Natural Language Processing (NLP) AI Technology Patient Data

How Natural Language Processing (NLP) AI Technology is Saving Lives by Mining 'The Patient Narrative'

April 26 2018

You may have heard that big data in healthcare is being used to cure diseases, improve quality of life, predict epidemics and so on. But how much of an impact is this having on society today?

The complexity of human health means that there is a lot of information that radiologists and disease specialists inherently best capture in the patient narrative and other clinical documentation. Up to 80% of patient information is made up of unstructured data. Naturally, many clinicians want to concentrate on their job: telling the story of the patient and how to treat them most effectively rather than spending 50% of their time entering structured information in check boxes and drop downs. Therefore, there's a desire to start using Natural Language Processing (NLP) systematically so that clinicians put more work into patient care and less into clinical documentation. Here at Linguamatics we help healthcare organizations look at how this mass of unstructured data can help identify high-risk patients and reduce the time spent on documentation.

An example of what healthcare providers are looking at the population level for individuals that we know have food insecurity or social isolation issues. These social determinants of health help identify if a patient isn’t eating properly or can't get to an appointment their likelihood of having a good outcome is severely reduced.

But what specifically are they looking for in unstructured data to find these high-risk patients? For example, in radiology reports they’re looking at references to incidental findings like a pulmonary nodule. If a patient is in a road traffic accident, the radiologist might find a case of broken ribs which is being cared for in the ER, but there's a hint that they might have lung cancer. What Linguamatics I2E does is automatically pull out this vital unstructured information overnight from the EHR for the care coordinator to follow up on. At one of our health systems last year there were 37 cases of lung cancer that hadn't previously been diagnosed that were flagged using I2E and could potentially have been missed.

At Linguamatics we look at the population scale to identify those at high-risk, we have a dataset of 25 million medical transcripts, we’ve mined that data to look at patterns of how these concepts are represented in clinical notes. Healthcare organizations will have slight variations in documentation so it is important to tune the NLP algorithms and Linguamatics enable this to be done quickly and effectively.

Watch the full video below to learn more and find out Simon's WTF (What’s the Future) in health moment.

You can also learn more here about how Linguamatics I2E can help identify high-risk patients.

This blog is based on Simon Beaulah’s videoed responses in an interview with Jessica DaMassa of WTF Health @HIMSS18. See what 22 other health innovator have to add by viewing the full playlist at wtf.health.