TY - JOUR AU - Chen, Jinying AU - Lalor, John AU - Liu, Weisong AU - Druhl, Emily AU - Granillo, Edgard AU - Vimalananda, Varsha G AU - Yu, Hong PY - 2019 DA - 2019/03/11 TI -检测患者安全信息中报告的低血糖事件:厂商使用学习和过采样,以减少数据不平衡乔- J地中海互联网Res SP - e11990六世- 21 - 3 KW -安全消息KW -自然语言处理KW -低血糖KW -监督机器学习KW -不平衡数据KW -不良事件检测KW -与毒品有关的副作用和不良反应AB -背景:药物如胰岛素剂量不当会导致低血糖发作,这可能会导致严重的发病率,甚至死亡。虽然安全消息是为交换非紧急消息而设计的，但患者有时会通过安全消息报告低血糖事件。检测这些患者报告的不良事件可能有助于提醒临床团队，并采取早期纠正措施，以提高患者的安全。目的:我们旨在开发一种名为Hypoglycemia Detector(低血糖检测器)的自然语言处理系统，以自动识别患者安全信息中报告的低血糖事件。方法:一位公共卫生专家对3000条糖尿病患者与美国退伍军人事务部临床团队之间的安全消息进行了注释，以确定是否包含患者报告的低血糖事件。一名医生从这个数据集中随机选择了100个线程进行独立注释，以确定注释者之间的一致性。我们使用这个数据集来开发和评估HypoDetect。HypoDetect结合了3种广泛用于文本分类的机器学习算法:线性支持向量机、随机森林和逻辑回归。我们探索了不同的学习特性，包括新的知识驱动特性。 Because only 114 (3.80%) messages were annotated as positive, we investigated cost-sensitive learning and oversampling methods to mitigate the challenge of imbalanced data. Results: The interannotator agreement was Cohen kappa=.976. Using cross-validation, logistic regression with cost-sensitive learning achieved the best performance (area under the receiver operating characteristic curve=0.954, sensitivity=0.693, specificity 0.974, F1 score=0.590). Cost-sensitive learning and the ensembled synthetic minority oversampling technique improved the sensitivity of the baseline systems substantially (by 0.123 to 0.728 absolute gains). Our results show that a variety of features contributed to the best performance of HypoDetect. Conclusions: Despite the challenge of data imbalance, HypoDetect achieved promising results for the task of detecting hypoglycemia incidents from secure messages. The system has a great potential to facilitate early detection and treatment of hypoglycemia. SN - 1438-8871 UR - //www.mybigtv.com/2019/3/e11990/ UR - https://doi.org/10.2196/11990 UR - http://www.ncbi.nlm.nih.gov/pubmed/30855231 DO - 10.2196/11990 ID - info:doi/10.2196/11990 ER -