Department of Trauma Surgery, University Hospital of Zurich, Ramistrasse 100, 8091, Zurich, Switzerland.
IBM Haifa University Campus, 3498825, Mount Carmel Haifa, Israel.
World J Surg. 2020 Mar;44(3):764-772. doi: 10.1007/s00268-019-05267-6.
Early physiological assessment of multiple injured patients is crucial for decision making and has relied on personal experience of trauma experts. We have developed a new visual analytics tool (Sankey diagram, Watson Trauma Health care tool) that includes known prognostic parameters for polytrauma patients to help guide assessment and treatment decisions for physicians involved in trauma care.
A prospectively collected trauma database of a single level I trauma center (3655 patients) was used.
age >16 years, an injury severity score (ISS) >16 and presence of a complete data set in the database. Data collected included admission values of patient age, injury scoring, shock classification, temperature, acid-base and hemostasis parameters. All of these parameters were collected daily as longitudinal parameters. Endpoints of the clinical course we considered were sepsis, SIRS and early in hospital mortality (<72 h). A proof of concept of the visualization was developed over a 2-year period in a cooperation between physicians and engineers. Statistically, the most predictive parameters were selected by binary logistic regression and ROC analysis.
A dynamic interactive multilayer Sankey diagram, based on cohort similarities, was developed in a collaboration between the University Hospital of Zurich, Department of Trauma and IBM, from August 2017 until January 2018. It is a modular tool and allows any user to add a new patient, or work with an existing case. The visualization used the data-driven documents (D3) interactive visualization library to create a responsive graphic.
This application summarizes the experience of 3655 polytrauma patients and might serve as a guide for clinical decisions and educative purposes, as well as new scientific questions for the polytrauma patient.
IV.
对多发伤患者进行早期生理评估对于决策至关重要，并且一直依赖于创伤专家的个人经验。我们开发了一种新的可视化分析工具（桑基图，Watson 创伤保健工具），其中包含了多发伤患者的已知预后参数，以帮助指导参与创伤护理的医生进行评估和治疗决策。
使用了一个单级 I 创伤中心的前瞻性收集的创伤数据库（3655 例患者）。
年龄＞16 岁，损伤严重程度评分（ISS）＞16 分，数据库中存在完整数据集。收集的数据包括患者年龄、损伤评分、休克分类、体温、酸碱和止血参数的入院值。所有这些参数都作为纵向参数每日采集。我们考虑的临床病程终点是感染、SIRS 和早期院内死亡率（＜72 小时）。该可视化工具的概念验证是在医生和工程师之间的合作下，经过 2 年的时间开发的。统计上，通过二元逻辑回归和 ROC 分析选择最具预测性的参数。
基于队列相似性，苏黎世大学医院创伤科和 IBM 之间合作开发了一个动态交互式多层桑基图，从 2017 年 8 月到 2018 年 1 月。这是一个模块化工具，允许任何用户添加新患者或处理现有病例。该可视化工具使用数据驱动文档（D3）交互式可视化库来创建响应式图形。
该应用程序总结了 3655 例多发伤患者的经验，可作为临床决策和教育目的的指南，以及多发伤患者的新科学问题。
IV。
