Temporal phenome analysis of a large electronic health record cohort enables identification of hospital-acquired complications.
Temporal phenome analysis of a large electronic health record cohort enables identification of hospital-acquired complications.
复制标题
对大型电子健康记录队列进行时间表型分析可以识别医院获得性并发症。
DOI：
10.1136/amiajnl-2013-001861
复制
发表时间：
2013
期刊：
影响因子：
--
通讯作者：
Alterovitz,Gil
中科院分区：
文献类型：
--
作者：
Warner,JeremyL;Zollanvari,Amin;Ding,Quan;Zhang,Peijin;Snyder,GrahamM;Alterovitz,Gil
目的建立电子健康档案（EHR）中时间表型数据的可视化分析方法。材料和方法对重症监护多参数智能监测V.6 （MIMIC II）重症患者EHR数据库中的24580名成人进行分析，以住院时间（LOS）与ICD-9-CM代码之间的关联图可视化显示显着的时间关联。利用ICD-9-CM、微生物学和计算机化医嘱输入数据，对医院获得的艰难梭菌（HA-CDI）进行了扩展表型的定义。与随机选择的对照组相比，评估HA-CDI病例的LOS、估计费用、出院后30天死亡率和先前的药物提供者订单输入。结果基因表型分析共发现191个显著编码（p值，经假发现率调整，p值≤0.05）。414例患者中发现HA-CDI，与较长的中位LOS（20天vs 9天）相关，调整后危险度为0.33 （95% CI 0.28 ~ 0.39）。据估计，仅在美国，这种延长每年就会带来12 - 20亿美元的增量成本增加。全面的电子病历数据使大规模的基于现象的分析成为可能。时间依赖的病理疾病状态具有动态的现象进化，这可以通过视觉分析方法捕获。虽然MIMIC II是一个单一的机构回顾性数据库，但我们的方法应该可移植到其他电子病历数据源，包括前瞻性的“学习型医疗保健系统”。例如，预防HA-CDI的干预措施可以使用相同的技术进行动态评估。结论本文中描述的新的视觉分析方法直接导致了许多医院获得性疾病的识别，这些疾病可以通过扩展的表型定义进一步探索。
ObjectiveTo develop methods for visual analysis of temporal phenotype data available through electronic health records (EHR).Materials and methods24 580 adults from the multiparameter intelligent monitoring in intensive care V.6 (MIMIC II) EHR database of critically ill patients were analyzed, with significant temporal associations visualized as a map of associations between hospital length of stay (LOS) and ICD-9-CM codes. An expanded phenotype, using ICD-9-CM, microbiology, and computerized physician order entry data, was defined for hospital-acquiredClostridium difficile(HA-CDI). LOS, estimated costs, 30-day post-discharge mortality, and antecedent medication provider order entry were evaluated for HA-CDI cases compared to randomly selected controls.ResultsTemporal phenome analysis revealed 191 significant codes (p value, adjusted for false discovery rate, ≤0.05). HA-CDI was identified in 414 cases, and was associated with longer median LOS, 20 versus 9 days, and adjusted HR 0.33 (95% CI 0.28 to 0.39). This prolongation carries an estimated annual incremental cost increase of US$1.2–2.0 billion in the USA alone.DiscussionComprehensive EHR data have made large-scale phenome-based analysis feasible. Time-dependent pathological disease states have dynamic phenomic evolution, which may be captured through visual analytical approaches. Although MIMIC II is a single institutional retrospective database, our approach should be portable to other EHR data sources, including prospective ‘learning healthcare systems’. For example, interventions to prevent HA-CDI could be dynamically evaluated using the same techniques.ConclusionsThe new visual analytical method described in this paper led directly to the identification of numerous hospital-acquired conditions, which could be further explored through an expanded phenotype definition.