AUTHOR=Mu Yafei , Chen Yuxin , Meng Yuhuan , Chen Tao , Fan Xijie , Yuan Jiecheng , Lin Junwei , Pan Jianhua , Li Guibin , Feng Jinghua , Diao Kaiyuan , Li Yinghua , Yu Shihui , Liu Lingling TITLE=Machine learning models-based on integration of next-generation sequencing testing and tumor cell sizes improve subtype classification of mature B-cell neoplasms JOURNAL=Frontiers in Oncology VOLUME=Volume 13 - 2023 YEAR=2023 URL=https://www.frontiersin.org/journals/oncology/articles/10.3389/fonc.2023.1160383 DOI=10.3389/fonc.2023.1160383 ISSN=2234-943X ABSTRACT=Next-generation sequencing (NGS) panels for mature B-cell neoplasms (MBNs) are widely applied clinically but have yet to be routinely used in a manner that is suitable for subtype differential diagnosis. In this study, 849 newly diagnosed MBNs cases were retrospectively identified and included in mutational landscape analyses. Patterns of gene mutations in a variety of MBNs subtypes were found, important to investigate tumorigenesis in MBNs. A long list of novel mutations was revealed, valuable to both functional studies and clinical applications. By combining gene mutation information revealed by NGS and machine learning (ML), we established ML models that provide valuable information for MBNs subtype classification. In total, 8895 cases of 8 subtypes of MBNs in the Catalogue Of Somatic Mutations In Cancer (COSMIC) database were collected and utilized for ML model construction, and the models were validated on the 849 MBNs cases from our laboratory. A series of ML models was constructed in this study, and the most efficient model, with an accuracy of 0.87, was based on integration of NGS testing and tumor cell sizes. In conclusion, the ML models were of great statistical significance in the differential diagnosis of all cases and different MBNs subtypes. Additionally, using NGS results to assist in subtype classification of MBNs by method of ML has positive clinical potential.