reason given for using Bluetooth is the ability to create larger site-wide networks using Bluetooth mesh. Mesh can be used for control, monitoring and automation systems without the need for WiFi that can be unreliable and congested in hospitals.
Midmark RTLS uses a combination of infra-red, 433Mhhz RF, WiFi and Bluetooth to provide tracking of healthcare assets, care givers and patients. It allows medical equipment to be located quickly, key things such as IV pumps to be effectively distributed (par levelling) and the location of care staff and patients to be controlled and monitored. The Bluetooth part of Midmark RTLS is used more for wayfinding using powered, static beacons to mark locations. Systems also allow for health workflow processes including self-rooming to reduce waiting and queuing for care.
Healthcare is increasingly being provided at outpatient rather than inpatient treatment. This is leading to more clinics and treatments centres and the need for technical sophistication to efficiently process patients.
No mention was given to other crucial healthcare usecases we have come across at BeaconZone such as tracking (and temperature) of valuable medicines, tracking porters, wheelchairs and wayfinding from the hospital limits to reception areas.
Russ Sharer, Vice-President of Global Marketing for Fulham, a manufacturer of energy-efficient lighting sub-systems has written an article in Health Estate Journal (pdf) on the use of iBeacons in healthcare.
Russ says it’s often difficult to find life saving equipment in hospitals and many organisations have to compensate by purchasing more equipment than they need. However, in use, equipment still gets misplaced, usually just at the critical time it is needed. He explains how the use of Bluetooth beacons and mesh can solve this problem. The article provides a great introduction to iBeacons and some issues such as the affect of frequency of transmission on battery life.
While the article mentions Bluetooth Mesh and iBeacons, these specific technologies don’t always have to be used. Gateways can be used instead of mesh to allow greater throughput of data. Also, any beacons, not just iBeacons, can be used as it’s usually the MAC address of the beacon that’s used for identification purposes. Using sensor beacons allows further scenarios, for example, monitoring the temperature of expensive medicines.
There are also many more scenarios for the use of beacons in healthcare than are mentioned in the article. Our beacons are being using to track hundreds of dementia patients. We have also been involved in a project to use beacons for navigation in large hospitals. Once there’s a network of beacons in a hospital, it’s possible to add lots of widely varying solutions.
