Division of Digital Health Science, Department of Health Science Research, Mayo Clinic, Rochester, Minnesota.
The Robert D. and Patricia E. Kern Center for the Science of Health Care Delivery, Mayo Clinic, Rochester, Minnesota.
JAMA Netw Open. 2020 Jul 1;3(7):e208270. doi: 10.1001/jamanetworkopen.2020.8270.
Clinical domain knowledge about diseases and their comorbidities, severity, treatment pathways, and outcomes can facilitate diagnosis, enhance preventive strategies, and help create smart evidence-based practice guidelines.
To introduce a new representation of patient data called disease severity hierarchy that leverages domain knowledge in a nested fashion to create subpopulations that share increasing amounts of clinical details suitable for risk prediction.
DESIGN, SETTING, AND PARTICIPANTS: This retrospective cohort study included 51 969 patients aged 45 to 85 years, with 10 674 patients who received primary care at the Mayo Clinic between January 2004 and December 2015 in the training cohort and 41 295 patients who received primary care at Fairview Health Services from January 2010 to December 2017 in the validation cohort. Data were analyzed from May 2018 to December 2019.
Several binary classification measures, including the area under the receiver operating characteristic curve (AUC), Gini score, sensitivity, and positive predictive value, were used to evaluate models predicting all-cause mortality and major cardiovascular events at ages 60, 65, 75, and 80 years.
The mean (SD) age and proportions of women and white individuals were 59.4 (10.8) years, 6324 (59.3%) and 9804 (91.9%), respectively, in the training cohort and 57.4 (7.9) years, 21 975 (53.1%), and 37 653 (91.2%), respectively, in the validation cohort. During follow-up, 945 patients (8.9%) in the training cohort died, while 787 (7.4%) had major cardiovascular events. Models using the new representation achieved AUCs for predicting death in the training cohort at ages 60, 65, 75, and 80 years of 0.96 (95% CI, 0.94-0.97), 0.96 (95% CI, 0.95-0.98), 0.97 (95% CI, 0.96-0.98), and 0.98 (95% CI, 0.98-0.99), respectively, while standard methods achieved modest AUCs of 0.67 (95% CI, 0.55-0.80), 0.66 (95% CI, 0.56-0.79), 0.64 (95% CI, 0.57-0.71), and 0.63 (95% CI, 0.54-0.70), respectively.
In this study, the proposed patient data representation accurately predicted the age at which a patient was at risk of dying or developing major cardiovascular events substantially better than standard methods. The representation uses known relationships contained in electronic health records to capture disease severity in a natural and clinically meaningful way. Furthermore, it is expressive and interpretable. This novel patient representation can help to support critical decision-making, develop smart guidelines, and enhance health care and disease management by helping to identify patients with high risk.
关于疾病及其合并症、严重程度、治疗途径和结果的临床领域知识可以促进诊断，增强预防策略，并有助于创建智能循证实践指南。
介绍一种新的患者数据表示方法，称为疾病严重程度层次结构，该结构以嵌套方式利用领域知识来创建共享越来越多适合风险预测的临床详细信息的亚群。
设计、设置和参与者：这项回顾性队列研究包括 51969 名年龄在 45 至 85 岁之间的患者，其中 10674 名患者在 2004 年 1 月至 2015 年 12 月期间在梅奥诊所接受初级保健，41295 名患者在 2010 年 1 月至 2017 年 12 月期间在费尔维尤健康服务机构接受初级保健。数据分析于 2018 年 5 月至 2019 年 12 月进行。
使用几种二元分类测量方法，包括接受者操作特征曲线（AUC）下的面积、基尼分数、敏感性和阳性预测值，来评估预测所有原因死亡率和主要心血管事件的模型在 60、65、75 和 80 岁时的风险。
在训练队列中，患者的平均（标准差）年龄和女性及白人的比例分别为 59.4（10.8）岁、6324（59.3%）和 9804（91.9%），在验证队列中，患者的平均（标准差）年龄和女性及白人的比例分别为 57.4（7.9）岁、21975（53.1%）和 37653（91.2%）。在随访期间，训练队列中有 945 名患者（8.9%）死亡，787 名患者（7.4%）发生主要心血管事件。使用新表示方法的模型在训练队列中预测 60 岁、65 岁、75 岁和 80 岁时死亡的 AUC 分别为 0.96（95%CI，0.94-0.97）、0.96（95%CI，0.95-0.98）、0.97（95%CI，0.96-0.98）和 0.98（95%CI，0.98-0.99），而标准方法的 AUC 分别为 0.67（95%CI，0.55-0.80）、0.66（95%CI，0.56-0.79）、0.64（95%CI，0.57-0.71）和 0.63（95%CI，0.54-0.70）。
在这项研究中，与标准方法相比，所提出的患者数据表示方法能够更准确地预测患者处于风险状态的年龄，包括死亡或发生主要心血管事件的风险。该表示方法使用电子健康记录中包含的已知关系以自然且具有临床意义的方式捕获疾病严重程度。此外，它具有表现力和可解释性。这种新颖的患者表示方法可以帮助支持关键决策、制定智能指南，并通过帮助识别高风险患者来增强医疗保健和疾病管理。
