# Development and Validation of a Predictive Nomogram for Venous Thromboembolism Risk in Multiple Myeloma Patients: A Single-Center Cohort Study in China

## TL;DR

This study created a tool to predict the risk of blood clots in multiple myeloma patients, improving personalized treatment decisions.

## Contribution

A novel nomogram and online calculator were developed for VTE risk prediction in multiple myeloma patients.

## Key findings

- The nomogram showed strong predictive accuracy with a C-index of 0.811 in the training cohort.
- Calibration curves confirmed high agreement between predicted and observed VTE probabilities.
- The tool outperformed general strategies like 'treat all' or 'treat none' in decision curve analysis.

## Abstract

Objectives: Venous thromboembolism (VTE) is a significant complication in patients with multiple myeloma (MM) that adversely affects morbidity, mortality, and treatment outcomes. This study aimed to develop and validate a predictive nomogram for assessing VTE risk in MM patients using clinicopathological factors. Methods: Clinical data, including 25 candidate risk factors, were collected. Univariate and multivariate logistic regression analyses were performed to identify independent risk factors for VTE. The nomogram was constructed using these variables, and its performance was evaluated by plotting receiver operating characteristic (ROC) curves, calculating the area under the curve (AUC), and conducting calibration and decision curve analysis (DCA). Additionally, an online calculator was developed for clinical use. Results: In total, 148 patients (17.5%) developed VTE in this study. The independent risk factors included age, Karnofsky performance status (KPS), anticoagulation therapy, erythropoietin use, and hemoglobin (Hb), platelet (PLT), calcium (Ca), activated partial thromboplastin time (APTT), and D-dimer levels. The nomogram demonstrated robust discriminative ability, with a C-index of 0.811 in the training cohort and 0.714 in the validation cohort. The calibration curves exhibited a high level of agreement between the predicted and observed probabilities. DCA confirmed the nomogram’s clinical utility across various threshold ranges, outperforming the “treat all” and “treat none” strategies. Conclusions: This study successfully developed and validated a nomogram for predicting VTE risk in MM patients, demonstrating substantial predictive accuracy and clinical applicability. The nomogram and accompanying online calculator provide valuable tools for individualized VTE risk assessment and informed clinical decision-making.