Predictive value of near-term prediction models for severe immune-related adverse events in malignant tumor PD-1 inhibitor therapy

Immune-related adverse events (irAEs) impact outcomes, with most research focusing on early prediction (baseline data), rather than near-term prediction (one cycle before the occurrence of irAEs and the current cycle). We aimed to explore the near-term predictive value of neutrophil/lymphocyte ratio...

Full description

Saved in:
Bibliographic Details
Main Authors: Yunyi Du, Ying Zhang, Wenqi Zhao, Yuexiang Zhang, Fei Su, Xiaoling Zhang, Weiling Li, Wenqing Hu, Yongai Li, Jun Zhao
Format: Article
Language:English
Published: Taylor & Francis Group 2024-12-01
Series:Human Vaccines & Immunotherapeutics
Subjects:
Online Access:https://www.tandfonline.com/doi/10.1080/21645515.2024.2398309
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850185263012118528
author Yunyi Du
Ying Zhang
Wenqi Zhao
Yuexiang Zhang
Fei Su
Xiaoling Zhang
Weiling Li
Wenqing Hu
Yongai Li
Jun Zhao
author_facet Yunyi Du
Ying Zhang
Wenqi Zhao
Yuexiang Zhang
Fei Su
Xiaoling Zhang
Weiling Li
Wenqing Hu
Yongai Li
Jun Zhao
author_sort Yunyi Du
collection DOAJ
description Immune-related adverse events (irAEs) impact outcomes, with most research focusing on early prediction (baseline data), rather than near-term prediction (one cycle before the occurrence of irAEs and the current cycle). We aimed to explore the near-term predictive value of neutrophil/lymphocyte ratio (NLR), platelet/lymphocyte ratio (PLR), absolute eosinophil count (AEC) for severe irAEs induced by PD-1 inhibitors. Data were collected from tumor patients treated with PD-1 inhibitors. NLR, PLR, and AEC data were obtained from both the previous and the current cycles of irAEs occurrence. A predictive model was developed using elastic net logistic regression Cutoff values were determined using Youden’s Index. The predicted results were compared with actual data using Bayesian survival analysis. A total of 138 patients were included, of whom 47 experienced grade 1–2 irAEs and 18 experienced grade 3–5 irAEs. The predictive model identified optimal α and λ through 10-fold cross-validation. The Shapiro-Wilk test, Kruskal-Wallis test and logistic regression showed that only current cycle data were meaningful. The NLR was statistically significant in predicting irAEs in the previous cycle. Both NLR and AEC were significant predictors of irAEs in the current cycle. The model achieved an area under the ROC curve (AUC) of 0.783, with a sensitivity of 77.8% and a specificity of 80.8%. A probability ≥ 0.1345 predicted severe irAEs. The model comprising NLR, AEC, and sex may predict the irAEs classification in the current cycle, offering a near-term predictive advantage over baseline models and potentially extending the duration of immunotherapy for patients.
format Article
id doaj-art-6ddbeb11c972409dae8f6bd9bc4970d2
institution OA Journals
issn 2164-5515
2164-554X
language English
publishDate 2024-12-01
publisher Taylor & Francis Group
record_format Article
series Human Vaccines & Immunotherapeutics
spelling doaj-art-6ddbeb11c972409dae8f6bd9bc4970d22025-08-20T02:16:46ZengTaylor & Francis GroupHuman Vaccines & Immunotherapeutics2164-55152164-554X2024-12-0120110.1080/21645515.2024.2398309Predictive value of near-term prediction models for severe immune-related adverse events in malignant tumor PD-1 inhibitor therapyYunyi Du0Ying Zhang1Wenqi Zhao2Yuexiang Zhang3Fei Su4Xiaoling Zhang5Weiling Li6Wenqing Hu7Yongai Li8Jun Zhao9Department of Oncology, Changzhi People’s Hospital Affiliated to Changzhi Medical College, Changzhi, Shanxi, ChinaDepartment of Respiratory, Pengzhou People’s Hospital, Chengdu, Sichuan, ChinaDepartment of Statistics, University of Auckland, AucklandDepartment of Oncology, Changzhi People’s Hospital Affiliated to Changzhi Medical College, Changzhi, Shanxi, ChinaDepartment of Oncology, Graduate of School of Changzhi Medical College, Changzhi, Shanxi, ChinaDepartment of Oncology, Changzhi People’s Hospital Affiliated to Changzhi Medical College, Changzhi, Shanxi, ChinaDepartment of Oncology, The People’s Hospital of Jianyang City, Chengdu, Sichuan, ChinaDepartment of Gastrointestinal Surgery, Changzhi People’s Hospital Affiliated to Changzhi Medical College, Changzhi, Shanxi, ChinaDepartment of Radiology, Changzhi People’s Hospital, Changzhi, Shanxi, ChinaDepartment of Oncology, Changzhi People’s Hospital Affiliated to Changzhi Medical College, Changzhi, Shanxi, ChinaImmune-related adverse events (irAEs) impact outcomes, with most research focusing on early prediction (baseline data), rather than near-term prediction (one cycle before the occurrence of irAEs and the current cycle). We aimed to explore the near-term predictive value of neutrophil/lymphocyte ratio (NLR), platelet/lymphocyte ratio (PLR), absolute eosinophil count (AEC) for severe irAEs induced by PD-1 inhibitors. Data were collected from tumor patients treated with PD-1 inhibitors. NLR, PLR, and AEC data were obtained from both the previous and the current cycles of irAEs occurrence. A predictive model was developed using elastic net logistic regression Cutoff values were determined using Youden’s Index. The predicted results were compared with actual data using Bayesian survival analysis. A total of 138 patients were included, of whom 47 experienced grade 1–2 irAEs and 18 experienced grade 3–5 irAEs. The predictive model identified optimal α and λ through 10-fold cross-validation. The Shapiro-Wilk test, Kruskal-Wallis test and logistic regression showed that only current cycle data were meaningful. The NLR was statistically significant in predicting irAEs in the previous cycle. Both NLR and AEC were significant predictors of irAEs in the current cycle. The model achieved an area under the ROC curve (AUC) of 0.783, with a sensitivity of 77.8% and a specificity of 80.8%. A probability ≥ 0.1345 predicted severe irAEs. The model comprising NLR, AEC, and sex may predict the irAEs classification in the current cycle, offering a near-term predictive advantage over baseline models and potentially extending the duration of immunotherapy for patients.https://www.tandfonline.com/doi/10.1080/21645515.2024.2398309Immune-related adverse events (irAEs)PD-1 inhibitorsneutrophil/lymphocyte ratio (NLR)platelet/lymphocyte ratio (PLR)absolute eosinophil count (AEC)prediction model
spellingShingle Yunyi Du
Ying Zhang
Wenqi Zhao
Yuexiang Zhang
Fei Su
Xiaoling Zhang
Weiling Li
Wenqing Hu
Yongai Li
Jun Zhao
Predictive value of near-term prediction models for severe immune-related adverse events in malignant tumor PD-1 inhibitor therapy
Human Vaccines & Immunotherapeutics
Immune-related adverse events (irAEs)
PD-1 inhibitors
neutrophil/lymphocyte ratio (NLR)
platelet/lymphocyte ratio (PLR)
absolute eosinophil count (AEC)
prediction model
title Predictive value of near-term prediction models for severe immune-related adverse events in malignant tumor PD-1 inhibitor therapy
title_full Predictive value of near-term prediction models for severe immune-related adverse events in malignant tumor PD-1 inhibitor therapy
title_fullStr Predictive value of near-term prediction models for severe immune-related adverse events in malignant tumor PD-1 inhibitor therapy
title_full_unstemmed Predictive value of near-term prediction models for severe immune-related adverse events in malignant tumor PD-1 inhibitor therapy
title_short Predictive value of near-term prediction models for severe immune-related adverse events in malignant tumor PD-1 inhibitor therapy
title_sort predictive value of near term prediction models for severe immune related adverse events in malignant tumor pd 1 inhibitor therapy
topic Immune-related adverse events (irAEs)
PD-1 inhibitors
neutrophil/lymphocyte ratio (NLR)
platelet/lymphocyte ratio (PLR)
absolute eosinophil count (AEC)
prediction model
url https://www.tandfonline.com/doi/10.1080/21645515.2024.2398309
work_keys_str_mv AT yunyidu predictivevalueofneartermpredictionmodelsforsevereimmunerelatedadverseeventsinmalignanttumorpd1inhibitortherapy
AT yingzhang predictivevalueofneartermpredictionmodelsforsevereimmunerelatedadverseeventsinmalignanttumorpd1inhibitortherapy
AT wenqizhao predictivevalueofneartermpredictionmodelsforsevereimmunerelatedadverseeventsinmalignanttumorpd1inhibitortherapy
AT yuexiangzhang predictivevalueofneartermpredictionmodelsforsevereimmunerelatedadverseeventsinmalignanttumorpd1inhibitortherapy
AT feisu predictivevalueofneartermpredictionmodelsforsevereimmunerelatedadverseeventsinmalignanttumorpd1inhibitortherapy
AT xiaolingzhang predictivevalueofneartermpredictionmodelsforsevereimmunerelatedadverseeventsinmalignanttumorpd1inhibitortherapy
AT weilingli predictivevalueofneartermpredictionmodelsforsevereimmunerelatedadverseeventsinmalignanttumorpd1inhibitortherapy
AT wenqinghu predictivevalueofneartermpredictionmodelsforsevereimmunerelatedadverseeventsinmalignanttumorpd1inhibitortherapy
AT yongaili predictivevalueofneartermpredictionmodelsforsevereimmunerelatedadverseeventsinmalignanttumorpd1inhibitortherapy
AT junzhao predictivevalueofneartermpredictionmodelsforsevereimmunerelatedadverseeventsinmalignanttumorpd1inhibitortherapy