Multi-institutional prognostic modeling of survival outcomes in NSCLC patients treated with first-line immunotherapy using radiomics
Abstract 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 an...
| Main Authors: | , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2024-01-01
|
| Series: | Journal of Translational Medicine |
| Online Access: | https://doi.org/10.1186/s12967-024-04854-z |
| _version_ | 1827381992192212992 |
|---|---|
| author | Sevinj Yolchuyeva Leyla Ebrahimpour Marion Tonneau Fabien Lamaze Michele Orain François Coulombe Julie Malo Wiam Belkaid Bertrand Routy Philippe Joubert Venkata SK. Manem |
| author_facet | Sevinj Yolchuyeva Leyla Ebrahimpour Marion Tonneau Fabien Lamaze Michele Orain François Coulombe Julie Malo Wiam Belkaid Bertrand Routy Philippe Joubert Venkata SK. Manem |
| author_sort | Sevinj Yolchuyeva |
| collection | DOAJ |
| description | Abstract 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. |
| first_indexed | 2024-03-08T14:13:01Z |
| format | Article |
| id | doaj.art-402d9860876a4dd9abb12bb7bde2e5fb |
| institution | Directory Open Access Journal |
| issn | 1479-5876 |
| language | English |
| last_indexed | 2024-03-08T14:13:01Z |
| publishDate | 2024-01-01 |
| publisher | BMC |
| record_format | Article |
| series | Journal of Translational Medicine |
| spelling | doaj.art-402d9860876a4dd9abb12bb7bde2e5fb2024-01-14T12:34:36ZengBMCJournal of Translational Medicine1479-58762024-01-012211910.1186/s12967-024-04854-zMulti-institutional prognostic modeling of survival outcomes in NSCLC patients treated with first-line immunotherapy using radiomicsSevinj Yolchuyeva0Leyla Ebrahimpour1Marion Tonneau2Fabien Lamaze3Michele Orain4François Coulombe5Julie Malo6Wiam Belkaid7Bertrand Routy8Philippe Joubert9Venkata SK. Manem10Department of Mathematics and Computer Science, Université du Québec à Trois RivièresQuebec Heart & Lung Institute Research CenterCentre de Recherche du Centre Hospitalier Universitaire de MontréalQuebec Heart & Lung Institute Research CenterQuebec Heart & Lung Institute Research CenterQuebec Heart & Lung Institute Research CenterCentre de Recherche du Centre Hospitalier Universitaire de MontréalCentre de Recherche du Centre Hospitalier Universitaire de MontréalCentre de Recherche du Centre Hospitalier Universitaire de MontréalQuebec Heart & Lung Institute Research CenterDepartment of Mathematics and Computer Science, Université du Québec à Trois RivièresAbstract 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.https://doi.org/10.1186/s12967-024-04854-z |
| spellingShingle | Sevinj Yolchuyeva Leyla Ebrahimpour Marion Tonneau Fabien Lamaze Michele Orain François Coulombe Julie Malo Wiam Belkaid Bertrand Routy Philippe Joubert Venkata SK. Manem Multi-institutional prognostic modeling of survival outcomes in NSCLC patients treated with first-line immunotherapy using radiomics Journal of Translational Medicine |
| title | Multi-institutional prognostic modeling of survival outcomes in NSCLC patients treated with first-line immunotherapy using radiomics |
| title_full | Multi-institutional prognostic modeling of survival outcomes in NSCLC patients treated with first-line immunotherapy using radiomics |
| title_fullStr | Multi-institutional prognostic modeling of survival outcomes in NSCLC patients treated with first-line immunotherapy using radiomics |
| title_full_unstemmed | Multi-institutional prognostic modeling of survival outcomes in NSCLC patients treated with first-line immunotherapy using radiomics |
| title_short | Multi-institutional prognostic modeling of survival outcomes in NSCLC patients treated with first-line immunotherapy using radiomics |
| title_sort | multi institutional prognostic modeling of survival outcomes in nsclc patients treated with first line immunotherapy using radiomics |
| url | https://doi.org/10.1186/s12967-024-04854-z |
| work_keys_str_mv | AT sevinjyolchuyeva multiinstitutionalprognosticmodelingofsurvivaloutcomesinnsclcpatientstreatedwithfirstlineimmunotherapyusingradiomics AT leylaebrahimpour multiinstitutionalprognosticmodelingofsurvivaloutcomesinnsclcpatientstreatedwithfirstlineimmunotherapyusingradiomics AT mariontonneau multiinstitutionalprognosticmodelingofsurvivaloutcomesinnsclcpatientstreatedwithfirstlineimmunotherapyusingradiomics AT fabienlamaze multiinstitutionalprognosticmodelingofsurvivaloutcomesinnsclcpatientstreatedwithfirstlineimmunotherapyusingradiomics AT micheleorain multiinstitutionalprognosticmodelingofsurvivaloutcomesinnsclcpatientstreatedwithfirstlineimmunotherapyusingradiomics AT francoiscoulombe multiinstitutionalprognosticmodelingofsurvivaloutcomesinnsclcpatientstreatedwithfirstlineimmunotherapyusingradiomics AT juliemalo multiinstitutionalprognosticmodelingofsurvivaloutcomesinnsclcpatientstreatedwithfirstlineimmunotherapyusingradiomics AT wiambelkaid multiinstitutionalprognosticmodelingofsurvivaloutcomesinnsclcpatientstreatedwithfirstlineimmunotherapyusingradiomics AT bertrandrouty multiinstitutionalprognosticmodelingofsurvivaloutcomesinnsclcpatientstreatedwithfirstlineimmunotherapyusingradiomics AT philippejoubert multiinstitutionalprognosticmodelingofsurvivaloutcomesinnsclcpatientstreatedwithfirstlineimmunotherapyusingradiomics AT venkataskmanem multiinstitutionalprognosticmodelingofsurvivaloutcomesinnsclcpatientstreatedwithfirstlineimmunotherapyusingradiomics |