obtaining a Bayesian classifier of MM by a method comprising the following steps:

1) obtaining the expression data of 97 classifier genes in n MM samples, wherein the 97 classifier genes comprise: ACBD3, ADAR, ADSS, ALDH2, ANP32E, ANXA2, ATF3, ATP8B2, CACYBP, CAPN2, CCND1, CCT3, CDC42SE1, CERS2, CHSY3, CLIC1, CLMN, COPA, CSNK1G3, DAP3, DENND1B, ENSA, EPRS, EPSTI1, EVL, FAM13A, FAM49A, FLAD1, FRZB, GLRX2, HAX1, HDGF, HLA-A, HLA-B, HLA-C, HLA-F, HLA-G, IL6R, ISG20L2, JTB, KLF2, LAMTOR2, LDHA, MCL1, MOXD1, MRPL24, MRPL9, MVP, MYL6, NDUFS2, NOP58, NOTCH2NL, NTAN1, PAK1, PI4 KB, PIEZO1, PIK3AP1, PIM2, PIP5K1B, PMVK, POGZ, PPIA, PRCC, PRKCA, PRRC2C, PSMB4, PSMD4, RAB29, RCBTB2, SCAMP3, SCAPER, SDHC, SEL1L3, SELPLG, SHC1, SIDT1, SSR2, STAP1, TAP1, TIMM17A, TLR10, TMCO1, TOR1AIP2, TOR3A, TP53INP1, TPM3, TRANK1, TROVE2, UAP1, UBE2Q1, UBQLN4, UHMK1, VPS45, YY1AP1, ZC3H11A, ZFP36, and ZNF593;

2) Assigning the MM samples into an MCL1-M high subtype or an MCL1-M low subtype by consensus clustering; and

3) employing a naïve Bayes method to construct the Bayesian classifier on the basis of the two subtypes of step 2), the 97 classifier gene expression data of n MM samples in step 1), and prognostic survival data of the n MM samples;

obtaining or detecting the expression of 97 classifier genes in the patients with MM;

predicting, using the constructed Bayesian classifier, the prognosis of the patients with MM and the treatment effect of using bortezomib or bortezomib-containing drug combinations, wherein the constructed Bayesian classifier determines whether the patient with MM belongs to the MCL1-M high subtype or the MCL1-M low subtype, and wherein the predicted prognosis of the patient with MM belonging to the MCL1-M high subtype is significantly poorer than that of the patient with MM belonging to the MCL1-M low subtype; and

treating the patient with MM determined to belong to the MCL1-M high subtype by the constructed Bayesian classifier with bortezomib or a bortezomib-containing drug combination.