This study by Masser et al. aims to quantify the impact of transportation insecurity on the delivery of routine ophthalmological care. Researchers performed a retrospective, cross-sectional study and utilizing demographic information in combination with free text in a Natural language processing (NLP) model in order to identify associations between demographic and transportation insecurity. Researchers found that amongst various demographics, the main statistically significant correlations found between demographic and transportation insecurity is that those who are older (≥ 80 years old) are more likely to suffer from transportation insecurity and those who identify as Asian are less likely to identify as transportation insecure compared to those who may identify as White or Black. One important consideration to keep in mind when utilizing NLPs in clinical settings is that NLPs often have linguistic challenges such as identifying negations, hypothetical language along with implied inferences. As a result, NLPs face difficulty when it comes to interpreting clinical data such as patient notes as social needs often need to be implied and supplemented with contextual understanding.