# Construction and validation of nomogram prediction model for anxiety and depression in chemotherapy patients with multiple myeloma

## TL;DR

This study developed and validated a nomogram model to predict anxiety and depression in chemotherapy patients with multiple myeloma.

## Contribution

A new nomogram model was constructed and validated for predicting anxiety and depression in multiple myeloma chemotherapy patients.

## Key findings

- The incidence of anxiety and depression in MM chemotherapy patients was 28.33%.
- The nomogram model showed high predictive accuracy with AUCs of 0.945 and 0.967 in the modeling and validation groups, respectively.
- Gender, education level, tumor stage, complications, and treatment plan were identified as risk factors for anxiety and depression.

## Abstract

To construct and validate a nomogram prediction model for anxiety and depression in chemotherapy patients with multiple myeloma (MM).

From May 2021 to May 2023, 333 MM chemotherapy patients treated at our hospital were selected. The patients were randomly divided into a modeling group and a validation group in a 7:3 ratio (using a random number table method). According to whether the modeling group patients had anxiety and depression, they were grouped into a non-anxiety and depression group and an anxiety and depression group; a nomogram model constructed using R software was built to evaluate the predictive performance of the model. Clinical decision curves (DCA) were used to assess the value of the clinical application of the model.

Out of the 233 patients in this study, 66 experienced anxiety and depression, with an incidence rate of 28.33%. There were great differences in gender, economic income, education level, tumor staging, complications, and treatment plans between the anxiety and depression group and the non-anxiety and depression group (P<0.05). The results of multivariate Logistic regression analysis showed that gender, education level, tumor stage, complications, and treatment plan were risk factors for anxiety and depression in MM chemotherapy patients (P<0.05), while economic income served as a protective factor (P<0.05). The AUC of the modeling group was 0.945, and the H-L test was χ2 = 8.579, P = 0.674, with good agreement. The AUC of the validation group was 0.967, and the H-L test was χ2 = 7.315, P = 0.698, with good consistency. The DCA curve shows that the probability of assessing anxiety and depression in patients undergoing MM chemotherapy is higher for clinical use when the probability is between 0.05 and 0.95.

Gender, education, tumor stage, comorbidities and treatment regimen were risk factors for anxiety and depression in MM chemotherapy patients, while financial income was a protective factor for anxiety and depression in MM chemotherapy patients, and the constructed nomogram visually predicted the risk of anxiety and depression in MM chemotherapy patients.