利用常规实验室检查通过机器学习检测COVID-19
该研究基于1391例常规实验室数据(6项临床生化与14项血常规参数,以SARS-CoV-2 rRT-PCR为金标准),构建随机森林、XGBoost、支持向量机和逻辑回归四种算法的八种机器学习模型。所有模型准确度74%–91%,最佳模型在外部验证集上准确度91.18%、敏感度100%、特异度84.21%。作者认为机器学习模型可作为临床决策支持工具辅助COVID-19诊断。
要点
- 基于临床生化与血常规参数构建的机器学习模型可用于辅助COVID-19诊断。
- 随机森林模型在本研究数据集上准确度85.3%、敏感度79.6%、特异度91.2%。
- 支持向量机模型在外部验证集上准确度91.18%、敏感度100%、特异度84.21%。
核心结论
- 本研究的机器学习模型可作为临床决策支持工具,辅助医生对COVID-19的诊断判断。
研究设计与样本
- 使用1391例实验室数据构建机器学习模型,数据包括6项临床生化结果、14项血常规参数结果,并以SARS-CoV-2实时逆转录聚合酶链反应为金标准。
- 采用随机森林、梯度提升(XGBoost)、支持向量机和逻辑回归四种算法,基于血常规或临床生化联合血常规参数构建八种模型。
- 性能评估在本研究测试数据集和来自巴西的外部验证数据集上进行。
主要发现
- 所有模型的准确度范围为74%至91%。
- 基于临床生化与血常规参数训练的随机森林模型在本研究数据集上表现最佳(准确度85.3%;敏感度79.6%;特异度91.2%)。
- 仅基于血常规参数训练的随机森林模型检测COVID-19病例的准确度为82.8%。
- 在外部验证数据集上表现最佳的是基于临床生化与血常规参数训练的支持向量机模型(准确度91.18%;敏感度100%;特异度84.21%)。
临床怎么用
- 机器学习模型可利用常规临床生化与血常规检查结果辅助COVID-19诊断,作为医生临床判断的支持工具。
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
OBJECTIVES: The present study aimed to develop a clinical decision support tool to assist coronavirus disease 2019 (COVID-19) diagnoses with machine learning (ML) models using routine laboratory test results. METHODS: We developed ML models using laboratory data (n = 1,391) composed of six clinical chemistry (CC) results, 14 CBC parameter results, and results of a severe acute respiratory syndrome coronavirus 2 real-time reverse transcription-polymerase chain reaction as a gold standard method. Four ML algorithms, including random forest (RF), gradient boosting (XGBoost), support vector machine (SVM), and logistic regression, were used to build eight ML models using CBC and a combination of CC and CBC parameters. Performance evaluation was conducted on the test data set and external validation data set from Brazil. RESULTS: The accuracy values of all models ranged from 74% to 91%. The RF model trained from CC and CBC analytes showed the best performance on the present study's data set (accuracy, 85.3%; sensitivity, 79.6%; specificity, 91.2%). The RF model trained from only CBC parameters detected COVID-19 cases with 82.8% accuracy. The best performance on the external validation data set belonged to the SVM model trained from CC and CBC parameters (accuracy, 91.18%; sensitivity, 100%; specificity, 84.21%). CONCLUSIONS: ML models presented in this study can be used as clinical decision support tools to contribute to physicians' clinical judgment for COVID-19 diagnoses.
引用
- Çubukçu HC, Topcu Dİ, Bayraktar N, et al. Detection of COVID-19 by Machine Learning Using Routine Laboratory Tests. Am J Clin Pathol. 2022. PMID: 34791032. doi:10.1093/ajcp/aqab187
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。