EMR Adverse Drug Event Detection for Pharmacovigilance

用于药物警戒的 EMR 药物不良事件检测

基本信息

批准号：
9123554
负责人：
HONG YU
金额：
$ 33.7万
依托单位：
UNIV OF MASSACHUSETTS MED SCH WORCESTER
依托单位国家：
美国
项目类别：
财政年份：
2014
资助国家：
美国
起止时间：
2014-09-01 至 2017-08-31
项目状态：
已结题

来源：
https://reporter.nih.gov/project-details/9123554
关键词：
Adverse drug event Adverse event Algorithms Antineoplastic Agents Biology Boxing Cancer Center Cancer Research Network Cessation of life Clinical Clinical Oncology Clinical Trials Collaborations Common Terminology Criteria for Adverse Events Comprehensive Cancer Center Computerized Medical Record Data Detection Discipline of Nursing Disease Drug toxicity Elements Future Goals Health Promotion Hematology Hospitals Informatics Injury Inpatients Intervention Knowledge Language Lead Left Machine Learning Malignant Neoplasms Manuals Maps Marketing Massachusetts Medical Methods Monitor Morbidity - disease rate Names Natural Language Processing Outpatients Patients Pattern Pharmaceutical Preparations Pharmacoepidemiology Prevention Public Health Records Reporting Research Research Personnel Resources Risk Safety Severities Signal Transduction Structure System Terminology Testing Therapeutic Toxic effect United States United States Food and Drug Administration Universities Weight Work abstracting disorder prevention firewall improved innovation insight lenalidomide medical schools mortality novel oncology open source patient safety post-market public health relevance response tool

项目摘要

DESCRIPTION (provided by applicant): Adverse drug events (ADEs) result in substantial patient morbidity and lead to over 100,000 deaths yearly. The timely identification of previously unknown toxicities of cancer drugs is an important, unsolved problem. In the United States, 20% of the 548 drugs introduced into the market between 1975 and 1999 were either withdrawn or acquired a new "black box" warning during the 25-year period following initial approval by the Food and Drug Administration. Adverse drug events are an important cause of morbidity and mortality in patients, yet 95% of ADEs are unreported, leading to delays in the detection of previously unknown ADEs and underestimation of the risk to known ADEs. It is known that Electronic Medical Record (EMR), discharge summaries, and lab results contain ADE information and biomedical natural language processing (BioNLP) provides automated tools that facilitate chart review and thus improve patient surveillance and post-marketing pharmacovigilance. The objectives for this proposal are to develop "intelligent" BioNLP approaches to extract disease, medication, and structured ADE information from EMRs, and then evaluate extracted ADEs for detecting known ADE types as well as clinically unrecognized or novel ADEs whose pattern or effect have not been previously identified.

描述（由申请人提供）：药物不良事件 (ADE) 导致患者大量发病，每年导致超过 100,000 人死亡。及时识别癌症药物以前未知的毒性是一个重要的、尚未解决的问题。在美国，1975 年至 1999 年间引入市场的 548 种药物中，有 20% 在食品和药物管理局最初批准后的 25 年内被撤回或获得新的“黑匣子”警告。药物不良事件是患者发病和死亡的重要原因，但 95% 的 ADE 未报告，导致先前未知 ADE 检测的延迟以及对已知 ADE 风险的低估。众所周知，电子病历 (EMR)、出院摘要和实验室结果包含 ADE 信息，生物医学自然语言处理 (BioNLP) 提供自动化工具，促进图表审查，从而改善患者监测和上市后药物警戒。该提案的目标是开发“智能”BioNLP 方法，从 EMR 中提取疾病、药物和结构化 ADE 信息，然后评估提取的 ADE，以检测已知的 ADE 类型以及临床上未识别的或新颖的 ADE，其模式或效果尚未发现。之前已被识别。