Identification of key predictors of acute GVHD in pediatric acute Leukemia using machine learning methods

IF 1.6 4区医学 Q4 IMMUNOLOGY

Transplant immunology Pub Date : 2025-12-01 Epub Date: 2025-10-20 DOI:10.1016/j.trim.2025.102318

İlknur Buçan Kırkbir , Hacer Kobya Bulut

{"title":"Identification of key predictors of acute GVHD in pediatric acute Leukemia using machine learning methods","authors":"İlknur Buçan Kırkbir , Hacer Kobya Bulut","doi":"10.1016/j.trim.2025.102318","DOIUrl":null,"url":null,"abstract":"<div><h3>Backround</h3><div>Hematopoietic stem cell transplantation (HSCT) is a crucial treatment for leukemia. Allogeneic Hematopoietic cell transplantation (HCT), in which stem cells from a healthy donor are used, carries significant risks, including graft versus host disease (GVHD), a severe complication that leads to high morbidity and mortality. This study aimed to identify significant predictors of acute GVHD (aGVHD) in pediatric patients with acute lymphoblastic leukemia (ALL) and acute myeloid leukemia (AML).</div></div><div><h3>Methods</h3><div>This retrospective study analyzed the predictors of aGVHD in pediatric patients using different machine learning methods: Random Forest (RF), Logistic Regression (LR), and Boruta. The dataset was obtained from the UCI machine learning open-source database, and after balancing the class distribution of the dependent variable aGVHD using the Synthetic Minority Oversampling Technique (SMOTE), a total of 124 pediatric patients, including demographic and clinical variables, were analyzed using the R open-source programming language.</div></div><div><h3>Results</h3><div>Significant differences were observed between the aGVHD and non-aGVHD groups in recipient age (<em>p</em> = 0.002), recipient weight (<em>p</em> = 0.02), donor age (<em>p</em> = 0.01), allele mismatch (<em>p</em> = 0.01), antigen mismatch (<em>p</em> = 0.01), and recipient CMV status (<em>p</em> = 0.04). Feature importance analyses using Random Forest (RF) and Boruta identified recipient age, weight, and donor age as the most influential predictors of aGVHD. Logistic Regression (LR) highlighted recipient Rh-positive status and donor blood group B as additional relevant factors, offering a complementary perspective. These findings may assist in risk assessment and the development of preventive strategies for aGVHD.</div></div><div><h3>Conclusion</h3><div>Machine learning methods effectively identified important predictors of aGVHD, demonstrating their potential to improve post-HCT care and preventive protocols. Our results underscore the complex aGVHD etiology, suggesting the involvement of various factors in its development. Further studies should focus on integrating these findings into the clinical practice to enhance patient outcomes.</div></div>","PeriodicalId":23304,"journal":{"name":"Transplant immunology","volume":"93 ","pages":"Article 102318"},"PeriodicalIF":1.6000,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Transplant immunology","FirstCategoryId":"3","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0966327425001467","RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"2025/10/20 0:00:00","PubModel":"Epub","JCR":"Q4","JCRName":"IMMUNOLOGY","Score":null,"Total":0}

引用次数: 0

Abstract

Backround

Hematopoietic stem cell transplantation (HSCT) is a crucial treatment for leukemia. Allogeneic Hematopoietic cell transplantation (HCT), in which stem cells from a healthy donor are used, carries significant risks, including graft versus host disease (GVHD), a severe complication that leads to high morbidity and mortality. This study aimed to identify significant predictors of acute GVHD (aGVHD) in pediatric patients with acute lymphoblastic leukemia (ALL) and acute myeloid leukemia (AML).

Methods

This retrospective study analyzed the predictors of aGVHD in pediatric patients using different machine learning methods: Random Forest (RF), Logistic Regression (LR), and Boruta. The dataset was obtained from the UCI machine learning open-source database, and after balancing the class distribution of the dependent variable aGVHD using the Synthetic Minority Oversampling Technique (SMOTE), a total of 124 pediatric patients, including demographic and clinical variables, were analyzed using the R open-source programming language.

Results

Significant differences were observed between the aGVHD and non-aGVHD groups in recipient age (p = 0.002), recipient weight (p = 0.02), donor age (p = 0.01), allele mismatch (p = 0.01), antigen mismatch (p = 0.01), and recipient CMV status (p = 0.04). Feature importance analyses using Random Forest (RF) and Boruta identified recipient age, weight, and donor age as the most influential predictors of aGVHD. Logistic Regression (LR) highlighted recipient Rh-positive status and donor blood group B as additional relevant factors, offering a complementary perspective. These findings may assist in risk assessment and the development of preventive strategies for aGVHD.

Conclusion

Machine learning methods effectively identified important predictors of aGVHD, demonstrating their potential to improve post-HCT care and preventive protocols. Our results underscore the complex aGVHD etiology, suggesting the involvement of various factors in its development. Further studies should focus on integrating these findings into the clinical practice to enhance patient outcomes.

Abstract Image

查看原文本刊更多论文

使用机器学习方法识别儿童急性白血病急性GVHD的关键预测因素。

背景：造血干细胞移植（HSCT）是治疗白血病的重要手段。同种异体造血细胞移植（HCT）使用来自健康供体的干细胞，具有重大风险，包括移植物抗宿主病（GVHD），这是一种导致高发病率和死亡率的严重并发症。本研究旨在确定急性淋巴细胞白血病（ALL）和急性髓系白血病（AML）患儿急性GVHD （aGVHD）的重要预测因素。方法：采用随机森林（Random Forest， RF）、Logistic回归（Logistic Regression， LR）和Boruta等不同的机器学习方法，对儿童aGVHD的预测因素进行回顾性分析。数据集来自UCI机器学习开源数据库，使用合成少数过采样技术（Synthetic Minority Oversampling Technique， SMOTE）平衡因变量aGVHD的类分布后，使用R开源编程语言对124例儿童患者进行分析，包括人口统计学和临床变量。结果:显著差异观察aGVHD和接受者non-aGVHD团体之间的年龄(p = 0.002),收件人体重(p = 0.02),供体年龄(p = 0.01),等位基因不匹配(p = 0.01),抗原不匹配(p = 0.01),和收件人巨细胞病毒状态(p = 0.04)。使用随机森林（RF）和Boruta进行特征重要性分析，确定受体年龄、体重和供体年龄是aGVHD最具影响力的预测因素。Logistic回归（LR）强调受体rh阳性状态和献血者B血型是额外的相关因素，提供了互补的视角。这些发现可能有助于aGVHD的风险评估和预防策略的制定。结论：机器学习方法有效地识别了aGVHD的重要预测因素，展示了它们改善hct后护理和预防方案的潜力。我们的研究结果强调了复杂的aGVHD病因学，表明其发展涉及多种因素。进一步的研究应侧重于将这些发现整合到临床实践中，以提高患者的预后。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

Transplant immunology 医学-免疫学

CiteScore

2.10

自引率

13.30%

发文量

198

审稿时长

48 days

期刊介绍： Transplant Immunology will publish up-to-date information on all aspects of the broad field it encompasses. The journal will be directed at (basic) scientists, tissue typers, transplant physicians and surgeons, and research and data on all immunological aspects of organ-, tissue- and (haematopoietic) stem cell transplantation are of potential interest to the readers of Transplant Immunology. Original papers, Review articles and Hypotheses will be considered for publication and submitted manuscripts will be rapidly peer-reviewed and published. They will be judged on the basis of scientific merit, originality, timeliness and quality.