Prediction of tumor lysis syndrome in childhood acute lymphoblastic leukemia based on machine learning models: a retrospective study

Yao Xiao; Li Xiao; Yang Zhang; Ximing Xu; Xianmin Guan; Yuxia Guo; Yali Shen; XiaoYing Lei; Ying Dou; Jie Yu

doi:10.3389/fonc.2024.1337295

Prediction of tumor lysis syndrome in childhood acute lymphoblastic leukemia based on machine learning models: a retrospective study

Front Oncol. 2024 Mar 7:14:1337295. doi: 10.3389/fonc.2024.1337295. eCollection 2024.

Authors

Yao Xiao¹, Li Xiao¹, Yang Zhang², Ximing Xu³, Xianmin Guan¹, Yuxia Guo¹, Yali Shen¹, XiaoYing Lei¹, Ying Dou¹, Jie Yu¹

Affiliations

¹ Department of Hematology and Oncology, Children's Hospital of Chongqing Medical University, National Clinical Research Center for Child Health and Disorders, Chongqing Key Laboratory of Pediatrics, Ministry of Education Key Laboratory of Child Development and Disorders, Chongqing, China.
² College of Medical Informatics, Chongqing Medical University, Chongqing, China.
³ Big Data Engineering Center for Children's Medical Care, Children's Hospital of Chongqing Medical University, Chongqing, China.

Abstract

Background: Tumor lysis syndrome (TLS) often occurs early after induction chemotherapy for acute lymphoblastic leukemia (ALL) and can rapidly progress. This study aimed to construct a machine learning model to predict the risk of TLS using clinical indicators at the time of ALL diagnosis.

Methods: This observational cohort study was conducted at the National Clinical Research Center for Child Health and Disease. Data were collected from pediatric ALL patients diagnosed between December 2008 and December 2021. Four machine learning models were constructed using the Least Absolute Shrinkage and Selection Operator (LASSO) to select key clinical indicators for model construction.

Results: The study included 2,243 pediatric ALL patients, and the occurrence of TLS was 8.87%. A total of 33 indicators with missing values ≤30% were collected, and 12 risk factors were selected through LASSO regression analysis. The CatBoost model with the best performance after feature screening was selected to predict the TLS of ALL patients. The CatBoost model had an AUC of 0.832 and an accuracy of 0.758. The risk factors most associated with TLS were the absence of potassium, phosphorus, aspartate transaminase (AST), white blood cell count (WBC), and urea levels.

Conclusion: We developed the first TLS prediction model for pediatric ALL to assist clinicians in risk stratification at diagnosis and in developing personalized treatment protocols. This study is registered on the China Clinical Trials Registry platform (ChiCTR2200060616).

Clinical trial registration: https://www.chictr.org.cn/, identifier ChiCTR2200060616.

Keywords: acute lymphoblastic leukemia; machine learning; predictive modeling; treatment toxicity; tumor lysis syndrome.

Grants and funding

The author(s) declare financial support was received for theresearch, authorship, and/or publication of this article. This work was supported by the Intelligence Medicine Project of Chongqing Medical University (YJSZHYX202103), the personalized treatment strategy based on individualized therapy to guide the diagnosis and treatment of relapsed acute lymphoblastic leukemia in children of Children’s Hospital of Chongqing Medical University (LY02026), and Multicenter randomized controlled clinical trial comparing dexamethasone and prednisone in induced remission in children with intermediate- and high-risk acute lymphoblastic leukemia of Children’s Hospital of Chongqing Medical University (LY03006).