Struggling to identify CMS lung cancer LDCT candidates? NLP can help!

May 13 2016

What if physicians could offer patients access to a potentially life-preserving test, but could not easily identify which of their patients were eligible?

That is the exact situation many providers have found themselves in since Medicare announced it would begin covering lung cancer screening for patients meeting a certain set of criteria.

In a decision memo published February, 2015, CMS agreed to make Medicare coverage available for a low dose computed tomography (LDCT) lung cancer screening for eligible patients. Patients who are between ages 55 and 77, asymptomatic, are either a current smoker or have quit within the last 15 years, and, have a tobacco smoking history of at least 30 pack-years can now qualify for an annual preventative screening.

CMS added the coverage after determining there was sufficient evidence that LDCT procedures were cost-effective for high risk populations. A study by the National Lung Cancer Screening Trial, for example, found that 12,000 deaths a year could be avoided if high-risk patients underwent a LDCT scan. Lung cancer is currently the leading cause of cancer-related death among both men and women in the US.

While Medicare coverage for LDCT screening has great potential to save lives, the identification of eligible cohorts has proved difficult. While some modern EHRs may capture elements of the eligibility criteria, many of the relevant details are stored in an unstructured text format because of the complicated nature of documenting tobacco use.

The documentation of tobacco use requires flexibility in describing the types of tobacco (e.g., cigarettes, cigars, chewable) and the amount and frequency of tobacco use, including changes over time. Providers must also note start and quit dates for tobacco use, along with the quit duration. These elements are essential when calculating pack-years, which is based on the number of packs of cigarettes smoked per day multiplied by the number of years the patient has smoked.

Because so much critical information is stored as unstructured text, the process for identifying patients eligible for LDCT screenings requires significant manual chart review and is very tedious. This means that opportunities for early detection of lung cancer are being missed in a disease where early detection is critical to successful treatment. Natural language processing (NLP) technologies, however, can facilitate cohort selection by extracting structured information from unstructured patient documentation. 

Using Linguamatics I2E, patients who meet the requirements for LDCT lung cancer screening can be identified from unstructured patient text.

Linguamatics are working with providers to leverage our I2E NLP technology to query free-text within patient records and easily identify which patients meet Medicare’s LDCT screening requirements based on their age, disease and smoking status, and pack-year consumption. Because eligible patients are more easily identified, more high-risk individuals are likely to take advantage of LDCT testing and hence benefit from earlier treatment.

Linguamatics NLP technology gives providers the ability to easily query free-text narratives – which quite possibly can help physicians save more lives.