Much has been written about the role artificial intelligence (AI) can play in the fight against the Covid-19 pandemic. While the practicality of new technology is still being explored, companies are earnestly working on AI-enabled tools that could support the measures being taken to curb the outbreak.
This includes tools to enforce social distancing, assess contact tracing, share valuable insights, as well as automated rapid tests, risk assessment apps, and resources to accelerate associated drug discovery initiatives, among others.
While the widespread adoption of these AI-enabled solutions for these applications could take time due to appropriate scepticism around it, there is no contesting the fact that it can expedite efforts to manage the ongoing Covid-19 crisis. But while caution should still be exercised when it comes to experimental technologies – especially during a health emergency like this – there are less-explored areas amid this crisis where technology can add a lot of value without the accompanied risk.
Rostering Medical Staff
Incorporating AI into the mundane – but critical – administrative functions in a hospital can relieve these institutes of unprecedented strain on resources, especially doctors, physicians, and other medical practitioners. Amid growing chaos in hospitals with more new cases emerging and existing patients demanding greater medical attention, AI may be able to create the biggest impact in this battleground in this pandemic.
In this scenario, one of the biggest challenges that health systems are facing is accurately scheduling and planning a medical staff rota. Challenging to manage even in normal times, relying on spreadsheets may not be enough during a crisis.
This is because with hospitals across the world having gone past the first wave of Covid-19-related hospital admissions, staff have been shifted off their usual tasks and deployed to critical care units and emergency departments. Donning and doffing layers of PPE, they have to support patients in the intensive care unit and attend to wards full of probable Covid-19 patients – all while their leaves are curtailed and shift hours extended.
Scheduling, in these circumstances, has undoubtedly become more complex.
What is more, large numbers of workers remain absent because they are ill themselves, or are self-isolating. Although medical students in a lot of places have been drafted early and retired doctors implored to return to service to help plug these gaps, calculating how best to deploy them alongside regular staff has been a herculean task.
How Can AI Help?
A company based out of Norway Globus.ai has created an AI-enabled system that is ideally suited to help in these situations by helping hospitals find the right skilled workers to fill shifts. It has gone into overdrive since the Covid-19 outbreak by allowing hospitals to match the competencies of medical practitioners to its needs, and align it with appropriate shifts based on availability.
It uses Natural Language Processing (NLP), deep learning and machine learning (ML) techniques to extract information, match the competencies of healthcare workers to specific tasks, and help fill available slots – making the planning of medical staff rota much easier and more efficient. What is more, its AI-powered staffing assistant also factors in policy and legal requirements when making these recommendations. For instance, it can account for cases where law mandates a set number of working hours, or the presence of a senior doctor for certain shifts.
According to the company, it has adapted the product to handle emergency staffing during Covid-19 and has been handling about 4,500 shifts per week. This has been saving hospitals “90% of the time it takes to fill each available slot”, making it more efficient to match staff to slots.
Although it is currently operational only in certain areas of Norway where it is providing public hospitals free access to its services amid Covid-19, the company has been working with Ernst & Young to roll it out on a larger scale to help hospitals and healthcare institutions across the world.
Other Ways In Which AI Can Help
Without promising the moon, AI can help healthcare providers in ways that can complement the above application. This includes introduction of tools that can estimate capacity for severely ill patients and strategies to circumvent it, and enabling hospitals to plan better in the event of a surge in cases. It should also factor in availability of beds, critical care doctors, and crucial equipment like ventilators, and the ratio of these inputs to patients.
In addition to these, tools to monitor and identify patients before their conditions deteriorate, and innovative ways to screen visitors should be integrated into clinical operations as well.
While some progress has been made in these areas through research based on data from certain communities and by reviewing literature on past outbreaks, there is a lot more that needs to be explored. What is more, most of these are still at its nascent stage and hence, unproven. It will, thus, take time to validate these technologies.