How natural language processing can help relieve the healthcare worker shortage

(Credit: Unsplash)

This article is brought to you thanks to the collaboration of The European Sting with the World Economic Forum.

Author: Tashfeen Suleman, CEO, CloudMedx


  • The WHO predicts a shortage of 18 million health workers by 2030.
  • A new survey shows the “biggest pain points” affecting these workers: increasing use of tech can add even more layers of documentation.
  • Healthcare workers want to spend more time caring directly for patients, and less on paperwork. Natural language processing (NLP) is a game changer. It can take over a lot of this work, freeing healthcare personnel to spend more time on direct care.

Across the world, fears are rising about a lack of nurses, doctors, and healthcare technicians in the coming years. The World Health Organization predicts a shortage of 18 million health workers by 2030.

There was already a shortage before the COVID-19 pandemic, but the last few years have exacerbated the problem. Experiencing burnout, exhaustion and mistreatment, many in the sector, especially nurses, have quit their jobs. But there are also other reasons for the shortage as well. For example, in the United States, many doctors are reaching retirement age just as the population of elderly people is expanding – meaning more people will need healthcare from fewer providers.

In addition to attracting young people to careers in medicine, other solutions are needed. One of these is to put new, emerging technologies to good use. But this is a very difficult challenge in healthcare. Unfortunately, the sector has a history of bringing in technologies that are meant to help but end up making things more complicated.

Tech as relief and burden

A new global survey of healthcare workers shows how concerned they are about this. A large majority (70%) say they believe digital health technology will enable positive transformation. But virtually the same number (69%) say these technologies will present a “challenging burden.”

I’ve seen this problem in action for years. The most prominent example involves electronic health records (EHRs). These were meant to improve care and make things much more efficient. And while they have brought benefits, they have also increased the amount of time healthcare staff have to spend dealing with documentation.

One study found that time spent on direct patient care dropped by more than 8 percent at one center. Another found that nurses perceive a high workload due to all the documentation. In a survey published in March, U.S. physicians were polled about the “documentation burden” presented by EHRs. Majorities said they’re spending too much time on documentation, and that it’s reducing the time they have for patient care. And one-third said they’re spending two hours or more completing documentation outside of work hours each day.

It shouldn’t be this way. Technologies can be designed to handle more administrative tasks so that healthcare workers spend more time in direct patient care. The more we relieve the documentation burden, the more patients can get the attention they need.

The potential of NLP

Natural language processing is a technology focused on helping machines process information as humans do. Several companies have been working to apply this to the world of medicine.

When doctors and nurses need relevant information from a patient’s healthcare records, they should not have to go digging through long lists of information collected over the years. Instead, technology should be able to read through all the text and automatically pull up relevant information for a patient’s treatment. One study published in 2020 found that specifically designed algorithms could do so with 96% accuracy.

Similarly, healthcare providers should be able to speak into their phones or other devices and have the information they provide automatically entered into healthcare records through NLP. When a patient comes into an emergency department complaining of certain symptoms, NLP can help pull up relevant information from the patient’s records – for example, a family history that could show the patient has an elevated risk for a heart attack. So doctors and nurses would see that information automatically pop up when they open the patient’s file.

Of course, there is always a possibility of machine errors, just as there are possibilities of human errors. It’s important to have healthcare personnel look at the information and doublecheck it. But there’s no need for them to spend extra time finding the information in the first place – just as they should not have to scroll through long forms with lots of text fields in order to input information. Technology should do all that for them.

There are also other ways to use NLP. For example, this technology has been built into AskSophie, a tool in which people can describe symptoms they’re having in order to learn about patients with similar ailments and what’s causing them.

Serving the needs of healthcare workers through technology

NLP is just one tool that can help relieve burdens on doctors and nurses and strengthen global healthcare for the future. Artificial intelligence can help deliver a more holistic approach to health by showing government and healthcare leaders the social determinants of health that must be addressed in different areas. Algorithms can help predict patient flow so hospitals have a better sense of how much staff they’ll need at any moment. And companies are developing new ways to monitor patients in need from afar. The possibilities are endless.

The key is to incorporate the needs of healthcare workers in the development of new technologies. The more people are freed to spend time caring for patients and avoiding burdens of documentation, the more people will join and stay in the healthcare field. This will make the global health outlook only stronger.

Speak your Mind Here

Fill in your details below or click an icon to log in:

WordPress.com Logo

You are commenting using your WordPress.com account. Log Out /  Change )

Twitter picture

You are commenting using your Twitter account. Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. Log Out /  Change )

Connecting to %s

%d bloggers like this: