Machine learning based on multiplatform tests assists in subtype classification of mature B‐cell neoplasms
British Journal of Haematology · 2025
DOI: 10.1111/bjh.19934 ↗Kurz gefasst
Validierungsstudie in der Zeitschrift British Journal of Haematology, 2025. Verfasst von Junwei Lin und 11 weiteren Autor:innen. Beteiligte Einrichtung: Guangzhou Medical University, Guangzhou, China. Hauptthemen laut MEDLINE: Lymphoma, B-Cell, Lymphoma, Follicular, Leukemia, Lymphocytic, Chronic, B-Cell, Leukemia, Hairy Cell. Die Arbeit wurde bisher 6-mal zitiert (Crossref) und nennt 38 Literaturangaben. Gefördert von: The Science and Technology Program of Guangzhou, The Guangzhou Health and Family Planning Science and Technology Project, The Subject Construction Project of Guangzhou Medical University.
Abstract (Originalsprache)
Mature B‐cell neoplasms (MBNs) are clonal proliferative diseases encompassing over 40 subtypes. The WHO classification (morphology, immunology, cytogenetics and molecular biology) provides comprehensive diagnostic understandings. However, MBN subtyping relies heavily on the expertise of clinicians and pathologists, and differences in clinical experience can lead to variations in subtyping efficiency and consistency. Additionally, due to the diversity in genetic backgrounds, machine learning (ML) models constructed based on Western populations may not be suitable for Chinese MBN patients. To construct a highly accurate classification model suitable for Chinese MBN patients, we first developed an ML model based on next‐generation sequencing (NGS) from Chinese MBN patients, with an accuracy of 0.719, which decreased to 0.707 after model feature selection. Another ML model based on NGS and tumour cell size had an accuracy of 0.715, which increased to 0.763 after model feature selection. Both models were more accurate than models constructed using Western MBN patient databases. Furthermore, by adding flow cytometry for CD5 and CD10, the accuracy reached 0.864, which further improved to 0.872 after model feature selection. These models are accessible via an open‐access website. Overall, ML models incorporating multiplatform tests can serve as practical auxiliary tools for MBN subtype classification.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Substanzen
Autor:innen und Institutionen
- Guangzhou Medical University, Guangzhou, China.
- Guangzhou KingMed Transformative Medicine Institute Co., Ltd., Guangzhou, China.
- Guangzhou Women and Children's Medical Center, Guangzhou Medical University, Guangzhou, China.
- Department of Hematology, The Third Affiliated Hospital of Sun Yat-sen University and Sun Yat-sen Institute of Hematology, Guangzhou, China.
- Guangzhou KingMed Center for Clinical Laboratory Co., Ltd., Guangzhou, China.
- Guangzhou KingMed Diagnostics Group Co., Ltd., Guangzhou, China.
ORCID-Profile: Yuxin Chen
Förderung
- The Science and Technology Program of Guangzhou
- The Guangzhou Health and Family Planning Science and Technology Project
- The Subject Construction Project of Guangzhou Medical University
- The STI 2030-Major Projects
- The Postdoctoral Research Initiation Fund from Guangzhou Institute of Pediatrics, Guangzhou Women and children's Medical center
- Medical discipline Construction Project of Pudong Health Committee of Shanghai
- National Natural Science Foundation of china
Zitieren
APA
Lin, J., Mu, Y., Liu, L., Meng, Y., Chen, T., Fan, X., Yuan, J., Shen, M., Pan, J., Ren, Y., Yu, S., & Chen, Y. (2025). Machine learning based on multiplatform tests assists in subtype classification of mature B‐cell neoplasms. British Journal of Haematology. https://doi.org/10.1111/bjh.19934
Vancouver
Lin J, Mu Y, Liu L, Meng Y, Chen T, Fan X, et al. Machine learning based on multiplatform tests assists in subtype classification of mature B‐cell neoplasms. British Journal of Haematology. 2025. doi:10.1111/bjh.19934
BibTeX
@article{Lin2025,
author = {Lin, Junwei and Mu, Yafei and Liu, Lingling and Meng, Yuhuan and Chen, Tao and Fan, Xijie and Yuan, Jiecheng and Shen, Maoting and Pan, Jianhua and Ren, Yuxia and Yu, Shihui and Chen, Yuxin},
title = {Machine learning based on multiplatform tests assists in subtype classification of mature B‐cell neoplasms},
journal = {British Journal of Haematology},
year = {2025},
doi = {10.1111/bjh.19934}
}
EUVIMED