BACKGROUND: Multiple myeloma (MM) represents the second most common hematological malignancy characterized by the infiltration of the bone marrow by plasma cells that produce monoclonal immunoglobulin. While the quality and length of life of MM patients have significantly increased, MM remains a hard-to-treat disease; almost all patients relapse. As MM is highly heterogenous, patients relapse at different times. It is currently not possible to predict when relapse will occur; numerous studies investigating the dysregulation of non-coding RNA molecules in cancer suggest that microRNAs could be good markers of relapse. RESULTS: Using small RNA sequencing, we profiled microRNA expression in peripheral blood in three groups of MM patients who relapsed at different intervals. In total, 24 microRNAs were significantly dysregulated among analyzed subgroups. Independent validation by RT-qPCR confirmed changed levels of miR-598-3p in MM patients with different times to relapse. At the same time, differences in the mass spectra between groups were identified using matrix-assisted laser desorption/ionization time of flight mass spectrometry. All results were analyzed by machine learning. CONCLUSION: Mass spectrometry coupled with machine learning shows potential as a reliable, rapid, and cost-effective preliminary screening technique to supplement current diagnostics.

• Keywords
• Liquid biopsy, MALDI-TOF MS, Machine learning, Multiple myeloma, Relapse, Small RNA seq, microRNA,
• Publication type
• Journal Article MeSH

Multiple myeloma (MM) is the second most prevalent hematological malignancy, characterized by infiltration of the bone marrow by malignant plasma cells. Extramedullary disease (EMD) represents a more aggressive condition involving the migration of a subclone of plasma cells to paraskeletal or extraskeletal sites. Liquid biopsies could improve and speed diagnosis, as they can better capture the disease heterogeneity while lowering patients' discomfort due to minimal invasiveness. Recent studies have confirmed alterations in the proteome across various malignancies, suggesting specific changes in protein classes. In this study, we show that MALDI-TOF mass spectrometry fingerprinting of peripheral blood can differentiate between MM and primary EMD patients. We constructed a predictive model using a supervised learning method, partial least squares-discriminant analysis (PLS-DA) and evaluated its generalization performance on a test dataset. The outcome of this analysis is a method that predicts specifically primary EMD with high sensitivity (86.4%), accuracy (78.4%), and specificity (72.4%). Given the simplicity of this approach and its minimally invasive character, this method provides rapid identification of primary EMD and could prove helpful in clinical practice.

• Keywords
• Extramedullary disease, Liquid biopsy, MALDI-TOF mass spectrometry, Machine learning, Multiple myeloma, Partial least squares-discriminant analysis, Principal component analysis,
• MeSH
• Middle Aged MeSH
• Humans MeSH
• Multiple Myeloma * blood   diagnosis   MeSH
• Biomarkers, Tumor blood   MeSH
• Aged MeSH
• Spectrometry, Mass, Matrix-Assisted Laser Desorption-Ionization methods   MeSH
• Liquid Biopsy methods   MeSH
• Check Tag
• Middle Aged MeSH
• Humans MeSH
• Male MeSH
• Aged MeSH
• Female MeSH
• Publication type
• Journal Article MeSH
• Names of Substances
• Biomarkers, Tumor MeSH