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.     

Leadership qualities emerging in an online social support group intervention

Technology-delivered interventions addressing a broad range of problems for which clients present for therapy are proliferating. However, little is known of leadership dynamics that emerge in online group interventions. The purpose of this study was to assess the types of leadership qualities that would emerge in an online social support group intervention to improve medication adherence for men with HIV, and to characterize the demographic and psychosocial profiles of leaders. Written posts (n = 616) from 66 men were coded using an adapted version of the Full Range Model of leadership. Results showed that 10% (n = 64) of posts reflected one of five leadership types, the most common of which was mentoring/providing feedback (40% of leadership posts). The next most common leadership style was instances in which encouragement was offered (30% of leadership posts). Leaders appeared to have lived with HIV longer and have higher Internet knowledge scores than non-leaders. Results indicate that online group interventions potentially may be useful to supplement traditional face-to-face treatment by providing an additional venue for group members to mentor and provide emotional support to each other. However, additional research is needed to more fully understand leadership qualities and group dynamics in other online group intervention settings.     

北京市社区老年人潜在不适当用药的调查分析

目的 调查北京市社区老年人潜在不适当用药(potentially inappropriate medication,PIM)现状.方法 采用自我报告方式,收集北京市社区215名老年人用药信息,根据2019版美国老年人PIM标准(Beers criteria for PIM use in older adults,Beers标准)和中国老年人潜在不适当用药判断标准(中国PIM标准)评价并做描述性分析.结果 根据2019版Beers标准发现66人(30.7%)存在84例次PIM,其中中枢神经系统药物(36例次)、血液系统药物(14例次)、内分泌系统药物(11例次)导致的PIM最多;采用中国PIM标准发现53人(24.7%)存在73例次PIM,前三位分别为:中枢神经系统药物(31例次),血液系统药物(17例次),解热、镇痛、抗炎与抗风湿药(17例次).结论 社区老年人PIM发生率较高,特别是中枢神经系统和血液系统用药需要引起关注.Beers标准和中国PIM标准可相互补充,且需不断更新完善.