Research and applications: Word sense disambiguation in the clinical domain: a comparison of knowledge-rich and knowledge-poor unsupervised methods

Objective

To evaluate state-of-the-art unsupervised methods on the word sense disambiguation (WSD) task in the clinical domain. In particular, to compare graph-based approaches relying on a clinical knowledge base with bottom-up topic-modeling-based approaches. We investigate several enhancements to the topic-modeling techniques that use domain-specific knowledge sources.

Materials and methods

The graph-based methods use variations of PageRank and distance-based similarity metrics, operating over the Unified Medical Language System (UMLS). Topic-modeling methods use unlabeled data from the Multiparameter Intelligent Monitoring in Intensive Care (MIMIC II) database to derive models for each ambiguous word. We investigate the impact of using different linguistic features for topic models, including UMLS-based and syntactic features. We use a sense-tagged clinical dataset from the Mayo Clinic for evaluation.

Results

The topic-modeling methods achieve 66.9% accuracy on a subset of the Mayo Clinic''s data, while the graph-based methods only reach the 40–50% range, with a most-frequent-sense baseline of 56.5%. Features derived from the UMLS semantic type and concept hierarchies do not produce a gain over bag-of-words features in the topic models, but identifying phrases from UMLS and using syntax does help.

Discussion

Although topic models outperform graph-based methods, semantic features derived from the UMLS prove too noisy to improve performance beyond bag-of-words.

Conclusions

Topic modeling for WSD provides superior results in the clinical domain; however, integration of knowledge remains to be effectively exploited.     

Research and applications: Learning regular expressions for clinical text classification

Objectives

Natural language processing (NLP) applications typically use regular expressions that have been developed manually by human experts. Our goal is to automate both the creation and utilization of regular expressions in text classification.

Methods

We designed a novel regular expression discovery (RED) algorithm and implemented two text classifiers based on RED. The RED+ALIGN classifier combines RED with an alignment algorithm, and RED+SVM combines RED with a support vector machine (SVM) classifier. Two clinical datasets were used for testing and evaluation: the SMOKE dataset, containing 1091 text snippets describing smoking status; and the PAIN dataset, containing 702 snippets describing pain status. We performed 10-fold cross-validation to calculate accuracy, precision, recall, and F-measure metrics. In the evaluation, an SVM classifier was trained as the control.

Results

The two RED classifiers achieved 80.9–83.0% in overall accuracy on the two datasets, which is 1.3–3% higher than SVM''s accuracy (p<0.001). Similarly, small but consistent improvements have been observed in precision, recall, and F-measure when RED classifiers are compared with SVM alone. More significantly, RED+ALIGN correctly classified many instances that were misclassified by the SVM classifier (8.1–10.3% of the total instances and 43.8–53.0% of SVM''s misclassifications).

Conclusions

Machine-generated regular expressions can be effectively used in clinical text classification. The regular expression-based classifier can be combined with other classifiers, like SVM, to improve classification performance.     

Evaluating the state of the art in disorder recognition and normalization of the clinical narrative

Objective The ShARe/CLEF eHealth 2013 Evaluation Lab Task 1 was organized to evaluate the state of the art on the clinical text in (i) disorder mention identification/recognition based on Unified Medical Language System (UMLS) definition (Task 1a) and (ii) disorder mention normalization to an ontology (Task 1b). Such a community evaluation has not been previously executed. Task 1a included a total of 22 system submissions, and Task 1b included 17. Most of the systems employed a combination of rules and machine learners.Materials and methods We used a subset of the Shared Annotated Resources (ShARe) corpus of annotated clinical text—199 clinical notes for training and 99 for testing (roughly 180 K words in total). We provided the community with the annotated gold standard training documents to build systems to identify and normalize disorder mentions. The systems were tested on a held-out gold standard test set to measure their performance.Results For Task 1a, the best-performing system achieved an F₁ score of 0.75 (0.80 precision; 0.71 recall). For Task 1b, another system performed best with an accuracy of 0.59.Discussion Most of the participating systems used a hybrid approach by supplementing machine-learning algorithms with features generated by rules and gazetteers created from the training data and from external resources.Conclusions The task of disorder normalization is more challenging than that of identification. The ShARe corpus is available to the community as a reference standard for future studies.     

Automated confidence ranked classification of randomized controlled trial articles: an aid to evidence-based medicine

Objective: For many literature review tasks, including systematic review (SR) and other aspects of evidence-based medicine, it is important to know whether an article describes a randomized controlled trial (RCT). Current manual annotation is not complete or flexible enough for the SR process. In this work, highly accurate machine learning predictive models were built that include confidence predictions of whether an article is an RCT.Materials and Methods: The LibSVM classifier was used with forward selection of potential feature sets on a large human-related subset of MEDLINE to create a classification model requiring only the citation, abstract, and MeSH terms for each article.Results: The model achieved an area under the receiver operating characteristic curve of 0.973 and mean squared error of 0.013 on the held out year 2011 data. Accurate confidence estimates were confirmed on a manually reviewed set of test articles. A second model not requiring MeSH terms was also created, and performs almost as well.Discussion: Both models accurately rank and predict article RCT confidence. Using the model and the manually reviewed samples, it is estimated that about 8000 (3%) additional RCTs can be identified in MEDLINE, and that 5% of articles tagged as RCTs in Medline may not be identified.Conclusion: Retagging human-related studies with a continuously valued RCT confidence is potentially more useful for article ranking and review than a simple yes/no prediction. The automated RCT tagging tool should offer significant savings of time and effort during the process of writing SRs, and is a key component of a multistep text mining pipeline that we are building to streamline SR workflow. In addition, the model may be useful for identifying errors in MEDLINE publication types. The RCT confidence predictions described here have been made available to users as a web service with a user query form front end at: http://arrowsmith.psych.uic.edu/cgi-bin/arrowsmith_uic/RCT_Tagger.cgi.     

PhenDisco: phenotype discovery system for the database of genotypes and phenotypes

The database of genotypes and phenotypes (dbGaP) developed by the National Center for Biotechnology Information (NCBI) is a resource that contains information on various genome-wide association studies (GWAS) and is currently available via NCBI''s dbGaP Entrez interface. The database is an important resource, providing GWAS data that can be used for new exploratory research or cross-study validation by authorized users. However, finding studies relevant to a particular phenotype of interest is challenging, as phenotype information is presented in a non-standardized way. To address this issue, we developed PhenDisco (phenotype discoverer), a new information retrieval system for dbGaP. PhenDisco consists of two main components: (1) text processing tools that standardize phenotype variables and study metadata, and (2) information retrieval tools that support queries from users and return ranked results. In a preliminary comparison involving 18 search scenarios, PhenDisco showed promising performance for both unranked and ranked search comparisons with dbGaP''s search engine Entrez. The system can be accessed at http://pfindr.net.