Natural language processing is a subdivision of artificial intelligence – and one that could be of great use in healthcare, mining clinical nuggets from all free texts in electronic health records and data warehouses .
Marty Elisco, CEO of Augintel, a healthcare NLP company, believes that NLP will go mainstream in 2023 for three reasons: the bottlenecks are solved, the value is proven, and right time.
Healthcare IT News spoke to Elisco to get him to better explain these reasons and help healthcare CIOs and other health IT leaders understand why 2023 might just be the year for NLP.
Q. One of the reasons you suggest more healthcare providers will adopt natural language processing technology by 2023 is because this kinks have been solved. Please talk about the problems you said were solved and how that would encourage adoption.
ONE. Let’s first set the definition of NLP by level. NLP refers to the branch of computer science that deals with giving computers the ability to understand text and speech in the same way that humans can.
NLP can be applied in a number of contexts. It may refer to speech-to-text recognition. It can also be used for handwriting recognition. But in our segment and in the context of this discussion, we are using NLP to crawl content — or extract information — from text.
About five years ago, machine learning technology took a huge leap forward. It is possible to train algorithms efficiently with huge amounts of data. That innovation enabled NLP for intelligent content – machine learning began to be applied to large amounts of narrative data to build NLP models that could identify key concepts described in text. .
Over the past few years, as the cost of developing a model has decreased, it has become economically feasible to develop industry-specific models.
For example, in the legal industry, NLP has been used for e-discovery. Attorneys use NLP to mine the material provided during the discovery phase to make it easier to use relevant content. And there has been a lot of progress lately in leveraging NLP in healthcare – behavioral health and health and human services, more specifically.
Early efforts at smart content in health and human services are often custom projects aimed at analyzing data at a specific point in time rather than providing a tool that is accessible on a daily basis. The expertise and effort required to “teach” the intensive healthcare landscape is too burdensome for many and leads to project failure – or never being started.
Over the last year or so, industry-specific solutions have become available in the market as the tests to prove them have been completed. These pilot programs benefit from collaboration between data scientists and customers/users, who have fine-tuned the language model for the needs of that industry.
So the bottlenecks have been solved. The technology is mature and stable, innovative technology companies have built task-specific SaaS solutions that can be easily achieved with context-intensive and customers are now reaping the rewards. .
Q. You also say that the value of NLP has been proven. Please give a few examples of NLP that prove its worth.
ONE. The ROI achieved by organizations leveraging NLP has been delivered.
As an example, case officers in Allegheny County continue to discover that a wealth of information has been buried in case notes and unstructured data. With the information overload, it takes a lot of time for the staff in charge to find the relevant data.
They want to tackle this challenge – the challenge of quickly accessing critical data at the right time with the ultimate goal of helping to improve services for the families and children they help. They know that the ability to access deeper insights quickly and easily paints a picture of the whole incident without having to spend hours flipping through notes.
In particular, a caseworker claimed that the NLP platform alone saved her 5 hours per week of administrative work.
An NLP background has also helped Allegheny County better understand the social determinants of health. Often, a careful review of the entire case history is needed to understand things like drug history or home insecurity – two SDOH factors that significantly affect overall health. But with all the color, detail and deeper descriptions living in unstructured data, an NLP tool allows social workers to see early warning signs in real time.
Needless to say, it’s incredibly useful for families when case workers can pull information like this from unstructured data earlier in the process.
Q. And finally, you say that with 2023, this is the right time for NLP in healthcare. Please explain.
ONE. It’s no secret that staff shortages and burnout have become a real challenge for healthcare organizations in recent years. According to a study published in Mayo Clinic Proceedings, the rate of clinician burnout among US physicians spiked during the first two years of the COVID-19 pandemic after six years of decline.
Furthermore, the study found that the rate of clinician burnout is 62.8% in 2021, compared with 38.2% in 2020. The trend is clear.
Additional research has shown that 64% of burnout is due to an administrative burden, which certainly contributes to the break point of the caseworker. With overstressed employees, the attrition rate remains high.
Some organizations report 30% attrition per quarter. There is a loss of case knowledge that occurs with attrition, and that loss directly affects the outcome. When new caregivers are assigned, they simply don’t have time to read the entire file, which can lead to disruption of the continuum of care, especially in complex cases.
So you have skinny curators and clinicians who are spending too much time with the people they care for, and they’ve had more than enough. Coupled with the impact on outcomes from lost case knowledge, it is clear that the status quo cannot continue if we are to maintain a reliable and functioning health care system. .
At the same time, there are significant advances in cost-effective machine learning tools, especially NLP, that can alleviate that stress somewhat. It’s time for health care providers to lean on the tools at hand. Therefore, I believe that 2023 will be the year NLP takes off.
Follow Bill’s HIT coverage on LinkedIn: Bill Siwicki
Email the writer: [email protected]
Healthcare IT News is a publication of HIMSS Media.
