Yang Yujia, Tang Li, Deng Yiting, Li Xuzi, Luo Anling, Zhang Zhao, He Li, Zhu Cairong, Zhou Muke
Department of Neurology, West China Hospital, Sichuan University, Chengdu, Sichuan, China.
Department of Epidemiology and Health Statistics, West China School of Public Health and West China Fourth Hospital, Sichuan University, Chengdu, Sichuan, China.
Front Neurosci. 2023 Sep 7;17:1256592. doi: 10.3389/fnins.2023.1256592. eCollection 2023.
This study aimed to assess the accuracy of artificial intelligence (AI) models in predicting the prognosis of stroke.
We searched PubMed, Embase, and Web of Science databases to identify studies using AI for acute stroke prognosis prediction from the database inception to February 2023. Selected studies were designed cohorts and had complete data. We used the Quality Assessment of Diagnostic Accuracy Studies tool to assess the qualities and bias of included studies and used a random-effects model to summarize and analyze the data. We used the area under curve (AUC) as an indicator of the predictive accuracy of AI models.
We retrieved a total of 1,241 publications and finally included seven studies. There was a low risk of bias and no significant heterogeneity in the final seven studies. The total pooled AUC under the fixed-effects model was 0.872 with a 95% CI of (0.862-0.881). The DL subgroup showed its AUC of 0.888 (95%CI 0.872-0.904). The LR subgroup showed its AUC 0.852 (95%CI 0.835-0.869). The RF subgroup showed its AUC 0.863 (95%CI 0.845-0.882). The SVM subgroup showed its AUC 0.905 (95%CI 0.857-0.952). The Xgboost subgroup showed its AUC 0.905 (95%CI 0.805-1.000).
The accuracy of AI models in predicting the outcomes of ischemic stroke is good from our study. It could be an assisting tool for physicians in judging the outcomes of stroke patients. With the update of AI algorithms and the use of big data, further AI predictive models will perform better.
本研究旨在评估人工智能（AI）模型预测中风预后的准确性。
我们检索了PubMed、Embase和Web of Science数据库，以识别从数据库建立至2023年2月使用AI进行急性中风预后预测的研究。所选研究为设计队列研究且数据完整。我们使用诊断准确性研究质量评估工具来评估纳入研究的质量和偏倚，并使用随机效应模型对数据进行汇总和分析。我们使用曲线下面积（AUC）作为AI模型预测准确性的指标。
我们共检索到1241篇出版物，最终纳入7项研究。最终的7项研究存在低偏倚风险且无显著异质性。固定效应模型下的总合并AUC为0.872，95%置信区间为（0.862 - 0.881）。深度学习（DL）亚组的AUC为0.888（95%置信区间0.872 - 0.904）。逻辑回归（LR）亚组的AUC为0.852（95%置信区间0.835 - 0.869）。随机森林（RF）亚组的AUC为0.863（95%置信区间0.845 - 0.882）。支持向量机（SVM）亚组的AUC为0.905（95%置信区间0.857 - 0.952）。极端梯度提升（Xgboost）亚组的AUC为0.905（95%置信区间0.805 - 1.000）。
从我们的研究来看，AI模型预测缺血性中风预后的准确性良好。它可以作为医生判断中风患者预后的辅助工具。随着AI算法的更新和大数据的应用，进一步的AI预测模型将表现得更好。
