Abstract

Background The acute graft-versus-host disease (aGvHD) is the most important cause of mortality in patients receiving allogeneic hematopoietic stem cell transplantation. Given that it occurs at the stage of severe tissue damage, its diagnosis is late. With the advancement of machine learning (ML), promising real-time models to predict aGvHD have emerged.

Objective This article aims to synthesize the literature on ML classification algorithms for predicting aGvHD, highlighting algorithms and important predictor variables used.

Methods A systemic review of ML classification algorithms used to predict aGvHD was performed using a search of the PubMed, Embase, Web of Science, Scopus, Springer, and IEEE Xplore databases undertaken up to April 2019 based on Preferred Reporting Items for Systematic reviews and Meta-Analyses (PRISMA) statements. The studies with a focus on using the ML classification algorithms in the process of predicting of aGvHD were considered.

Results After applying the inclusion and exclusion criteria, 14 studies were selected for evaluation. The results of the current analysis showed that the algorithms used were Artificial Neural Network (79%), Support Vector Machine (50%), Naive Bayes (43%), k-Nearest Neighbors (29%), Regression (29%), and Decision Trees (14%), respectively. Also, many predictor variables have been used in these studies so that we have divided them into more abstract categories, including biomarkers, demographics, infections, clinical, genes, transplants, drugs, and other variables.

Conclusion Each of these ML algorithms has a particular characteristic and different proposed predictors. Therefore, it seems these ML algorithms have a high potential for predicting aGvHD if the process of modeling is performed correctly.

Authors' Contributions

All authors made significant contributions to the manuscript. CS developed the design of the systematic review and was involved in the data screening and extraction with FA, conducted the medical evaluation of the included studies, and wrote the manuscript. ARP and AK were involved in the medical assessment of the included studies. FA supervised and guided the project. ABH and ER categorized the biomarkers and variables that extracted from findings. All authors provided critical revision and approved the manuscript.

中文翻译：

---

遵循Allo-HSCT预测aGvHD的机器学习分类算法：系统综述。

摘要

背景 急性移植物抗宿主病（aGvHD）是接受异基因造血干细胞移植的患者死亡的最重要原因。由于它发生在严重的组织损伤阶段，因此其诊断为晚期。随着机器学习（ML）的发展，已经出现了有希望的实时模型来预测aGvHD。

目的 本文旨在综合有关用于预测aGvHD的ML分类算法的文献，重点介绍所使用的算法和重要的预测变量。

方法 根据对系统评价和Meta的首选报告项目，搜索了截至2019年4月进行的PubMed，Embase，Web of Science，Scopus，Springer和IEEE Xplore数据库，对用于预测aGvHD的ML分类算法进行了系统评价-分析（PRISMA）语句。考虑了侧重于在aGvHD预测过程中使用ML分类算法的研究。

结果 应用纳入和排除标准后，选择了14项研究进行评估。当前的分析结果表明，所使用的算法是：人工神经网络（79％），支持向量机（50％），朴素贝叶斯（43％），k最近邻（29％），回归（29％），和决策树（14％）。同样，在这些研究中使用了许多预测变量，因此我们将其划分为更抽象的类别，包括生物标记，人口统计学，感染，临床，基因，移植，药物和其他变量。

结论 这些ML算法中的每一种都有特定的特征和提出的不同预测变量。因此，如果建模过程正确执行，这些ML算法似乎具有预测aGvHD的巨大潜力。

作者的贡献

所有作者都对该手稿做出了重大贡献。CS开发了系统评价的设计，并参与了FA的数据筛选和提取，对纳入研究进行了医学评估，并撰写了手稿。ARP和AK参与了纳入研究的医学评估。FA负责并指导了该项目。ABH和ER对从发现中提取的生物标志物和变量进行了分类。所有作者都提供了重要的修订并批准了该手稿。