# Predictive Model for Occurrence of Febrile Neutropenia after Chemotherapy in Patients with Diffuse Large B-Cell Lymphoma: A Multicenter, Retrospective, Observational Study

## TL;DR

This study developed a predictive model to assess the risk of febrile neutropenia in patients with diffuse large B-cell lymphoma before starting chemotherapy.

## Contribution

A novel predictive model for febrile neutropenia risk in DLBCL patients using pretreatment clinical factors.

## Key findings

- The model achieved an area under the ROC curve of 0.844 for predicting febrile neutropenia.
- Clinical factors like lymphopenia and high soluble interleukin-2 receptor levels were significant predictors.
- The model can help clinicians better manage chemotherapy risks in DLBCL patients.

## Abstract

Febrile neutropenia (FN) is a major concern in patients undergoing chemotherapy for diffuse large B-cell lymphoma (DLBCL); however, the overall risk of FN is difficult to assess. This study aimed to develop a model for predicting the occurrence of FN in patients with DLBCL. In this multicenter, retrospective, observational analysis, a multivariate logistic regression model was used to analyze the association between FN incidence and pretreatment clinical factors. We included adult inpatients and outpatients (aged ≥ 18 years) diagnosed with DLBCL who were treated with chemotherapy. The study examined 246 patients. Considering FN occurring during the first cycle of chemotherapy as the primary outcome, a predictive model with a total score of 5 points was constructed as follows: 1 point each for a positive hepatitis panel, extranodal involvement, and a high level of soluble interleukin-2 receptor and 2 points for lymphopenia. The area under the receiver operating characteristic curve of this model was 0.844 (95% confidence interval: 0.777–0.911). Our predictive model can assess the risk of FN before patients with DLBCL start chemotherapy, leading to better outcomes.