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.     

Immediate effects of real-time postural biofeedback on spinal posture,muscle activity,and perceived pain severity in adults with neck pain

BackgroundPrevious studies have investigated various types of postural biofeedback devices on different body regions to improve posture; however, they focused only on healthy adults without a history of chronic musculoskeletal disorders. In addition, those postural biofeedback devices used in previous studies are often designed for experimental research. The designs are usually bulky with many wires, which is not practical for everyday use.Research questionThe aim of this study was to determine the immediate effect of a commercially available real-time postural biofeedback device on spinal posture, muscle activity, and perceived pain severity in adults with neck pain.Methods21 adults who had chronic or recurrent nonspecific neck pain for more than 3 months and whose pain was induced or aggravated by prolonged computer work were enrolled in this study. Spinal posture (head tilt, neck flexion, cervical and thoracic angles), muscle activity (cervical erector spinae, upper trapezius, and thoracic erector spinae), and self-reported neck and shoulder pain were measured during computer typing tasks, with and without biofeedback.ResultsCompared with the non-biofeedback condition, the biofeedback condition significantly decreased neck flexion, upper cervical, and lower thoracic angles and lowered the activity of the cervical erector spinae. Self-reported neck pain was not influenced by the application of biofeedback, but significantly increased over the 1-hour typing task.SignificanceThe application of a commercially available wearable real-time biofeedback device improves sitting posture and reduces muscular activity in adults with nonspecific neck pain during computer work. Future studies should examine the long-term effects of wearable real-time postural biofeedback devices for prevention and management of neck pain.     

伤口评估卡片联合电子照片在老年科护士伤口专科知识培训中的应用

[目的]探讨伤口评估卡片联合电子照片在老年科护士伤口专科知识培训中的应用效果。[方法]按照随机数字表法将老年科60名护士分为观察组和对照组各30例,对照组采用电子照片对护士伤口专科知识进行培训和指导,观察组采用自制伤口评估卡片联合电子照片对护士伤口专科知识进行培训和指导。比较两组护士伤口专科知识的掌握程度、护士记录伤口病人护理文书的记录质量及护士对伤口病人伤口转归的护理管理能力。[结果]观察组护士伤口专科知识的掌握程度、护士记录伤口病人护理文书的记录质量及护士对伤口病人伤口转归的护理管理能力均优于对照组(P<0.05)。[结论]在老年科护士伤口专科知识培训中应用伤口评估卡片联合电子照片效果显著。     

An assessment of weight change associated with the initiation of a protease or integrase strand transfer inhibitor in patients with human immunodeficiency virus

Abstract

Objective

Evidence suggests that integrase strand transfer inhibitors (INSTIs) are associated with greater weight gain than other antiretrovirals. This real-world study compares weight/body mass index (BMI) change between insured US patients with human immunodeficiency virus (HIV-1) initiating a protease inhibitor (PI) or INSTI.     

Functional evaluation of out-of-the-box text-mining tools for data-mining tasks

Objective The trade-off between the speed and simplicity of dictionary-based term recognition and the richer linguistic information provided by more advanced natural language processing (NLP) is an area of active discussion in clinical informatics. In this paper, we quantify this trade-off among text processing systems that make different trade-offs between speed and linguistic understanding. We tested both types of systems in three clinical research tasks: phase IV safety profiling of a drug, learning adverse drug–drug interactions, and learning used-to-treat relationships between drugs and indications.Materials We first benchmarked the accuracy of the NCBO Annotator and REVEAL in a manually annotated, publically available dataset from the 2008 i2b2 Obesity Challenge. We then applied the NCBO Annotator and REVEAL to 9 million clinical notes from the Stanford Translational Research Integrated Database Environment (STRIDE) and used the resulting data for three research tasks.Results There is no significant difference between using the NCBO Annotator and REVEAL in the results of the three research tasks when using large datasets. In one subtask, REVEAL achieved higher sensitivity with smaller datasets.Conclusions For a variety of tasks, employing simple term recognition methods instead of advanced NLP methods results in little or no impact on accuracy when using large datasets. Simpler dictionary-based methods have the advantage of scaling well to very large datasets. Promoting the use of simple, dictionary-based methods for population level analyses can advance adoption of NLP in practice.     

Cardiac Implantable Electronic Devices in Patients With Left Ventricular Assist Systems

Recent progress and evolution in device engineering, surgical implantation practices, and periprocedural management have advanced the promise of durable support with left ventricular assist systems (LVAS) in patients with stage D heart failure. With greater uptake of LVAS globally, a growing population of LVAS recipients have pre-existing cardiac implantable electronic devices (CIEDs). Strategies for optimal clinical management of CIEDs in patients with durable LVAS are evolving, and clinicians will increasingly face complex decisions regarding implantation, programming, deactivation, and removal of CIEDs. Traditional decision-making pathways for CIEDs may not apply to LVAS-supported patients, as few patients die of arrhythmic causes and many arrhythmias may be well tolerated. Given limited data, treatment decisions must be individualized and made collaboratively among electrophysiologists, advanced heart failure specialists, and patients and their caregivers. Large, prospective, well-conducted studies are needed to better understand the contemporary utility of CIEDs in patients with newer-generation LVAS.