Develop a predictive model for the efficacy of multiple myeloma by combining multi-omics and machine learning

The aim of this study is to develop a machine learning model for predicting efficacy in newly diagnosed multiple myeloma (NDMM) patients, in order to advance the treatment management of MM. From August 2022 to July 2023, serum samples were collected from NDMM patients and treatment patients, and serum metabolites were analyzed. Based on the results of metabolomics analysis and combined with the transcriptome sequencing data of NDMM patients in the database, the patients were grouped according to the treatment effects, and the differentially expressed amino acid metabolism-related genes (AAMG) among patients with different treatment effects were screened out. Bioinformatics analysis and machine learning were utilized to construct a model for predicting efficacy in NDMM patients. This model can be used to screen for PRMM patients.