Development of a robust predictive model for neutropenia after esophageal cancer chemotherapy using GLMMLasso.

Abstract

Background: Neutropenia can easily progress to febrile neutropenia and is a risk factor for life-threatening infections. Predicting and preventing severe neutropenia can help avoid such infections.

Aim: This study aimed to develop an optimal model using advanced statistical methods to predict neutropenia after 5-fluorouracil/cisplatin chemotherapy for esophageal cancer and to create a nomogram for clinical application.

Method: Patients who received 5-fluorouracil/cisplatin chemotherapy at Chiba University Hospital, Japan, between January 2011 and March 2021 were included. Clinical parameters were measured before the first, second, and third chemotherapy cycles and were randomly divided by patient into a training cohort (60%) and test cohort (40%). The predictive performance of Logistic, Stepwise, Lasso, and GLMMLasso models was evaluated by the area under the receiver-operating characteristic curve (AUC). A nomogram based on GLMMLasso was developed, and the accuracy of probabilistic predictions was evaluated by the Brier score.

Results: The AUC for the first cycle of chemotherapy was 0.781 for GLMMLasso, 0.751 for Lasso, 0.697 for Stepwise, and 0.669 for Logistic. The respective AUCs for GLMMLasso in the second and third cycles were 0.704 and 0.900. The variables selected by GLMMLasso were cisplatin dose, 5-fluorouracil dose, use of leucovorin, sex, cholinesterase, and platelets. A nomogram predicting neutropenia was created based on each regression coefficient. The Brier score for the nomogram was 0.139.

Conclusion: We have developed a predictive model with high performance using GLMMLasso. Our nomogram can represent risk visually and may facilitate the assessment of the probability of chemotherapy-induced severe neutropenia in clinical practice.