To identify and contrast risk factors for six-month pediatric asthma readmissions using traditional models (Cox proportional-hazards and logistic regression) and artificial neural-network modeling. This retrospective cohort study of the 2013 Nationwide Readmissions Database included children 5 to 18 years old with a primary diagnosis of asthma. The primary outcome was time to asthma readmission in the Cox model, and readmission within 180 days in logistic regression. A basic neural network construction with 2 hidden layers and multiple replications considered all dataset variables and potential variable interactions to predict 180-day readmissions. Logistic regression and neural-network models were compared on area-under-the receiver-operating curve. Of 18,489 pediatric asthma hospitalizations, 1858 were readmitted within 180 days. In Cox and logistic models, longer index length of stay, public insurance, and nonwinter index admission seasons were associated with readmission risk, whereas micropolitan county was protective. In neural-network modeling, 9 factors were significantly associated with readmissions. Four overlapped with the Cox model (nonwinter-month admission, long length of stay, public insurance, and micropolitan hospitals), whereas 5 were unique (age, hospital bed number, teaching-hospital status, weekend index admission, and complex chronic conditions). The area under the curve was 0.592 for logistic regression and 0.637 for the neural network. Different methods can produce different readmission models. Relying on traditional modeling alone overlooks key readmission risk factors and complex factor interactions identified by neural networks.

中文翻译：

---

比较人工智能和传统方法来识别与小儿哮喘再入院相关的因素

使用传统模型（Cox 比例风险和逻辑回归）和人工神经网络模型来识别和对比六个月小儿哮喘再入院的风险因素。这项针对 2013 年全国再入院数据库的回顾性队列研究包括 5 至 18 岁初步诊断为哮喘的儿童。主要结局是 Cox 模型中哮喘再入院的时间，以及逻辑回归中 180 天内的再入院时间。具有 2 个隐藏层和多次重复的基本神经网络结构考虑了所有数据集变量和潜在变量相互作用，以预测 180 天的再入院率。在接受者操作曲线下面积上比较逻辑回归和神经网络模型。在 18,489 名因哮喘住院的儿童中，有 1858 人在 180 天内再次入院。在考克斯和逻辑模型中，较长的指数住院时间、公共保险和非冬季指数入院季节与再入院风险相关，而小城市县则具有保护作用。在神经网络模型中，有 9 个因素与再入院显着相关。其中 4 个与 Cox 模型重叠（非冬季入院、住院时间长、公共保险和小城市医院），而 5 个是独特的（年龄、医院床位数、教学医院状况、周末指数入院和复杂的慢性病） 。逻辑回归的曲线下面积为 0.592，神经网络的曲线下面积为 0.637。不同的方法可以产生不同的再入院模型。仅依靠传统模型会忽略神经网络识别的关键再入院风险因素和复杂因素相互作用。