Search

The emergence of "big data" initiatives has led to the need for tools that can automatically extract valuable chemical information from large volumes of unstructured data, such as the scientific literature. Since chemical information can be present in figures, tables, and textual paragraphs, successful information extraction often depends on the ability to interpret all of these domains simultaneously. We present a complete toolkit for the automated extraction of chemical entities and their associated properties, measurements, and relationships from scientific documents that can be used to populate structured chemical databases. Our system provides an extensible, chemistry-aware, natural language processing pipeline for tokenization, part-of-speech tagging, named entity recognition, and phrase parsing. Within this scope, we report improved performance for chemical named entity recognition through the use of unsupervised word clustering based on a massive corpus of chemistry articles. For phrase parsing and information extraction, we present the novel use of multiple rule-based grammars that are tailored for interpreting specific document domains such as textual paragraphs, captions, and tables. We also describe document-level processing to resolve data interdependencies and show that this is particularly necessary for the autogeneration of chemical databases since captions and tables commonly contain chemical identifiers and references that are defined elsewhere in the text. The performance of the toolkit to correctly extract various types of data was evaluated, affording an F-score of 93.4%, 86.8%, and 91.5% for extracting chemical identifiers, spectroscopic attributes, and chemical property attributes, respectively; set against the CHEMDNER chemical name extraction challenge, ChemDataExtractor yields a competitive F-score of 87.8%. All tools have been released under the MIT license and are available to download from http://www.chemdataextractor.org .

Objectives: Osteoporosis treatment rates after a fracture are low. This study evaluated methods to increase guideline-recommended osteoporosis care postfracture., Design: Participants were randomly assigned to usual care or one of two interventions. Analysis of primary outcomes used electronic data and linear regression., Setting: A Pacific Northwest nonprofit health maintenance organization., Participants: Female patients aged 50 to 89 who suffered a fracture in 1999 and had not received bone mineral density (BMD) measurement or medication for osteoporosis (n=311) and their primary care providers (n=159)., Intervention: Patient-specific clinical guideline advice to the primary care provider delivered by electronic medical record (EMR) message or electronic reminder to the provider plus an educational letter mailed to the patient., Measurements: BMD measurement and osteoporosis medication., Results: At 6 months, provider reminder resulted in 51.5% of patients receiving BMD measurement or osteoporosis medication, provider reminder plus patient education resulted in 43.1%, and usual care resulted in 5.9% (P<.001). The effect of provider advice combined with patient education was not significantly different from provider advice alone (P=.88). Patients aged 60 to 69 were 18% (95% confidence interval=3-34) more likely to receive BMD measurement or an osteoporosis medication than those aged 80 to 89., Conclusion: Patient-specific postfracture advice to the provider through an EMR message significantly increased BMD measurement and osteoporosis medication. As EMRs become more widespread, this intervention could improve osteoporosis management for many postfracture patients. Future research should identify barriers to and facilitators of care for older, high-risk patients.

High blood pressure (also called hypertension) is one of the most important and common risk factors for atherosclerotic cardiovascular disease (CVD) and other chronic diseases. National guidelines recommend that all individuals with blood pressure readings of 120/80 mm Hg or higher adopt healthy lifestyle habits, including the Dietary Approaches to Stop Hypertension (DASH) diet, to manage their blood pressure. The DASH diet, which is high in fruits, vegetables, and low-fat dairy products and reduced in fat, has been shown in large, randomized, controlled trials to reduce blood pressure significantly. The DASH diet also has been shown to reduce blood cholesterol and homocysteine levels and to enhance the benefits of antihypertensive drug therapy. The DASH diet should be promoted, along with maintaining healthy weight, reducing sodium intake, increasing regular physical activity, and limiting alcohol intake, for lowering blood pressure and reducing the risk of CVD.

The preponderance of literature supports the efficacy of specialist care for asthma. Not every patient with asthma needs to be treated by a specialist, however. An optimal health care delivery model for asthma (i.e. one that provides high quality care that is cost effective) requires some mix of primary and specialty services. A tiered model of care in which the primary care physician acts as the first point of contact and decision-maker with regard to referral and that includes asthma specialists, including allergists, pulmonologists, and other health care professionals with expertise in asthma, appears to be a reasonable solution. The number of studies that compare various models for organizing asthma care is limited, however. Thus, further research is needed to determine how best to align the roles of primary care physicians, allied health professionals, and subspecialists in order to ensure seamless communication and cost-effective care that is targeted to individual patient needs.

A simple new goniometer has been developed for measurement of the mobility of the cervical spine. It consists of a headgear with three rigid scales calibrated in degrees, mounted on a skull cap with straps around the chin, and it measures flexion/extension, lateral flexion and horizontal rotation. Its construction and use are described. Three observers each tested the same 10 subjects to determine inter-observer error. Two observers then each tested 10 different subjects on two occasions at intervals of 10 to 30 minutes to test intra-observer error. Statistical analysis of the inter-observer error data by analysis of variance, and the intra-observer error data by calculation of means and standard errors of the differences between the means, showed that acceptably reproducible results could be obtained with this new goniometer, and it is also shown that an experienced observer can obtain more consistently reproducible results. Reference is made to the successful use of this technique in a comparative study (published elsewhere) of two drugs in degenerative joint disease of the cervical spine.