Building longitudinal medication dose data using medication information extracted from clinical notes in electronic health records

ObjectiveTo develop an algorithm for building longitudinal medication dose datasets using information extracted from clinical notes in electronic health records (EHRs).Materials and MethodsWe developed an algorithm that converts medication information extracted using natural language processing (NLP) into a usable format and builds longitudinal medication dose datasets. We evaluated the algorithm on 2 medications extracted from clinical notes of Vanderbilt’s EHR and externally validated the algorithm using clinical notes from the MIMIC-III clinical care database.ResultsFor the evaluation using Vanderbilt’s EHR data, the performance of our algorithm was excellent; F1-measures were ≥0.98 for both dose intake and daily dose. For the external validation using MIMIC-III, the algorithm achieved F1-measures ≥0.85 for dose intake and ≥0.82 for daily dose.DiscussionOur algorithm addresses the challenge of building longitudinal medication dose data using information extracted from clinical notes. Overall performance was excellent, but the algorithm can perform poorly when incorrect information is extracted by NLP systems. Although it performed reasonably well when applied to the external data source, its performance was worse due to differences in the way the drug information was written. The algorithm is implemented in the R package, “EHR,” and the extracted data from Vanderbilt’s EHRs along with the gold standards are provided so that users can reproduce the results and help improve the algorithm.ConclusionOur algorithm for building longitudinal dose data provides a straightforward way to use EHR data for medication-based studies. The external validation results suggest its potential for applicability to other systems.     

Web-based News Reports on Midwives Compared with Obstetricians: A Prospective Analysis

Abstract: Background: The media both creates and reflects public opinion. The way in which health professionals are depicted in the media is likely to influence views held by and about different health professions. The aim of this study was to examine how midwives and obstetricians are reported in English language web-based news reports from around the world. Methods: News alerts from the Internet search engine Google were created to search for the terms “midwife,”“midwives,”“midwifery,”“obstetrics,” and “obstetricians.” These alerts were received over a 12-month period (May 1, 2006–April 31, 2007), downloaded, and analyzed using quantitative content analysis. Results: A total of 522 web-based news reports for midwifery and 564 for obstetrics (n = 1,086) were found. Dominant categories for midwives were: “mainstreaming midwives” (models of care/rise of midwifery) (28%); “the Cinderella of the maternity care” (workforce/industrial) (27%); “delivering the baby with your hands tied” (funding, insurance, and legislation) (21%); “ask the expert” (education, research, and health advice) (8%), “recognizing midwives” (awards and announcements) (7%), “unsafe midwives” (litigation) (6%); and “the art of birth” (books, film, and photographs) (2%). Dominant categories for obstetricians were: “ask the expert” (research and advice) (26%); “doctors are heroes amongst us” (awards and announcements) (19%); “obstetric workforce woes” (workforce/industrial) (19%); “new frontiers” (trends in care and new technology) (17%); “the disappearing obstetrician” (insurance and litigation) (10%); and “human-interest news reports” (9%). Obstetricians were more likely to be recognized as experts on pregnancy and birth and receive public recognition compared with midwives. Midwives were more likely to be depicted as struggling to be a mainstream option while being hampered by lack of funding, insurance, and legislative barriers. Conclusions: Although midwives have rising acceptance, they still struggle with recognition. Obstetricians have both acceptance and recognition. Countries where midwifery is a mainstream option have more news reports related to midwifery than obstetrics. Different issues appear more dominant in some countries, such as work force in the United Kingdom and funding, insurance, and legislation in the United States. (BIRTH 39:1 March 2012)     

Differential effects of bifrontal tDCS on arousal and sleep duration in insomnia patients and healthy controls

Background

Arousal and sleep represent basic domains of behavior, and alterations are of high clinical importance.

Bone Marrow Failure in Children: Approach to Diagnosis and Treatment

Indian Journal of Pediatrics - Bone marrow failure has many different etiologies, including genetic defects which manifest with specific syndromes, as well as acquired conditions as a result of...     

Urinary bladder cancer risk factors in an area of former coal,iron, and steel industries in Germany

ABSTRACT

This study was performed to investigate the frequency of bladder cancer in patients with an occupational history such as underground hard coal mining and/or painting after the structural change in the local industry. A total of 206 patients with bladder cancer and 207 controls were enlisted regarding occupational and nonoccupational bladder cancer risk factors by questionnaire. The phase II enzymes N-acetyltransferase 2 (NAT2), glutathione S-transferases M1 (GSTM1), and T1 (GSTT1) and the single nucleotide polymorphism (SNP) rs11892031[A/C] reported to be associated with bladder cancer in genome-wide association studies were genotyped. The bladder cancer risk in varnishers and underground hard coal miners was increased as previously shown in a study in this area performed in the 1980s. The occupation of a car mechanic was associated with a significantly elevated bladder cancer risk and higher in the case of underground hard coal miners even though the mine was closed in 1987. The frequency of GSTM1 negative genotype was comparable in cases and controls (53% versus 54%). In the case of NAT2, the slow NAT2 genotype was more frequent (62% versus 58%) and ultra-slow NAT2 genotype (NAT2*6A and/or *7B alleles only) was 23% versus 15%. An occupational history of a varnisher or an underground hard coal miner remains a risk factor for bladder cancer occurrence. Data indicate that in the case of bladder cancer, GSTM1 is a susceptibility factor related to environmental and/or occupational exposure.