Machine learning-based nomogram predicts heart failure risk in elderly relapsed/refractory multiple myeloma patients...

Area of Science:

• Cardiology
• Oncology
• Medical Informatics

Background:

• Elderly patients with relapsed/refractory multiple myeloma (RRMM) undergoing carfilzomib therapy face significant risks of heart failure (HF).
• Early identification of HF risk is crucial for effective clinical management and improved patient outcomes in this vulnerable population.

Purpose of the Study:

• To develop and validate a machine learning-based nomogram for predicting heart failure (HF) in elderly patients with relapsed/refractory multiple myeloma (RRMM) receiving carfilzomib-based therapy.
• To facilitate early identification and individualized clinical management of HF in this patient cohort.

Main Methods:

• Retrospective analysis of clinical data from 192 elderly RRMM patients treated with carfilzomib-based therapy.
• Application of machine learning algorithms (LASSO, SVM, XGBoost) for variable selection.
• Nomogram construction using robust predictors, with performance assessed by C-index, calibration curves, and decision curve analysis (DCA).

Main Results:

• Heart failure (HF) occurred in 25.5% of patients.
• Machine learning models identified coronary artery disease (CAD), hypertension, renal insufficiency, and albumin (Alb) levels as significant HF risk factors.
• The developed nomogram demonstrated good predictive performance (C-index: 0.780), internal and external calibration, and clinical utility via DCA.

Conclusions:

• A practical nomogram for cardiovascular risk assessment in elderly RRMM patients on carfilzomib therapy has been developed.
• This tool can assist clinicians in early risk stratification.
• The nomogram supports tailored monitoring and management strategies throughout treatment.