Ruksakulpiwat Suebsarn, Thongking Witchuda, Zhou Wendie, Benjasirisan Chitchanok, Phianhasin Lalipat, Schiltz Nicholas K, Brahmbhatt Smit
Department of Medical Nursing, Faculty of Nursing, 26685Mahidol University, Bangkoknoi, Bangkok, Thailand.
School of Engineering Science and Mechanics, 47745Shibaura Institute of Technology, Tokyo, Japan.
Chronic Illn. 2023 Mar;19(1):26-39. doi: 10.1177/17423953211067435. Epub 2021 Dec 13.
To evaluate the existing evidence of a machine learning-based classification system that stratifies patients with stroke.
The authors carried out a systematic review following the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) recommendations for a review article. PubMed, MEDLINE, Web of Science, and CINAHL Plus Full Text were searched from January 2015 to February 2021.
There are twelve studies included in this systematic review. Fifteen algorithms were used in the included studies. The most common forms of machine learning (ML) used to classify stroke patients were the support vector machine (SVM) (n = 8 studies), followed by random forest (RF) (n = 7 studies), decision tree (DT) (n = 4 studies), gradient boosting (GB) (n = 4 studies), neural networks (NNs) (n = 3 studies), deep learning (n = 2 studies), and k-nearest neighbor (k-NN) (n = 2 studies), respectively. Forty-four features of inputs were used in the included studies, and age and gender are the most common features in the ML model.
There is no single algorithm that performed better or worse than all others at classifying patients with stroke, in part because different input data require different algorithms to achieve optimal outcomes.
评估一种基于机器学习的对中风患者进行分层的分类系统的现有证据。
作者按照系统评价和Meta分析的首选报告项目（PRISMA）对综述文章的建议进行了系统评价。检索了2015年1月至2021年2月期间的PubMed、MEDLINE、Web of Science和CINAHL Plus全文数据库。
本系统评价纳入了12项研究。纳入研究中使用了15种算法。用于对中风患者进行分类的最常见机器学习形式是支持向量机（SVM）（8项研究），其次是随机森林（RF）（7项研究）、决策树（DT）（4项研究）、梯度提升（GB）（4项研究）、神经网络（NNs）（3项研究）、深度学习（2项研究）和k近邻（k-NN）（2项研究）。纳入研究中使用了44个输入特征，年龄和性别是机器学习模型中最常见的特征。
在对中风患者进行分类时，没有一种算法比其他算法表现得更好或更差，部分原因是不同的输入数据需要不同的算法来实现最佳结果。
