Department of Medicine, Division of Hematology and Oncology, Vanderbilt University, Nashville, Tennessee, USA.
J Am Med Inform Assoc. 2013 Dec;20(e2):e281-7. doi: 10.1136/amiajnl-2013-001861. Epub 2013 Aug 1.
To develop methods for visual analysis of temporal phenotype data available through electronic health records (EHR).
24 580 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-acquired Clostridium 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.
Temporal 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.
Comprehensive 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.
The 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.
开发用于分析电子健康记录 (EHR) 中可用的时间表型数据的方法。
对来自多参数智能监护重症监护 V.6（MIMIC II）EHR 数据库的 24580 名危重病患者进行分析，通过将住院时间 (LOS) 与 ICD-9-CM 代码之间的关联映射可视化，来显示重要的时间关联。使用 ICD-9-CM、微生物学和计算机化医师医嘱输入数据定义了医院获得性艰难梭菌 (HA-CDI) 的扩展表型。与随机选择的对照相比，评估了 HA-CDI 病例的 LOS、估计成本、30 天出院后死亡率和前序药物提供者医嘱输入。
时间表型分析显示了 191 个显著代码（p 值，经错误发现率调整，≤0.05）。共发现 414 例 HA-CDI，与中位数 LOS 延长 20 天至 9 天相关，调整后的 HR 为 0.33（95%CI 0.28 至 0.39）。仅在美国，这一延长估计每年会增加 120 亿至 200 亿美元的增量成本。
全面的 EHR 数据使得大规模基于表型的分析成为可能。依赖时间的病理疾病状态具有动态表型演变，这可以通过视觉分析方法捕捉。尽管 MIMIC II 是一个单一机构的回顾性数据库，但我们的方法应该可以应用于其他 EHR 数据源，包括前瞻性“学习型医疗保健系统”。例如，可以使用相同的技术来动态评估预防 HA-CDI 的干预措施。
本文描述的新的视觉分析方法直接导致了对许多医院获得性疾病的识别，这些疾病可以通过扩展表型定义进一步探索。
