What question did this study set out to answer?

This review aims to evaluate the potential of AI and machine learning applications in enhancing the prediction of clinical outcomes in relapsed/refractory multiple myeloma.

May 30, 2026

Artificial intelligence and machine learning in relapsed/refractory multiple myeloma: A systematic review.

Key Points

This review aims to evaluate the potential of AI and machine learning applications in enhancing the prediction of clinical outcomes in relapsed/refractory multiple myeloma.
Systematic search of PubMed, Embase, and Web of Science for studies using AI/ML in RRMM until December 2025.
Studies were included if they applied AI/ML algorithms, involved RRMM populations, and predicted clinical outcomes.
Performance metrics and clinical applicability were extracted from identified studies.
20 studies involving over 20,000 patients were reviewed across six application domains.
AI/ML models demonstrated significant improvement over traditional prognostic systems like R-ISS.
Key predictors identified include CAR T-cell risk stratification and treatment response accuracy with AUC values up to 0.98.

Abstract

e19500 Background: Relapsed/refractory multiple myeloma (RRMM) remains incurable with heterogeneous outcomes. Traditional prognostic systems (ISS/R-ISS) offer limited discriminatory power and no treatment guidance in heterogeneous RRMM. The heterogeneity of RRMM makes it suitable for AI/ML applications; however, these approaches have not been systematically reviewed. Methods: We systematically searched PubMed, Embase, and Web of Science (till December 2025) for studies applying AI/ML to RRMM populations. Included studies required: (1) AI/ML algorithm application, (2) RRMM patients included or validated, and (3) clinical outcome prediction. Studies were categorized by application domain. Performance metrics (C-index, AUC), validation methods, and clinical applicability were extracted. Results: We identified 20 studies applying AI/ML to >20,000 patients across six RRMM-relevant domains. Survival prediction (n=7): Transformer, Random Forest, and ensemble models achieved C-indices of 0.62–0.82; the EMN-HARMONY model (N=14,345) showed 6-variable score outperforming R-ISS, while POD24 was strongest mortality predictor. CAR T-cell therapy (n=3): The MyCARe logistic regression model stratified 5-month relapse risk (7% vs 27% vs 53%; p0.80) using ECOG, hemoglobin, and comorbidities. Minimal residual disease (MRD) (n=1): AI-based pattern classification of longitudinal MRD significantly stratified PFS (p<10⁻⁷). Imaging radiomics (n=2): 3D-CNN on whole-body MRI (AUC 0.804) and DeepSurv on PET/CT (C-index 0.657) identified prognostic imaging features. External validation: 11/20 studies (55%). Conclusions: AI/ML demonstrates substantial potential for RRMM risk stratification, CAR T optimization, treatment response prediction, and toxicity prevention. Three models (MyCARe, EMN-HARMONY, carfilzomib cardiotoxicity nomogram) use routine clinical variables and are immediately implementable. Standardized external validation and prospective trials are needed for widespread clinical application. Study Method Finding Metric Mosquera 2025 Ensemble ML 6-variables vs R-ISS C-index:0.66 Gagelmann 2024 Logistic MyCARe CAR T relapse score 7% vs 53% relapse Gómez-Martín 2025 IsomiR Daratumumab response AUC:0.98 Qiao 2025 XGBoost carfilzomib cardiotoxicity C:0.78 Martinez-Lopez 2024 AI class MRD dynamics p10⁻⁷ Morita 2024 3D-CNN whole-body-MRI prognosis AUC:0.80

Mark Helpful

Bookmark

Relay