Redundancy-Aware Topic Modeling for Patient Record Notes

Abstract

The clinical notes in a given patient record contain much redundancy, in large part due to clinicians’ documentation habit of copying from previous notes in the record and pasting into a new note. Previous work has shown that this redundancy has a negative impact on the quality of text mining and topic modeling in particular. In this paper we describe a novel variant of Latent Dirichlet Allocation (LDA) topic modeling, Red-LDA, which takes into account the inherent redundancy of patient records when modeling content of clinical notes. To assess the value of Red-LDA, we experiment with three baselines and our novel redundancy-aware topic modeling method: given a large collection of patient records, (i) apply vanilla LDA to all documents in all input records; (ii) identify and remove all redundancy by chosing a single representative document for each record as input to LDA; (iii) identify and remove all redundant paragraphs in each record, leaving partial, non-redundant documents as input to LDA; and (iv) apply Red-LDA to all documents in all input records. Both quantitative evaluation carried out through log-likelihood on held-out data and topic coherence of produced topics and qualitative assessement of topics carried out by physicians show that Red-LDA produces superior models to all three baseline strategies. This research contributes to the emerging field of understanding the characteristics of the electronic health record and how to account for them in the framework of data mining. The code for the two redundancy-elimination baselines and Red-LDA is made publicly available to the community.

Evaluating topic model interpretability from a primary care physician perspective

“…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].…”

“…A topic may then be sampled from the topic multinomial, which indexes individual topics from which words are drawn to generate documents. The inclusion of a Dirichlet prior has the benefit of mitigating overfitting, which is a limitation of PLSI [18]. …”

Using phrases and document metadata to improve topic modeling of clinical reports

“…[7,8] In the clinical domain, work has investigated the use of topic models in cased-based retrieval,[1] characterizing clinical concepts over time,[9] and the impact of copy and pasted text on topic learning. [10] Topics have also been used as features in classifiers in order to predict patient satisfaction,[11] depression,[12] infection,[13] and mortality. [14]…”

A Strategy for Prioritizing Electronic Medical Records Using Structured Analysis and Natural Language Processing

“…Even though the goal of anonymization proposals is not to analyze or prioritize EMRs, the NLP techniques applied to recognize identifiers and quasi-identifiers are very close to the process of identifying entities for other purposes. Other existing research for EMR text pre-processing has demonstrated the possibility of extracting temporal expressions [32], [33]; correcting misspelled words [34]; resolving existing coreferences [35]; eliminating redundancy [36] and generating summaries [37].…”