Machine learning-based coreference resolution of concepts in clinical documents

Ware, Henry; Mullett, Charles J.; Jagannathan, V.; El-Rawas, Oussama

doi:10.1136/amiajnl-2011-000774

Cited by 12 publications

(7 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…From Table 1, we see that we get the best results on both clinical and pathology sections of ODIE dataset. Table 2 shows a comparison of our system with previous state-of-the-art approaches [8,14,42,43,2,13,11,19,40] on i2b2 dataset. Just like for Table 1, the numbers shown in Table 2 correspond to average F1 score across all the i2b2 categories ("test", "treatment" etc.).…”

Section: When Gold Mentions Are Givenmentioning

confidence: 98%

Joint inference for end-to-end coreference resolution for clinical notes

Jindal

Roth

Gunter

2014

Proceedings of the 5th ACM Conference on Bioinformatics, Computational Biology, and Health Informatics

View full text Add to dashboard Cite

Recent US government initiatives have led to wide adoption of Electronic Health Records (EHRs). More and more health care institutions are storing patients' data in an electronic format. These EHRs contain valuable information which can be used in important applications like Clinical Decision Support (CDS). So, Information Extraction (IE) from EHRs is a very promising research area. This paper presents a robust method for end-to-end coreference resolution for clinical narratives. For our experiments, we used the datasets provided by i2b2/VA team as part of i2b2/VA 2011 shared task on coreference resolution. One part of this data was annotated according to ODIE guidelines and another part was annotated according to i2b2 guidelines. We designed a global inference strategy for end-to-end coreference resolution which jointly determines the mention types and coreference relations between them. This technique avoids the problem of error-propagation which is common in pipeline systems. For pronominal resolution, we developed different strategies for resolving different pronouns. We report the best results to date on both ODIE and i2b2 data. We got the best results for both types of cases: (1) where gold mentions are already given and (2) for end-to-end coreference resolution. ODIE and i2b2 data are annotated quite differently. Best results on both types of data proves the robustness of our algorithm.

show abstract

Section: When Gold Mentions Are Givenmentioning

confidence: 98%

Joint inference for end-to-end coreference resolution for clinical notes

Jindal

Roth

Gunter

2014

Proceedings of the 5th ACM Conference on Bioinformatics, Computational Biology, and Health Informatics

View full text Add to dashboard Cite

show abstract

“…Parameters such as target lesions, tumor measurements, response, performance status and others need to be agreed upon and embedded in the EMR. While there have been enormous efforts on electronic language capture or natural language processing, these systems cannot extract data that does not exist (despite predictive 'neural' algorithms) nor substitute, in our opinion, for quality, standardized information entered at the point-of-care or alternatively, collected and then entered by data-entry personnel [6][7][8].…”

Section: Data Warehouse and Biorepositorymentioning

confidence: 99%

The Creation of an Integrated Health-Information Platform: Building the Framework to Support Personalized Medicine

Sullivan

Hulse

Jacobsen

et al. 2012

Personalized Medicine

View full text Add to dashboard Cite

To advance medicine toward better evidence-based, cost-effective and individualized treatment, a new model of discovery, translation and delivery of information must be developed. This requires the collaboration of the major constituents in the areas of healthcare (i.e., patients, clinicians, administrators and researchers) and the partnership of disciplines (i.e., bioinformatics, epidemiologists, statisticians, information technologists, physicians and scientists) and organizations (i.e., drug and device companies, healthcare agencies, academic and community medical centers and information technology firms) to develop an integrative platform. The over-riding goal of this platform is to improve patient care, with the developed system enabling this by providing each of the major constituents with evidence-based and tailored information at the individual patient level.

show abstract

“…Co-reference resolution aims to recognize two mentions that refer to the same entity in a sentence or across sentences [67]. Current co-reference resolution studies use rule-based [68,69], machine learning [35,70,71] and hybrid systems [72] to identify noun phrases, including person, pronoun, and concepts such as medical tests. The performance of these systems varies depending on the data quality [73].…”

Section: Natural Language Processingmentioning

confidence: 99%

“Big Data” and the Electronic Health Record

Ross¹,

Wei²,

Ohno-Machado³

2014

Yearb Med Inform

136

View full text Add to dashboard Cite

SummaryObjectives: Implementation of Electronic Health Record (EHR) systems continues to expand. The massive number of patient encounters results in high amounts of stored data. Transforming clinical data into knowledge to improve patient care has been the goal of biomedical informatics professionals for many decades, and this work is now increasingly recognized outside our field. In reviewing the literature for the past three years, we focus on "big data" in the context of EHR systems and we report on some examples of how secondary use of data has been put into practice. Methods: We searched PubMed database for articles from January 1, 2011 to November 1, 2013. We initiated the search with keywords related to "big data" and EHR. We identified relevant articles and additional keywords from the retrieved articles were added. Based on the new keywords, more articles were retrieved and we manually narrowed down the set utilizing predefined inclusion and exclusion criteria. Results: Our final review includes articles categorized into the themes of data mining (pharmacovigilance, phenotyping, natural language processing), data application and integration (clinical decision support, personal monitoring, social media), and privacy and security. Conclusion: The increasing adoption of EHR systems worldwide makes it possible to capture large amounts of clinical data. There is an increasing number of articles addressing the theme of "big data", and the concepts associated with these articles vary. The next step is to transform healthcare big data into actionable knowledge.

show abstract

Machine learning-based coreference resolution of concepts in clinical documents

Abstract: Our machine learning approach is a promising solution for recognizing coreferent concepts, which in turn is useful for practical applications such as the assembly of problem and medication lists from clinical documents.

Cited by 12 publications

References 8 publications

Joint inference for end-to-end coreference resolution for clinical notes

Joint inference for end-to-end coreference resolution for clinical notes

The Creation of an Integrated Health-Information Platform: Building the Framework to Support Personalized Medicine

“Big Data” and the Electronic Health Record

Contact Info

Product

Resources

About