Readmission prediction using deep learning on electronic health records
Readmission prediction using deep learning on electronic health records
复制标题
DOI：
10.1016/j.jbi.2019.103256
复制
发表时间：
2019-09-01
影响因子：
4.5
通讯作者：
Nowaczyk, Slawomir
中科院分区：
文献类型：
--
作者：
Ashfaq, Awais;Sant'Anna, Anita;Nowaczyk, Slawomir
非计划性30天再入院是充血性心力衰竭（CHF）患者的一个标志，会带来重大的健康风险并增加护理成本。为了减少再入院和控制护理成本，重要的是要为有再入院风险的患者启动有针对性的干预计划。这需要在出院时识别高风险患者。在这里，使用2012年至2016年在瑞典住院的7500多名CHF患者的真实的数据，我们构建并测试了一个深度学习框架来预测30天的计划外再入院。我们使用专家特征和临床概念的上下文嵌入，提出了一种对成本敏感的长短期记忆（LSTM）神经网络。本研究针对电子健康记录（EHR）驱动的预测模型在一个单一的框架中的关键要素：使用专家和机器派生的功能，结合顺序模式和解决类不平衡问题。我们评估了每个元素对预测性能（ROC AUC，Fl测量）和成本节约的贡献。我们表明，具有所有关键元素的模型实现了更高的区分能力（AUC：0.77; FI：0.51;成本：最大可能节省的22%），在至少两个评估指标中优于简化模型。此外，我们提出了一个简单的财务分析，以估计每年节省，如果有针对性的干预措施提供给高风险患者。
Unscheduled 30-day readmissions are a hallmark of Congestive Heart Failure (CHF) patients that pose significant health risks and escalate care cost. In order to reduce readmissions and curb the cost of care, it is important to initiate targeted intervention programs for patients at risk of readmission. This requires identifying high-risk patients at the time of discharge from hospital. Here, using real data from over 7500 CHF patients hospitalized between 2012 and 2016 in Sweden, we built and tested a deep learning framework to predict 30-day unscheduled readmission. We present a cost-sensitive formulation of Long Short-Term Memory (LSTM) neural network using expert features and contextual embedding of clinical concepts. This study targets key elements of an Electronic Health Record (EHR) driven prediction model in a single framework: using both expert and machine derived features, incorporating sequential patterns and addressing the class imbalance problem. We evaluate the contribution of each element towards prediction performance (ROC-AUC, Fl-measure) and costsavings. We show that the model with all key elements achieves higher discrimination ability (AUC: 0.77; Fl: 0.51; Cost: 22% of maximum possible savings) outperforming the reduced models in at least two evaluation metrics. Additionally, we present a simple financial analysis to estimate annual savings if targeted interventions are offered to high risk patients.