Electronic cigarettes were developed in China in the early 2000s and first introduced to the US market in 2007. Once established in the US, the product experienced explosive growth, with the number of electronic cigarette users doubling every year between 2008 and 2012. In 2012, it was estimated that 75% of US adults had heard of electronic cigarettes, and 8% had tried them. While electronic cigarettes have been studied over the last sev- eral years, no scientific consensus has emerged regarding either the safety of electronic cigarettes, or their po- tential as a smoking cessation aid. With this proposal, we will investigate how electronic cigarette use is documented in the Veterans Association Electronic Health Record, focusing specifically on the relationship between electronic cigarette use and com- bustible tobacco use, with the goal of understanding both how electronic cigarette use is documented in the context of the United States? only nationwide health system, and how electronic cigarette related information can be reliably extracted from narrative clinical text using fully automated Natural Language Processing meth- ods.
The proposed research focuses on the use of Natural Language Processing methods to automatically extract mentions of electronic cigarette use from the Veterans Association Electronic Health Record. The research will provide insight into important, currently unresolved questions regarding how clinicians record electronic cigarette use in the context of a nationwide health system, and whether patients report the use of electronic cigarettes as a smoking cessation aid or use the devices in conjunction with combustible tobacco.