Related Experiment Video
Updated: Jul 6, 2025
Predictive Immune Modeling of Solid Tumors
Published on: February 25, 2020
Multi-institutional prognostic modeling of survival outcomes in NSCLC patients treated with first-line immunotherapy
Sevinj Yolchuyeva1,2, Leyla Ebrahimpour3,2,4, Marion Tonneau5,6
1Department of Mathematics and Computer Science, Université du Québec à Trois Rivières, Trois-Rivières, Canada.
Background:
Immune checkpoint inhibitors (ICIs) have emerged as one of the most promising first-line therapeutics in the management of non-small cell lung cancer (NSCLC). However, only a subset of these patients responds to ICIs, highlighting the clinical need to develop better predictive and prognostic biomarkers. This study will leverage pre-treatment imaging profiles to develop survival risk models for NSCLC patients treated with first-line immunotherapy.
Methods:
Advanced NSCLC patients (n = 149) were retrospectively identified from two institutions who were treated with first-line ICIs. Radiomics features extracted from pretreatment imaging scans were used to build the predictive models for progression-free survival (PFS) and overall survival (OS). A compendium of five feature selection methods and seven machine learning approaches were utilized to build the survival risk models. The concordance index (C-index) was used to evaluate model performance.
Results:
From our results, we found several combinations of machine learning algorithms and feature selection methods to achieve similar performance. K-nearest neighbourhood (KNN) with ReliefF (RL) feature selection was the best-performing model to predict PFS (C-index = 0.61 and 0.604 in discovery and validation cohorts), while XGBoost with Mutual Information (MI) feature selection was the best-performing model for OS (C-index = 0.7 and 0.655 in discovery and validation cohorts).
Conclusion:
The results of this study highlight the importance of implementing an appropriate feature selection method coupled with a machine learning strategy to develop robust survival models. With further validation of these models on external cohorts when available, this can have the potential to improve clinical decisions by systematically analyzing routine medical images.
Insights
Predicting non-small cell lung cancer (NSCLC) patient survival after immunotherapy is crucial. This study used radiomics imaging features and machine learning to build predictive models for progression-free and overall survival, showing promising results for clinical decision-making.
Area of Science:
- Oncology
- Medical Imaging
- Artificial Intelligence
Background:
- Immune checkpoint inhibitors (ICIs) are a promising first-line treatment for non-small cell lung cancer (NSCLC).
- Predictive biomarkers are needed as only a subset of NSCLC patients respond to ICIs.
- This study aims to develop survival risk models using pre-treatment imaging profiles.
Purpose of the Study:
- To develop and validate survival risk models for NSCLC patients receiving first-line immunotherapy.
- To leverage radiomics features from pre-treatment imaging for predicting progression-free survival (PFS) and overall survival (OS).
- To identify optimal combinations of feature selection methods and machine learning algorithms for robust survival prediction.
Main Methods:
- Retrospective analysis of 149 advanced NSCLC patients treated with first-line ICIs.
- Extraction of radiomics features from pre-treatment imaging scans.
- Application of five feature selection methods and seven machine learning algorithms to build survival models.
- Evaluation of model performance using the concordance index (C-index).
Main Results:
- Several machine learning and feature selection combinations demonstrated similar predictive performance.
- K-nearest neighbourhood (KNN) with ReliefF (RL) best predicted PFS (C-index: 0.61 discovery, 0.604 validation).
- XGBoost with Mutual Information (MI) best predicted OS (C-index: 0.7 discovery, 0.655 validation).
Conclusions:
- The choice of feature selection and machine learning strategy is critical for developing robust survival models.
- These radiomics-based models have the potential to improve clinical decision-making in NSCLC immunotherapy.
- Further validation on external cohorts is recommended to confirm the clinical utility of these models.
