MCORES: a system for noun phrase coreference resolution for clinical records

Objective

Narratives of electronic medical records contain information that can be useful for clinical practice and multi-purpose research. This information needs to be put into a structured form before it can be used by automated systems. Coreference resolution is a step in the transformation of narratives into a structured form.

Methods

This study presents a medical coreference resolution system (MCORES) for noun phrases in four frequently used clinical semantic categories: persons, problems, treatments, and tests. MCORES treats coreference resolution as a binary classification task. Given a pair of concepts from a semantic category, it determines coreferent pairs and clusters them into chains. MCORES uses an enhanced set of lexical, syntactic, and semantic features. Some MCORES features measure the distance between various representations of the concepts in a pair and can be asymmetric.

Results and Conclusion

MCORES was compared with an in-house baseline that uses only single-perspective ‘token overlap’ and ‘number agreement’ features. MCORES was shown to outperform the baseline; its enhanced features contribute significantly to performance. In addition to the baseline, MCORES was compared against two available third-party, open-domain systems, RECONCILE_ACL09 and the Beautiful Anaphora Resolution Toolkit (BART). MCORES was shown to outperform both of these systems on clinical records.     

2010 i2b2/VA challenge on concepts,assertions, and relations in clinical text

The 2010 i2b2/VA Workshop on Natural Language Processing Challenges for Clinical Records presented three tasks: a concept extraction task focused on the extraction of medical concepts from patient reports; an assertion classification task focused on assigning assertion types for medical problem concepts; and a relation classification task focused on assigning relation types that hold between medical problems, tests, and treatments. i2b2 and the VA provided an annotated reference standard corpus for the three tasks. Using this reference standard, 22 systems were developed for concept extraction, 21 for assertion classification, and 16 for relation classification.These systems showed that machine learning approaches could be augmented with rule-based systems to determine concepts, assertions, and relations. Depending on the task, the rule-based systems can either provide input for machine learning or post-process the output of machine learning. Ensembles of classifiers, information from unlabeled data, and external knowledge sources can help when the training data are inadequate.     

The role of information technology in translating educational interventions into practice: an analysis using the PRECEDE/PROCEED model

Objective

The evidence base for information technology (IT) has been criticized, especially with the current emphasis on translational science. The purpose of this paper is to present an analysis of the role of IT in the implementation of a geriatric education and quality improvement (QI) intervention.

Design

A mixed-method three-group comparative design was used. The PRECEDE/PROCEED implementation model was used to qualitatively identify key factors in the implementation process. These results were further explored in a quantitative analysis.

Method

Thirty-three primary care clinics at three institutions (Intermountain Healthcare, VA Salt Lake City Health Care System, and University of Utah) participated. The program consisted of an onsite, didactic session, QI planning and 6 months of intense implementation support.

Results

Completion rate was 82% with an average improvement rate of 21%. Important predisposing factors for success included an established electronic record and a culture of quality. The reinforcing and enabling factors included free continuing medical education credits, feedback, IT access, and flexible support. The relationship between IT and QI emerged as a central factor. Quantitative analysis found significant differences between institutions for pre–post changes even after the number and category of implementation strategies had been controlled for.

Conclusions

The analysis illustrates the complex dependence between IT interventions, institutional characteristics, and implementation practices. Access to IT tools and data by individual clinicians may be a key factor for the success of QI projects. Institutions vary widely in the degree of access to IT tools and support. This article suggests that more attention be paid to the QI and IT department relationship.     

Impact of data fragmentation across healthcare centers on the accuracy of a high-throughput clinical phenotyping algorithm for specifying subjects with type 2 diabetes mellitus

Objective

To evaluate data fragmentation across healthcare centers with regard to the accuracy of a high-throughput clinical phenotyping (HTCP) algorithm developed to differentiate (1) patients with type 2 diabetes mellitus (T2DM) and (2) patients with no diabetes.

