Related Experiment Video
Updated: May 19, 2026
Predictive Immune Modeling of Solid Tumors
Published on: February 25, 2020
Development of an online prediction tool for immunotherapy-related adverse events in patients with advanced NSCLC
Ling-Chun Cao1, Jing-Jing Ye1, Wen-Qian Mei1
1Department of Respiratory and Critical Care Medicine, Chaohu Hospital of Anhui Medical University, Hefei, Anhui, China.
Objective:
Despite the widespread use of immune checkpoint inhibitors (ICIs) improving survival outcomes in non-small cell lung cancer (NSCLC) patients, immune-related adverse events (irAEs) triggered by ICIs have become a major challenge in clinical practice. This study aims to establish an interpretable machine learning model to predict ICI treatment of irAE risk in advanced NSCLC patients, thereby supporting clinical decision-making and thus improving the safety of immunotherapy.
Methods:
A total of 550 patients were enrolled in the study. The development cohort consisted of 420 patients treated with ICIs from January 2019 to October 2023 and was randomly divided into a training set (n = 295) and a test set (n = 125). In addition, a temporally distinct cohort of 130 patients treated from November 2023 to November 2024 served as the validation set. Nine machine-learning algorithms were trained and evaluated in parallel, and the optimal model was selected based on discrimination, calibration, and clinical utility.
Results:
Among the 550 patients, 361 (65.6%) developed irAEs. Six essential features were chosen including neutrophil count (Neut), lymphocyte count (Lymph), platelet count (Plt), hemoglobin (Hb), Eastern Cooperative Oncology Group Performance Status (ECOG PS), and history of diabetes. Although the neural network (NN) model performed slightly better in the test set, the logistic regression (LR) model offered superior interpretability, and its clinical net benefit was similar to that of the NN model. Therefore, the LR model was ultimately selected as the optimal predictive model (AUC = 0.855 in the test set; 0.801 in the validation set).
Conclusion:
The LR model enables the early identification of patients at high risk of developing irAEs during hospitalization and supports their timely adoption of individualized management measures. The web tool developed based on this model is available at https://lingchun.shinyapps.io/web123/.
Insights
This study developed an interpretable logistic regression model to predict immune-related adverse events (irAEs) in non-small cell lung cancer (NSCLC) patients receiving immune checkpoint inhibitors (ICIs). The model aids in early risk identification and personalized management for improved immunotherapy safety.
Area of Science:
- Oncology
- Immunotherapy
- Machine Learning in Medicine
Background:
- Immune checkpoint inhibitors (ICIs) improve survival in non-small cell lung cancer (NSCLC).
- Immune-related adverse events (irAEs) are a significant clinical challenge with ICIs.
- Predicting irAE risk is crucial for safe and effective immunotherapy.
Purpose of the Study:
- To develop an interpretable machine learning model for predicting irAE risk in advanced NSCLC patients treated with ICIs.
- To support clinical decision-making and enhance immunotherapy safety.
- To identify key predictive features for irAE development.
Main Methods:
- Trained and evaluated nine machine learning algorithms on a cohort of 550 NSCLC patients.
- Selected the optimal model based on discrimination, calibration, and clinical utility.
- Utilized a training set (n=295), test set (n=125), and validation set (n=130).
Main Results:
- Identified six key features: neutrophil count, lymphocyte count, platelet count, hemoglobin, ECOG PS, and diabetes history.
- The logistic regression (LR) model demonstrated strong predictive performance (AUC=0.855 in test set, 0.801 in validation set).
- The LR model provided superior interpretability with comparable clinical utility to a neural network model.
Conclusions:
- The developed LR model enables early identification of patients at high risk for irAEs.
- Facilitates timely adoption of individualized management strategies.
- A web tool is available for clinical application: https://lingchun.shinyapps.io/web123/