The rise of contactless IoT technologies in healthcare
With the coronavirus crisis showing no signs of abating, health organizations the world are turning to technological solutions to minimize the opportunities for physical contact between healthcare providers and patients.
As in other realms, contactless technology has been proposed as an obvious solution for both achieving this aim and improving the quality of data collected
With many contactless rollouts in the healthcare setting either imminent or already ongoing, those overseeing technology deployments need to keep some considerations in mind to ensure successful adoption. Although the current need for the technology may be time-sensitive, for those championing the move to contactless, getting this rollout right is necessary to both ensure successful data collection and lay the groundwork for contactless’ use for years to come. Because, if experience teaches disaster planners anything, it’s that COVID-19 will not be the last major disruption.
Network considerations and security
One of the most pressing needs for those leading contactless projects in healthcare is to make sure sensitive patient data is kept well-secured and protected from hackers. For healthcare organizations that have to comply with formal data protection codes, like the (HIPAA), this requirement is particularly salient. Even for those that don’t, the leak of healthcare data may have damaging repercussions. Secondly, planners need to ensure the availability of a network to connect contactless IoT sensors to a central application.
When it comes to deploying contactless technologies, healthcare organizations have plenty of options these days. Both cellular and 0G networks are perfect for the healthcare IoT use-case. Sigfox enjoys an advantage in this respect. The network is optimized for the frequent throughput of small packets of information. Datapoints such as the opening of a door can be very useful to clinicians in the context of patient monitoring, and only require small messages to be sent one way.
Additionally, securing these feeds, like installing the equipment, should be relatively straightforward for implementation personnel. The process of correlating IoT data feeds with individual electronic medical records (EMRs), for instance, can be done in centralized systems at the application level, thereby avoiding the need to transmit personally identifiable information (PII) over IoT feeds at all — although appropriate systems to secure the transmission end-to-end should be put in place as a best practice regardless of the contents. Furthermore, the data transmitted is typically only useful within a specific application and may also be in a proprietary format. This makes it almost useless, in itself, to potential hackers — and thus not a lucrative target for interception.
In other instances, due to 0G’s growing coverage, low power communication networks can be used as backup or failover communications systems for Wi-Fi or cellular-predominant monitoring systems. This is an important advantage considering that communications redundancy is sometimes an operational requirement in the healthcare setting. Furthermore, even in environments which would present technical challenges for traditional network infrastructure (such as underground facilities), the ability of end-users to install their own base systems and infrastructures can make deploying the technology quickly feasible. In the UK, our 0G network covers 90% of the population, so additional base systems would not be necessary in most cases. In other words, the technicalities of achieving a contactless implementation, even a rushed one, do not typically pose a problem these days.
Another key consideration for implementation teams is identifying and defining appropriate use-cases for contactless technology that can be deployed quickly without the need to overcome cumbersome regulatory hurdles. For instance, while medical robotics is a relatively mature field and prototypes capable of autonomous decision-making are already coming to market, those that need to use robot technology in the short term would be better-advised to focus on simpler implementations. For instance, robots could be tasked with performing clerical duties.
Examples of these might include medicine distribution, cleaning tasks, and transporting biohazardous test samples to a laboratory. These so-called ‘service robots’ have been exploited widely in the elderly care industry in Japan where healthcare administrator robots free up human workers from having to conduct repetitive unskilled tasks. This, in turn, reduces the probability of human error and in many cases leads to better reporting.
Robots are not suitable for all healthcare environments and examples of contactless IoT applications that are growing in use amid the coronavirus pandemic include:
- Tracking Personal Protective Equipment (PPE). IoT sensors can be attached to critical PPE supplies to track their movement within a hospital system.
- Video consultations can be initiated after a GP has received an alert from a patient being monitored at home through IoT sensors.
- Monitoring vulnerable populations through periodic electronic ‘check-ins’
- Measuring environmental parameters to enable meta analyses assessing the impact of these parameters on COVID-19 patient outcomes
Benefits for patients and providers
Contactless technology can directly benefit both healthcare institutions, through helping safeguard the health of their staff, as well as that of “end users” (patients). An example of the former is SPICA Technologies’ ongoing rollout of an IoT-based system for monitoring legionella levels in the water supply through IoT-connected sensors. Legionella is a water-borne bacterium that causes legionellosis which can be fatal in about 10% of cases.
Benefits of contactless healthcare solutions for patients include:
- IoT-connected motion detector sensors to detect falls. Innovative startups, such as Vitalbase, are already using this technology in combination with AI algorithms to hasten the process of calling for help among those that are socially isolating or in quarantine. For example, Senioradom has been designed to automatically detect any potential behavioural anomalies due to a fall, a person feeling faint or a deteriorating mental condition such as Alzheimer’s.
- Bulk deployments of call for help buttons. These have been rolled out in Spanish hospitals to quickly call for assistance. Unlike conventional hospital paging systems, these do not need to be provisioned through wired networks. Here a 0G network technology is ideal for quick and widespread implementation in an environment such as a hastily constructed field hospital with quickly changing patient numbers.
Finally, before beginning a contactless implementation teams should map out timely data flows. In the healthcare setting, unlike many other IoT use-cases, the true network endpoints are often human beings. In the interest of minimizing opportunities for human-human interface, those planning contactless IoT deployments need to map out the data flow between the patient and the centralized application in exact detail.
Failure to do so can negate the whole rationale of the system. Some healthcare systems, for instance, used IoT-connected medical robots to collect swabs and tests from samples but neglect to consider how to get these to the testing laboratory. If a human still has to collect the biohazardous material, then exposure has not been avoided. In an ideal situation, contactless should mean contactless — with minimal possibility of transmission between healthcare workers and patients.
With the basic networking infrastructure now readily available and quickly deployable, a properly planned roll-out is all that is needed to push the frontier of healthcare into the contactless era.
Skin Analytics wins NHSX award for AI skin cancer tool
An artificial intelligence-driven tool that identifies skin cancers has received an award from NHSX, the NHS England and Department of Health and Social Care's initiative to bring technology into the UK's national health system.
NHSX has granted the Artificial Intelligence in Health and Care Award to DERM, an AI solution that can identify 11 types of skin lesion.
Developed by Skin Analytics, DERM analyses images of skin lesions using algorithms. Within primary care, Skin Analytics will be used as an additional tool to help doctors with their decision making.
In secondary care, it enables AI telehealth hubs to support dermatologists with triage, directing patients to the right next step. This will help speed up diagnosis, and patients with benign skin lesions can be identified earlier, redirecting them away from dermatology departments that are at full capacity due to the COVID-19 backlog.
Cancer Research has called the impact of the pandemic on cancer services "devastating", with a 42% drop in the number of people starting cancer treatment after screening.
DERM is already in use at University Hospitals Birmingham and Mid and South Essex Health & Care Partnership, where it has led to a significant reduction in unnecessary referrals to hospital.
Now NHSX have granted it the Phase 4 AI in Health and Care Award, making DERM available to clinicians across the country. Overall this award makes £140 million available over four years to accelerate the use of artificial intelligence technologies which meet the aims of the NHS Long Term Plan.
Dr Lucy Thomas, Consultant Dermatologist at Chelsea & Westminster Hospital, said: “Skin Analytics’ receipt of this award is great news for the NHS and dermatology departments. It will allow us to gather real-world data to demonstrate the benefits of AI on patient pathways and workforce challenges.
"Like many services, dermatology has severe backlogs due to the COVID-19 pandemic. This award couldn't have come at a better time to aid recovery and give us more time with the patients most in need of our help.”