“…These models have been largely discussed for general corpora (e.g., newspaper articles), and have been developed for many uses, including word-sense disambiguation [13], topic correlation [14], learning information hierarchies [15], and tracking themes over time [16, 17]. In the biomedical domain, work has investigated the use of topic models to evaluate the impact of copy and pasted text on topic learning [18], better understanding and predicting Medical Subject Headings (MeSH) applied to PubMed articles [19], and exploring the correlation between Federal Drug Administration (FDA) research priorities and topics in research articles funded under those priorities [20]. Recently, topic models have been employed in the clinical domain in problems such as cased-based retrieval [21]; characterizing clinical concepts over time [22]; and predicting patient satisfaction [23], depression [24], infection [25], and mortality [26].…”