An Empirical Analysis of Topic Modeling for Mining Cancer Clinical Notes

Chan, Katherine Redfield; Lou, Xinghua; Karaletsos, Theofanis; Crosbie, Christopher; Gardos, Stuart; Artz, David; Rätsch, Gunnar

doi:10.1109/icdmw.2013.91

Cited by 28 publications

(17 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We compare our proposed model with Labeled LDA [17], a supervised counterpart of Latent Dirichlet Allocation (LDA) [18], which has been applied previously to clinical data analysis [19]–[21]. The results show that our representations indeed capture the relationship between words and codes.…”

Section: Introductionmentioning

confidence: 99%

Joint learning of representations of medical concepts and words from EHR data

Bai

Chanda

Egleston

et al. 2017

2017 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

View full text Add to dashboard Cite

There has been an increasing interest in learning low-dimensional vector representations of medical concepts from electronic health records (EHRs). While EHRs contain structured data such as diagnostic codes and laboratory tests, they also contain unstructured clinical notes, which provide more nuanced details on a patient’s health status. In this work, we propose a method that jointly learns medical concept and word representations. In particular, we focus on capturing the relationship between medical codes and words by using a novel learning scheme for word2vec model. Our method exploits relationships between different parts of EHRs in the same visit and embeds both codes and words in the same continuous vector space. In the end, we are able to derive clusters which reflect distinct disease and treatment patterns. In our experiments, we qualitatively show how our methods of grouping words for given diagnostic codes compares with a topic modeling approach. We also test how well our representations can be used to predict disease patterns of the next visit. The results show that our approach outperforms several common methods.

show abstract

Section: Introductionmentioning

confidence: 99%

Joint learning of representations of medical concepts and words from EHR data

Bai

Chanda

Egleston

et al. 2017

2017 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

View full text Add to dashboard Cite

show abstract

“…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]. Additional work has been performed in using topic modeling methods to search for relationships between themes discovered in clinical notes and underlying patient genetics [27]. …”

Section: Introductionmentioning

confidence: 99%

Evaluating topic model interpretability from a primary care physician perspective

Arnold

Chen

et al. 2016

Computer Methods and Programs in Biomedicine

View full text Add to dashboard Cite

Background and Objective Probabilistic topic models provide an unsupervised method for analyzing unstructured text. These models discover semantically coherent combinations of words (topics) that could be integrated in a clinical automatic summarization system for primary care physicians performing chart review. However, the human interpretability of topics discovered from clinical reports is unknown. Our objective is to assess the coherence of topics and their ability to represent the contents of clinical reports from a primary care physician’s point of view. Methods Three latent Dirichlet allocation models (50 topics, 100 topics, and 150 topics) were fit to a large collection of clinical reports. Topics were manually evaluated by primary care physicians and graduate students. Wilcoxon Signed-Rank Tests for Paired Samples were used to evaluate differences between different topic models, while differences in performance between students and primary care physicians (PCPs) were tested using Mann-Whitney U tests for each of the tasks. Results While the 150-topic model produced the best log likelihood, participants were most accurate at identifying words that did not belong in topics learned by the 100-topic model, suggesting that 100 topics provides better relative granularity of discovered semantic themes for the data set used in this study. Models were comparable in their ability to represent the contents of documents. Primary care physicians significantly outperformed students in both tasks. Conclusion This work establishes a baseline of interpretability for topic models trained with clinical reports, and provides insights on the appropriateness of using topic models for informatics applications. Our results indicate that PCPs find discovered topics more coherent and representative of clinical reports relative to students, warranting further research into their use for automatic summarization.

show abstract

“…This technique is a critical component in most text analytics pipelines. The resulting topic models can provide informative and concise summaries of the content of large corpora, which can effectively support their exploration and analysis in diverse domains such as health care [7] and education [35]. However, evaluation of topic modeling results is challenging because no general gold standard is available, and automatic evaluation metrics, like topic coherence [39], at best weakly correlate with human judgments of quality [8,10].…”

Section: Introductionmentioning

confidence: 99%