abstract: Medical errors are now estimated to be the third leading cause of death in the United States (Makary & Daniel, 2016). Look-alike, sound- alike prescription drug mix-ups contribute to this figure. The US Food and Drug Administration (FDA) and Institute for Safe Medication Practices (ISMP) have recommended the use of Tall Man lettering since 2008, in which dissimilar portions of confusable drug names pairs are capitalized in order to make them more distinguishable. Research on the efficacy of Tall Man lettering in differentiating confusable drug name pairs has been inconclusive and it is imperative to investigate potential efficacy further considering the clinical implications (Lambert, Schroeder & Galanter, 2015). The present study aimed to add to the body of research on Tall Man lettering while also investigating another possibility for the mechanism behind Tall Man’s efficacy, if it in fact exists. Studies indicate that the first letter in a word offers an advantage over other positions, resulting in more accurate and faster recognition (Adelman, Marquis & Sabatos-DeVito, 2010; Scaltritti & Balota, 2013). The present study used a 2x3 repeated measures design to analyze the effect of position on Tall Man lettering efficacy. Participants were shown a prime drug, followed by a brief mask, and then either the same drug name or its confusable pair and asked to identify whether they were the same or different. All participants completed both lowercase and Tall Man conditions. Overall performance measured by accuracy and reaction time revealed lowercase to be more effective than Tall Man. With regard to the position of Tall Man letters, a first position advantage was seen both in accuracy and reaction time. A first position advantage was seen in the lowercase condition as well, suggesting the location of the differing portion of the word matters more than the format used. These findings add to the body of inconclusive research on the efficacy of Tall Man lettering in drug name confusion. Considering its impact on patient safety, more research should be conducted to definitively answer the question as to whether or not Tall Man should be used in practice. / Dissertation/Thesis / Masters Thesis Human Systems Engineering 2017

This thesis evaluates if and how drug name recognition can be used to find drug names in verbatims from reports on concomitant medication in clinical trial studies. In clinical trials, reports on concomitant medication are written if a trial participant takes other drugs than the studied drug. This information needs to be coded to a drug reference dictionary. Coded verbatims were used to create the data needed to train the drug name recognition models in this thesis. Labels for where in each verbatim the coded drugs name was, were created using a Levensthein distance. The drug name recognition models were trained and tested on verbatims with labels. Drug name recognition was performed using a logistic regression model and a bidirectional long short-term memory model. The bidirectional long short-term memory model performed the best result with an F1 score of 82.5% on classifying which words in the verbatims that were drug names. When the results were studied from case to case, they showed that the bidirectional long short-term memory classifications sometimes outperformed labels it was trained on in single word verbatims. The model was also tested on manually labelled golden standard data where it performed an F1-score of 46.4%. The results indicate that a bidirectional long short-term memory model can be implemented for drug name recognition, but that label reliability is an issue in this thesis.