Inclusion of social determinants of health improves sepsis readmission prediction models.
Inclusion of social determinants of health improves sepsis readmission prediction models.
复制标题
纳入健康的社会决定因素改善了脓毒症再入院预测模型。
DOI：
10.1093/jamia/ocac060
复制
发表时间：
2022
期刊：
影响因子：
--
通讯作者：
Wardi,Gabriel
中科院分区：
文献类型：
--
作者：
Amrollahi,Fatemeh;Shashikumar,SupreethP;Meier,Angela;Ohno-Machado,Lucila;Nemati,Shamim;Wardi,Gabriel
目的脓毒症 30 天非计划再入院率很高。预测模型被建议作为识别高风险患者的工具。然而，现有的脓毒症再入院模型的预测价值较低，并且此类模型中的大多数预测因素不具有可操作性。材料和方法来自 35 家医院的 AllofUs 研究计划队列中的患者的数据被用来开发多中心验证的脓毒症相关非计划再入院模型，该模型结合了健康的临床和社会决定因素 (SDH)，以预测 30 天的非计划再入院。脓毒症病例是使用观察性医疗结果合作伙伴关系中代表的概念来识别的。该数据集包括超过 60 个临床/实验室特征和超过 100 个 SDH 特征。结果将 SDH 因素纳入我们的临床和人口特征模型中，显着改善了受试者工作特征曲线 (AUC) 下的模型面积（从 0.75 到 0.80；P< .001）。与模型无关的可解释性技术揭示了人口统计、经济稳定性和获得医疗护理的延迟是计划外再入院的重要 SDH 预测特征。 讨论 这项工作代表了迄今为止使用客观临床数据（8935 例败血症指数遭遇）对败血症再入院进行的最大规模的研究之一。 SDH 对于确定哪些脓毒症患者更有可能出现 30 天计划外再入院非常重要。 AllofUS 数据集提供了来自不同个体的精细数据，使得该模型比之前的模型更具通用性。 结论 使用 SDH 可以提高模型的预测性能，以识别哪些脓毒症患者面临 30 天计划外再入院的高风险。
ObjectiveSepsis has a high rate of 30-day unplanned readmissions. Predictive modeling has been suggested as a tool to identify high-risk patients. However, existing sepsis readmission models have low predictive value and most predictive factors in such models are not actionable.Materials and MethodsData from patients enrolled in the AllofUs Research Program cohort from 35 hospitals were used to develop a multicenter validated sepsis-related unplanned readmission model that incorporates clinical and social determinants of health (SDH) to predict 30-day unplanned readmissions. Sepsis cases were identified using concepts represented in the Observational Medical Outcomes Partnership. The dataset included over 60 clinical/laboratory features and over 100 SDH features.ResultsIncorporation of SDH factors into our model of clinical and demographic features improves model area under the receiver operating characteristic curve (AUC) significantly (from 0.75 to 0.80;P< .001). Model-agnostic interpretability techniques revealed demographics, economic stability, and delay in getting medical care as important SDH predictive features of unplanned hospital readmissions.DiscussionThis work represents one of the largest studies of sepsis readmissions using objective clinical data to date (8935 septic index encounters). SDH are important to determine which sepsis patients are more likely to have an unplanned 30-day readmission. The AllofUS dataset provides granular data from a diverse set of individuals, making this model potentially more generalizable than prior models.ConclusionUse of SDH improves predictive performance of a model to identify which sepsis patients are at high risk of an unplanned 30-day readmission.