Extracting Healthcare Quality Information from Unstructured Data.

Healthcare quality research is a fundamental task that involves assessing treatment patterns and measuring the associated patient outcomes to identify potential areas for improving healthcare. While both qualitative and quantitative approaches are used, a major obstacle for the quantitative approach is that many useful healthcare quality indicators are buried within provider narrative notes, requiring expensive and laborious manual chart review to identify and measure them. Information extraction is a key Natural Language Processing (NLP) task for discovering and mining critical knowledge buried in unstructured clinical data.

Canary: An NLP Platform for Clinicians and Researchers.

Information Extraction methods can help discover critical knowledge buried in the vast repositories of unstructured clinical data. However, these methods are underutilized in clinical research, potentially due to the absence of free software geared towards clinicians with little technical expertise. The skills required for developing/using such software constitute a major barrier for medical researchers wishing to employ these methods.

Reasons for discontinuation of lipid-lowering medications in patients with chronic kidney disease.

Background/aims: Many patients with chronic kidney disease (CKD) do not receive lipid-lowering therapy despite their high cardiovascular risk. The reasons for this are unknown.

Methods: We have conducted a retrospective cohort study of discontinuation of lipid-lowering drugs in patients with CKD stage 3 and higher treated in practices affiliated with two academic medical centers between 2000 and 2010.

Statin use and calcific uremic arteriolopathy: a matched case-control study.

Background: Calcific uremic arteriolopathy (CUA), also known as calciphylaxis, is characterized by vascular calcification, thrombosis and intense inflammation. Prior research has shown that statins have anticalcification, antithrombotic and antiinflammatory properties; however, the association between statin use and CUA has not been investigated.

Methods: This matched case-control study included 62 adult maintenance hemodialysis (HD) patients with biopsy-confirmed CUA diagnosed between the years 2002 and 2011 (cases).

Discontinuation of statins in routine care settings: a cohort study.

Background: Systematic data on discontinuation of statins in routine practice of medicine are limited.

Objective: To investigate the reasons for statin discontinuation and the role of statin-related events (clinical events or symptoms believed to have been caused by statins) in routine care settings.

Design: A retrospective cohort study.

Structured vs. unstructured: factors affecting adverse drug reaction documentation in an EMR repository.

Adverse reactions to medications to which the patient was known to be intolerant are common. Electronic decision support can prevent them but only if history of adverse reactions to medications is recorded in structured format. We have conducted a retrospective study of 31,531 patients with adverse reactions to statins documented in the notes, as identified with natural language processing.