Lin Chaohsin, Hsu Shuofen, Lu Hsiao-Feng, Pan Li-Fei, Yan Yu-Hua
Department of Risk Management and Insurance, National Kaohsiung University of Science and Technology, Kaohsiung, Taiwan.
Department of Anesthesiology, Kaohsiung Chang Gung Memorial Hospital, Kaohsiung, Taiwan.
Risk Manag Healthc Policy. 2021 Sep 14;14:3853-3864. doi: 10.2147/RMHP.S318806. eCollection 2021.
The main purpose of this study is to predict the all-cause risk of 30-day readmission by employing the back-propagation neural network (BPNN) in comparison with traditional risk assessment tools of LACE index and HOSPITAL scores.
This was a retrospective cohort study from January 1st, 2018 to December 31st, 2019. A total of 55,688 hospitalizations from a medical center in Taiwan were examined. The LACE index (length of stay, acute admission, Charlson comorbidity index score, emergency department visits in previous 6 months) and HOSPITAL score (hemoglobin level at discharge, discharge from an Oncology service, sodium level at discharge, procedure during hospital stay, Index admission type, number of hospital admissions during the previous year, length of stay) are calculated. We employed variables from LACE index and HOSPITAL score as the input vector of BPNN for comparison purposes.
The BPNN constructed in the current study has a considerably better ability with a C statistics achieved 0.74 (95% CI 0.73 to 0.75), which is statistically significant larger than that of the other two models using DeLong's test. Also, it was possible to achieve higher sensitivity (70.32%) without penalizing the specificity (71.76%) and accuracy (71.68%) at its optimal threshold, which is at the 20% of patients with the highest predicted risk. Moreover, it is much more informative than the other two methods because of a considerably higher LR+ and a lower LR-.
Our findings suggest that more attention should be paid to methods based on non-linear classification systems, as they lead to substantial differences in risk-scores.
本研究的主要目的是通过运用反向传播神经网络（BPNN）预测30天再入院的全因风险，并与LACE指数和医院评分等传统风险评估工具进行比较。
这是一项回顾性队列研究，时间跨度为2018年1月1日至2019年12月31日。共检查了台湾一家医疗中心的55688例住院病例。计算LACE指数（住院时间、急性入院、查尔森合并症指数评分、前6个月急诊科就诊次数）和医院评分（出院时血红蛋白水平、肿瘤科出院、出院时钠水平、住院期间手术、首次入院类型、前一年住院次数、住院时间）。为了进行比较，我们将LACE指数和医院评分中的变量用作BPNN的输入向量。
本研究构建的BPNN具有相当好的能力，C统计量达到0.74（95%CI 0.73至0.75），使用德龙检验，该统计量显著大于其他两个模型。此外，在最佳阈值（即预测风险最高的20%患者）下，它能够在不影响特异性（71.76%）和准确性（71.68%）的情况下实现更高的敏感性（70.32%）。而且，由于其LR+相当高而LR-相当低，它比其他两种方法提供的信息更多。
我们的研究结果表明，应更多地关注基于非线性分类系统的方法，因为它们会导致风险评分存在实质性差异。
