Department of Health Services Research, Faculty of Medicine, University of Tsukuba, Tsukuba, Japan.
Health Services Research and Development Center, University of Tsukuba, Tsukuba, Japan.
Ann Med. 2022 Dec;54(1):2990-2997. doi: 10.1080/07853890.2022.2136402.
Undertriaged patients have worse outcomes than appropriately triaged patients. Machine learning provides better triage prediction than conventional triage in emergency departments, but no machine learning-based undertriage prediction models have yet been developed for prehospital telephone triage. We developed and validated machine learning models for telephone triage.
We conducted a retrospective cohort study with the largest after-hour house-call (AHHC) service dataset in Japan. Participants were ≥16 years and used the AHHC service between 1 November 2018 and 31 January 2021. We developed five prediction models based on support vector machine (SVM), lasso regression (LR), random forest (RF), gradient-boosted decision tree (XGB), and deep neural network (DNN). The primary outcome was undertriage, and predictors were telephone triage level and routinely available telephone-based data, including age, sex, 80 chief complaint categories and 10 comorbidities. We measured the area under the receiver operating characteristic curve (AUROC) for all the models.
We identified 15,442 eligible patients (age: 38.4 ± 16.6, male: 57.2%), including 298 (1.9%; age: 58.2 ± 23.9, male: 55.0%) undertriaged patients. RF and XGB outperformed the other models, with the AUROC values (95% confidence interval; 95% CI) of the SVM, LR, RF, XGB and DNN for undertriage being 0.62 (0.55-0.69), 0.79 (0.74-0.83), 0.81 (0.76-0.86), 0.80 (0.75-0.84) and 0.77 (0.73-0.82), respectively.
We found that RF and XGB outperformed other models. Our findings suggest that machine learning models can facilitate the early detection of undertriage and early intervention to yield substantially improved patient outcomes.KEY MESSAGESUndertriaged patients experience worse outcomes than appropriately triaged patients; thus, we developed machine learning models for predicting undertriage in the prehospital setting. In addition, we identified the predictors of risk factors associated with undertriage.Random forest and gradient-boosted decision tree models demonstrated better prediction performance, and the models identified the risk factors associated with undertriage.Machine learning models aid in the early detection of undertriage, leading to significantly improved patient outcomes and identifying undertriage-associated risk factors, including chief complaint categories, could help prioritize conventional telephone triage protocol revision.
与适当分诊的患者相比，分诊不足的患者预后更差。机器学习在急诊科提供的分诊预测比传统分诊更好，但尚未开发出用于院前电话分诊的基于机器学习的分诊不足预测模型。我们开发并验证了电话分诊的机器学习模型。
我们进行了一项回顾性队列研究，该研究使用了日本最大的下班后家庭就诊（AHHC）服务数据集。参与者年龄≥16 岁，并在 2018 年 11 月 1 日至 2021 年 1 月 31 日期间使用 AHHC 服务。我们基于支持向量机（SVM）、套索回归（LR）、随机森林（RF）、梯度提升决策树（XGB）和深度神经网络（DNN）开发了五个预测模型。主要结局为分诊不足，预测因子为电话分诊级别和常规的电话数据，包括年龄、性别、80 个主要投诉类别和 10 种合并症。我们测量了所有模型的接收者操作特征曲线下面积（AUROC）。
我们确定了 15442 名合格患者（年龄：38.4±16.6，男性：57.2%），包括 298 名（1.9%；年龄：58.2±23.9，男性：55.0%）分诊不足的患者。RF 和 XGB 优于其他模型，SVM、LR、RF、XGB 和 DNN 的 AUROC 值（95%置信区间；95%CI）分别为 0.62（0.55-0.69）、0.79（0.74-0.83）、0.81（0.76-0.86）、0.80（0.75-0.84）和 0.77（0.73-0.82）。
我们发现 RF 和 XGB 优于其他模型。我们的研究结果表明，机器学习模型可以帮助早期发现分诊不足，并进行早期干预，从而显著改善患者的预后。
分诊不足的患者比适当分诊的患者预后更差；因此，我们开发了用于院前环境中预测分诊不足的机器学习模型。此外，我们确定了与分诊不足相关的风险因素的预测因素。随机森林和梯度提升决策树模型表现出更好的预测性能，模型确定了与分诊不足相关的风险因素。机器学习模型有助于早期发现分诊不足，从而显著改善患者的预后，并确定与分诊不足相关的风险因素，包括主要投诉类别，有助于优先修订传统电话分诊方案。
