基于电子健康记录系统数据的机器学习预测模型预测青光眼手术干预
本研究利用单家学术机构385例原发性开角型青光眼(POAG)患者的电子健康记录(EHR)结构化数据,构建多变量逻辑回归、随机森林和人工神经网络模型,采用留一交叉验证评估预测需手术干预的性能。多变量逻辑回归区分需手术的进展期患者最有效,AUC为0.67;较高的平均收缩压与需青光眼手术的比值比显著增加相关(OR=1.09,P<.001),多种药物类别与需手术比值比降低相关。结论认为EHR中现有系统数据在缺乏眼科特异性数据时对识别POAG进展至手术干预风险具有一定预测价值。
要点
- 多变量逻辑回归区分需手术的进展期POAG患者最有效,AUC为0.67。
- 较高的平均收缩压与需青光眼手术的比值比显著增加相关(OR=1.09,P<.001)。
- 眼科药物、非阿片类镇痛药、抗高脂血症药、大环内酯类抗生素和钙通道阻滞剂与需青光眼手术的比值比降低相关。
核心结论
- EHR中现有系统数据在缺乏眼科特异性数据时对识别POAG患者进展至手术干预的风险具有一定预测价值。
- 血压相关指标和某些药物类别可作为青光眼进展的预测因素。
- 该方法为未来在EHR中基于系统数据开发自动风险预测以辅助临床决策提供了机会。
研究设计与样本
- 研究为机器学习模型的开发与评估。
- 纳入单家学术机构385例POAG患者的EHR结构化数据。
- 使用多变量逻辑回归、随机森林和人工神经网络建模,并进行留一交叉验证。
- 计算平均受试者工作特征曲线下面积(AUC)、敏感度、特异度、准确度和约登指数评估模型性能。
主要发现
- 多变量逻辑回归区分需手术的进展期患者最有效,AUC为0.67。
- 较高的平均收缩压与需青光眼手术的比值比显著增加相关(OR=1.09,P<.001)。
- 眼科药物与需青光眼手术的比值比降低相关(OR=0.28,P<.001)。
- 非阿片类镇痛药与需青光眼手术的比值比降低相关(OR=0.21,P=.002)。
- 抗高脂血症药、大环内酯类抗生素和钙通道阻滞剂分别与需青光眼手术的比值比降低相关(OR=0.39,P=.004;OR=0.40,P=.03;OR=0.43,P=.03)。
临床怎么用
- 原文未据此给出推荐。
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
PURPOSE: To predict the need for surgical intervention in patients with primary open-angle glaucoma (POAG) using systemic data in electronic health records (EHRs). DESIGN: Development and evaluation of machine learning models. METHODS: Structured EHR data of 385 POAG patients from a single academic institution were incorporated into models using multivariable logistic regression, random forests, and artificial neural networks. Leave-one-out cross-validation was performed. Mean area under the receiver operating characteristic curve (AUC), sensitivity, specificity, accuracy, and Youden index were calculated for each model to evaluate performance. Systemic variables driving predictions were identified and interpreted. RESULTS: Multivariable logistic regression was most effective at discriminating patients with progressive disease requiring surgery, with an AUC of 0.67. Higher mean systolic blood pressure was associated with significantly increased odds of needing glaucoma surgery (odds ratio [OR] = 1.09, P < .001). Ophthalmic medications (OR = 0.28, P < .001), non-opioid analgesic medications (OR = 0.21, P = .002), anti-hyperlipidemic medications (OR = 0.39, P = .004), macrolide antibiotics (OR = 0.40, P = .03), and calcium blockers (OR = 0.43, P = .03) were associated with decreased odds of needing glaucoma surgery. CONCLUSIONS: Existing systemic data in the EHR has some predictive value in identifying POAG patients at risk of progression to surgical intervention, even in the absence of eye-specific data. Blood pressure-related metrics and certain medication classes emerged as predictors of glaucoma progression. This approach provides an opportunity for future development of automated risk prediction within the EHR based on systemic data to assist with clinical decision-making.
引用
- Baxter SL, Marks C, Kuo TT, et al. Machine Learning-Based Predictive Modeling of Surgical Intervention in Glaucoma Using Systemic Data From Electronic Health Records. Am J Ophthalmol. 2019. PMID: 31323204. doi:10.1016/j.ajo.2019.07.005
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。