Materials and methods

This population-based study identified all Olmsted County, Minnesota residents in 2007. We used provider-linked electronic medical record data from the two healthcare centers that provide >95% of all care to County residents (ie, Olmsted Medical Center and Mayo Clinic in Rochester, Minnesota, USA). Subjects were limited to residents with one or more encounter January 1, 2006 through December 31, 2007 at both healthcare centers. DM-relevant data on diagnoses, laboratory results, and medication from both centers were obtained during this period. The algorithm was first executed using data from both centers (ie, the gold standard) and then from Mayo Clinic alone. Positive predictive values and false-negative rates were calculated, and the McNemar test was used to compare categorization when data from the Mayo Clinic alone were used with the gold standard. Age and sex were compared between true-positive and false-negative subjects with T2DM. Statistical significance was accepted as p<0.05.

Results

With data from both medical centers, 765 subjects with T2DM (4256 non-DM subjects) were identified. When single-center data were used, 252 T2DM subjects (1573 non-DM subjects) were missed; an additional false-positive 27 T2DM subjects (215 non-DM subjects) were identified. The positive predictive values and false-negative rates were 95.0% (513/540) and 32.9% (252/765), respectively, for T2DM subjects and 92.6% (2683/2898) and 37.0% (1573/4256), respectively, for non-DM subjects. Age and sex distribution differed between true-positive (mean age 62.1; 45% female) and false-negative (mean age 65.0; 56.0% female) T2DM subjects.

Conclusion

The findings show that application of an HTCP algorithm using data from a single medical center contributes to misclassification. These findings should be considered carefully by researchers when developing and executing HTCP algorithms.     

Towards spoken clinical-question answering: evaluating and adapting automatic speech-recognition systems for spoken clinical questions

Objective

To evaluate existing automatic speech-recognition (ASR) systems to measure their performance in interpreting spoken clinical questions and to adapt one ASR system to improve its performance on this task.

Design and measurements

The authors evaluated two well-known ASR systems on spoken clinical questions: Nuance Dragon (both generic and medical versions: Nuance Gen and Nuance Med) and the SRI Decipher (the generic version SRI Gen). The authors also explored language model adaptation using more than 4000 clinical questions to improve the SRI system''s performance, and profile training to improve the performance of the Nuance Med system. The authors reported the results with the NIST standard word error rate (WER) and further analyzed error patterns at the semantic level.

Results

Nuance Gen and Med systems resulted in a WER of 68.1% and 67.4% respectively. The SRI Gen system performed better, attaining a WER of 41.5%. After domain adaptation with a language model, the performance of the SRI system improved 36% to a final WER of 26.7%.

Conclusion

Without modification, two well-known ASR systems do not perform well in interpreting spoken clinical questions. With a simple domain adaptation, one of the ASR systems improved significantly on the clinical question task, indicating the importance of developing domain/genre-specific ASR systems.     

Machine-learned solutions for three stages of clinical information extraction: the state of the art at i2b2 2010

Objective

As clinical text mining continues to mature, its potential as an enabling technology for innovations in patient care and clinical research is becoming a reality. A critical part of that process is rigid benchmark testing of natural language processing methods on realistic clinical narrative. In this paper, the authors describe the design and performance of three state-of-the-art text-mining applications from the National Research Council of Canada on evaluations within the 2010 i2b2 challenge.

Design

The three systems perform three key steps in clinical information extraction: (1) extraction of medical problems, tests, and treatments, from discharge summaries and progress notes; (2) classification of assertions made on the medical problems; (3) classification of relations between medical concepts. Machine learning systems performed these tasks using large-dimensional bags of features, as derived from both the text itself and from external sources: UMLS, cTAKES, and Medline.

Measurements

Performance was measured per subtask, using micro-averaged F-scores, as calculated by comparing system annotations with ground-truth annotations on a test set.

Results

The systems ranked high among all submitted systems in the competition, with the following F-scores: concept extraction 0.8523 (ranked first); assertion detection 0.9362 (ranked first); relationship detection 0.7313 (ranked second).

Conclusion

For all tasks, we found that the introduction of a wide range of features was crucial to success. Importantly, our choice of machine learning algorithms allowed us to be versatile in our feature design, and to introduce a large number of features without overfitting and without encountering computing-resource bottlenecks.