原发性全髋关节置换术价值指标术前预测及患者特异性支付模型的深度学习模型开发与验证
基于全国住院患者样本与本机构数据库的78,335例骨关节炎原发性全髋关节置换术病例,利用15个术前变量开发人工神经网络,预测住院时长、住院费用和出院去向。模型在住院时长、费用和出院去向的曲线下面积分别为82.0%、83.4%和79.4%,并据此建立按合并症复杂度分层支付的患者特异性支付模型。
要点
- 人工神经网络基于15个术前变量预测全髋关节置换术住院时长、费用和出院去向。
- 住院时长、费用和出院去向的曲线下面积分别为82.0%、83.4%和79.4%。
- 患者特异性支付模型对中度、重度、严重合并症分别设定2.5%、8.9%、17.3%的风险增加。
核心结论
- 深度学习人工神经网络在预测价值导向结局方面表现出「学习」能力,具有良好的可靠性、反应性和有效性。
- 该模型可用于实施基于病例复杂度的分层支付患者特异性支付模型。
研究设计与样本
- 使用来自全国住院患者样本与本机构数据库的78,335例骨关节炎原发性全髋关节置换术病例的15个术前变量开发人工神经网络。
- 模型预测住院时长、住院费用和出院去向,效度指标包括准确率和受试者工作特征曲线下面积。
- 按所有患者精细化合并症队列分层预测不确定性以建立患者特异性支付模型。
主要发现
- 动态模型在前30轮训练中表现出「学习」,住院时长、费用和出院去向的曲线下面积分别为82.0%、83.4%和79.4%。
- 提出的患者特异性支付模型对中度、重度、严重合并症分别确立2.5%、8.9%、17.3%的风险增加。
关键数值与推荐
- 住院时长预测的曲线下面积为82.0%。
- 住院费用预测的曲线下面积为83.4%。
- 出院去向预测的曲线下面积为79.4%。
- 患者特异性支付模型对中度合并症的风险增加为2.5%。
- 患者特异性支付模型对重度合并症的风险增加为8.9%。
临床怎么用
- 原文结论指出该模型可用于实施基于病例复杂度的分层支付患者特异性支付模型。
局限性
- 原文未报告局限性
以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。
原文
BACKGROUND: The primary objective was to develop and test an artificial neural network (ANN) that learns and predicts length of stay (LOS), inpatient charges, and discharge disposition for total hip arthroplasty. The secondary objective was to create a patient-specific payment model (PSPM) accounting for patient complexity. METHODS: Using 15 preoperative variables from 78,335 primary total hip arthroplasty cases for osteoarthritis from the National Inpatient Sample and our institutional database, an ANN was developed to predict LOS, charges, and disposition. Validity metrics included accuracy and area under the curve of the receiver operating characteristic curve. Predictive uncertainty was stratified by All Patient Refined comorbidity cohort to establish the PSPM. RESULTS: The dynamic model demonstrated "learning" in the first 30 training rounds with areas under the curve of 82.0%, 83.4%, and 79.4% for LOS, charges, and disposition, respectively. The proposed PSPM established a risk increase of 2.5%, 8.9%, and 17.3% for moderate, major, and severe comorbidities, respectively. CONCLUSION: The deep learning ANN demonstrated "learning" with good reliability, responsiveness, and validity in its prediction of value-centered outcomes. This model can be applied to implement a PSPM for tiered payments based on the complexity of the case.
引用
- Ramkumar PN, Karnuta JM, Navarro SM, et al. Preoperative Prediction of Value Metrics and a Patient-Specific Payment Model for Primary Total Hip Arthroplasty: Development and Validation of a Deep Learning Model. J Arthroplasty. 2019. PMID: 31122849. doi:10.1016/j.arth.2019.04.055
供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。