论文标题
Embpred30：使用分类嵌入糖尿病患者评估30天的再入院
EmbPred30: Assessing 30-days Readmission for Diabetic Patients using Categorical Embeddings
论文作者
论文摘要
医院再入院是一种至关重要的医疗质量措施，有助于确定医院向患者提供的护理质量水平，并被证明非常昂贵。据估计，由于美国糖尿病患者的再入院，每年花费超过250亿美元。本文基准了现有的模型，并提出了一种新的基于嵌入式的最先进的深神经网络（DNN）。该模型可以在1999年至2008年之间从130家美国医院收集的数据中确定30天内的住院糖尿病患者是否在30天内进行了95.2％的及其在接收器操作特征（AUROC）下的区域的重新入院。结果令人鼓舞，因为患者患有药物变化，同时承认有很大的重新入院机会。识别潜在的患者进行再入院可以帮助医院系统改善其住院护理，从而使他们免于不必要的支出。
Hospital readmission is a crucial healthcare quality measure that helps in determining the level of quality of care that a hospital offers to a patient and has proven to be immensely expensive. It is estimated that more than $25 billion are spent yearly due to readmission of diabetic patients in the USA. This paper benchmarks existing models and proposes a new embedding based state-of-the-art deep neural network(DNN). The model can identify whether a hospitalized diabetic patient will be readmitted within 30 days or not with an accuracy of 95.2% and Area Under the Receiver Operating Characteristics(AUROC) of 97.4% on data collected from 130 US hospitals between 1999-2008. The results are encouraging with patients having changes in medication while admitted having a high chance of getting readmitted. Identifying prospective patients for readmission could help the hospital systems in improving their inpatient care, thereby saving them from unnecessary expenditures.
