Industrial Engineering Department, Federal University of Rio Grande do Sul, Av. Osvaldo Aranha 55, Porto Alegre, RS, Brazil.
BMC Emerg Med. 2024 Nov 18;24(1):219. doi: 10.1186/s12873-024-01135-2.
In Emergency Departments (EDs), triage is crucial for determining patient severity and prioritizing care, typically using the Manchester Triage Scale (MTS). Traditional triage systems, reliant on human judgment, are prone to under-triage and over-triage, resulting in variability, bias, and incorrect patient classification. Studies suggest that Machine Learning (ML) and Natural Language Processing (NLP) could enhance triage accuracy and consistency. This review analyzes studies on ML and/or NLP algorithms for ED patient triage.
Following Preferred Reporting Items for Systematic Review and Meta-Analysis (PRISMA) guidelines, we conducted a systematic review across five databases: Web of Science, PubMed, Scopus, IEEE Xplore, and ACM Digital Library, from their inception of each database to October 2023. The risk of bias was assessed using the Prediction model Risk of Bias Assessment Tool (PROBAST). Only articles employing at least one ML and/or NLP method for patient triage classification were included.
Sixty studies covering 57 ML algorithms were included. Logistic Regression (LR) was the most used model, while eXtreme Gradient Boosting (XGBoost), decision tree-based algorithms with Gradient Boosting (GB), and Deep Neural Networks (DNNs) showed superior performance. Frequent predictive variables included demographics and vital signs, with oxygen saturation, chief complaints, systolic blood pressure, age, and mode of arrival being the most retained. The ML algorithms showed significant bias risk due to critical bias assessment in classification models.
NLP methods improved ML algorithms' classification capability using triage nursing and medical notes and structured clinical data compared to algorithms using only structured data. Feature engineering (FE) and class imbalance correction methods enhanced ML workflows' performance, but FE and eXplainable Artificial Intelligence (XAI) were underexplored in this field. Registration and funding. This systematic review has been registered (registration number: CRD42024604529) in the International Prospective Register of Systematic Reviews (PROSPERO) and can be accessed online at the following URL: https://www.crd.york.ac.uk/prospero/display_record.php?RecordID=604529 . Funding for this work was provided by the National Council for Scientific and Technological Development (CNPq), Brazil.
在急诊科（ED）中，分诊对于确定患者的严重程度和优先治疗至关重要，通常使用曼彻斯特分诊量表（MTS）。传统的分诊系统依赖于人为判断，容易导致分诊不足和过度分诊，从而导致变异性、偏差和不正确的患者分类。研究表明，机器学习（ML）和自然语言处理（NLP）可以提高分诊的准确性和一致性。本综述分析了用于 ED 患者分诊的 ML 和/或 NLP 算法的研究。
根据系统评价和荟萃分析的首选报告项目（PRISMA）指南，我们在五个数据库中进行了系统综述：Web of Science、PubMed、Scopus、IEEE Xplore 和 ACM 数字图书馆，从每个数据库的创建到 2023 年 10 月。使用预测模型风险偏倚评估工具（PROBAST）评估偏倚风险。仅纳入至少使用一种 ML 和/或 NLP 方法进行患者分诊分类的文章。
共有 60 项研究涵盖了 57 种 ML 算法。逻辑回归（LR）是最常用的模型，而极端梯度增强（XGBoost）、基于梯度增强的决策树算法（GB）和深度神经网络（DNN）表现出更好的性能。常用的预测变量包括人口统计学和生命体征，其中血氧饱和度、主要投诉、收缩压、年龄和到达方式是保留最多的变量。由于分类模型的关键偏差评估，ML 算法存在显著的偏差风险。
与仅使用结构化数据的算法相比，使用分诊护理和医疗记录以及结构化临床数据的 NLP 方法提高了 ML 算法的分类能力。特征工程（FE）和类别不平衡校正方法增强了 ML 工作流程的性能，但在该领域，FE 和可解释人工智能（XAI）的应用还不够广泛。注册和资助。本系统评价已在国际前瞻性系统评价注册库（PROSPERO）中注册（注册号：CRD42024604529），可在线访问以下网址：https://www.crd.york.ac.uk/prospero/display_record.php?RecordID=604529。本工作的资金由巴西国家科学技术发展委员会（CNPq）提供。
