Integration of clinical, pathological, radiological, and transcriptomic data improves prediction for first-line immunotherapy outcome in metastatic non-small cell lung cancer
Abstract Immunotherapy is improving the survival of patients with metastatic non-small cell lung cancer (NSCLC), yet reliable biomarkers are needed to identify responders prospectively and optimize patient care. In this study, we explore the benefits of multimodal approaches to predict immunotherapy...
Saved in:
| Main Authors: | , , , , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2025-01-01
|
| Series: | Nature Communications |
| Online Access: | https://doi.org/10.1038/s41467-025-55847-5 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832594540284870656 |
|---|---|
| author | Nicolas Captier Marvin Lerousseau Fanny Orlhac Narinée Hovhannisyan-Baghdasarian Marie Luporsi Erwin Woff Sarah Lagha Paulette Salamoun Feghali Christine Lonjou Clément Beaulaton Andrei Zinovyev Hélène Salmon Thomas Walter Irène Buvat Nicolas Girard Emmanuel Barillot |
| author_facet | Nicolas Captier Marvin Lerousseau Fanny Orlhac Narinée Hovhannisyan-Baghdasarian Marie Luporsi Erwin Woff Sarah Lagha Paulette Salamoun Feghali Christine Lonjou Clément Beaulaton Andrei Zinovyev Hélène Salmon Thomas Walter Irène Buvat Nicolas Girard Emmanuel Barillot |
| author_sort | Nicolas Captier |
| collection | DOAJ |
| description | Abstract Immunotherapy is improving the survival of patients with metastatic non-small cell lung cancer (NSCLC), yet reliable biomarkers are needed to identify responders prospectively and optimize patient care. In this study, we explore the benefits of multimodal approaches to predict immunotherapy outcome using multiple machine learning algorithms and integration strategies. We analyze baseline multimodal data from a cohort of 317 metastatic NSCLC patients treated with first-line immunotherapy, including positron emission tomography images, digitized pathological slides, bulk transcriptomic profiles, and clinical information. Testing multiple integration strategies, most of them yield multimodal models surpassing both the best unimodal models and established univariate biomarkers, such as PD-L1 expression. Additionally, several multimodal combinations demonstrate improved patient risk stratification compared to models built with routine clinical features only. Our study thus provides evidence of the superiority of multimodal over unimodal approaches, advocating for the collection of large multimodal NSCLC datasets to develop and validate robust and powerful immunotherapy biomarkers. |
| format | Article |
| id | doaj-art-31249822e74440e199f362001f3cb902 |
| institution | Kabale University |
| issn | 2041-1723 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Nature Communications |
| spelling | doaj-art-31249822e74440e199f362001f3cb9022025-01-19T12:32:21ZengNature PortfolioNature Communications2041-17232025-01-0116111910.1038/s41467-025-55847-5Integration of clinical, pathological, radiological, and transcriptomic data improves prediction for first-line immunotherapy outcome in metastatic non-small cell lung cancerNicolas Captier0Marvin Lerousseau1Fanny Orlhac2Narinée Hovhannisyan-Baghdasarian3Marie Luporsi4Erwin Woff5Sarah Lagha6Paulette Salamoun Feghali7Christine Lonjou8Clément Beaulaton9Andrei Zinovyev10Hélène Salmon11Thomas Walter12Irène Buvat13Nicolas Girard14Emmanuel Barillot15Laboratoire d’Imagerie Translationnelle en Oncologie, Institut Curie, Inserm U1288, PSL Research UniversityBioinformatics and computational systems biology of cancer, Institut Curie, Inserm U900, PSL Research UniversityLaboratoire d’Imagerie Translationnelle en Oncologie, Institut Curie, Inserm U1288, PSL Research UniversityLaboratoire d’Imagerie Translationnelle en Oncologie, Institut Curie, Inserm U1288, PSL Research UniversityLaboratoire d’Imagerie Translationnelle en Oncologie, Institut Curie, Inserm U1288, PSL Research UniversityLaboratoire d’Imagerie Translationnelle en Oncologie, Institut Curie, Inserm U1288, PSL Research UniversityInstitut du Thorax Curie-Montsouris, Institut CurieInstitut du Thorax Curie-Montsouris, Institut CurieBioinformatics and computational systems biology of cancer, Institut Curie, Inserm U900, PSL Research UniversityDepartment of pathology, Institut CurieIn silico R&D, EvotecImmunity and cancer, Institut Curie, Inserm U932, PSL Research UniversityBioinformatics and computational systems biology of cancer, Institut Curie, Inserm U900, PSL Research UniversityLaboratoire d’Imagerie Translationnelle en Oncologie, Institut Curie, Inserm U1288, PSL Research UniversityInstitut du Thorax Curie-Montsouris, Institut CurieBioinformatics and computational systems biology of cancer, Institut Curie, Inserm U900, PSL Research UniversityAbstract Immunotherapy is improving the survival of patients with metastatic non-small cell lung cancer (NSCLC), yet reliable biomarkers are needed to identify responders prospectively and optimize patient care. In this study, we explore the benefits of multimodal approaches to predict immunotherapy outcome using multiple machine learning algorithms and integration strategies. We analyze baseline multimodal data from a cohort of 317 metastatic NSCLC patients treated with first-line immunotherapy, including positron emission tomography images, digitized pathological slides, bulk transcriptomic profiles, and clinical information. Testing multiple integration strategies, most of them yield multimodal models surpassing both the best unimodal models and established univariate biomarkers, such as PD-L1 expression. Additionally, several multimodal combinations demonstrate improved patient risk stratification compared to models built with routine clinical features only. Our study thus provides evidence of the superiority of multimodal over unimodal approaches, advocating for the collection of large multimodal NSCLC datasets to develop and validate robust and powerful immunotherapy biomarkers.https://doi.org/10.1038/s41467-025-55847-5 |
| spellingShingle | Nicolas Captier Marvin Lerousseau Fanny Orlhac Narinée Hovhannisyan-Baghdasarian Marie Luporsi Erwin Woff Sarah Lagha Paulette Salamoun Feghali Christine Lonjou Clément Beaulaton Andrei Zinovyev Hélène Salmon Thomas Walter Irène Buvat Nicolas Girard Emmanuel Barillot Integration of clinical, pathological, radiological, and transcriptomic data improves prediction for first-line immunotherapy outcome in metastatic non-small cell lung cancer Nature Communications |
| title | Integration of clinical, pathological, radiological, and transcriptomic data improves prediction for first-line immunotherapy outcome in metastatic non-small cell lung cancer |
| title_full | Integration of clinical, pathological, radiological, and transcriptomic data improves prediction for first-line immunotherapy outcome in metastatic non-small cell lung cancer |
| title_fullStr | Integration of clinical, pathological, radiological, and transcriptomic data improves prediction for first-line immunotherapy outcome in metastatic non-small cell lung cancer |
| title_full_unstemmed | Integration of clinical, pathological, radiological, and transcriptomic data improves prediction for first-line immunotherapy outcome in metastatic non-small cell lung cancer |
| title_short | Integration of clinical, pathological, radiological, and transcriptomic data improves prediction for first-line immunotherapy outcome in metastatic non-small cell lung cancer |
| title_sort | integration of clinical pathological radiological and transcriptomic data improves prediction for first line immunotherapy outcome in metastatic non small cell lung cancer |
| url | https://doi.org/10.1038/s41467-025-55847-5 |
| work_keys_str_mv | AT nicolascaptier integrationofclinicalpathologicalradiologicalandtranscriptomicdataimprovespredictionforfirstlineimmunotherapyoutcomeinmetastaticnonsmallcelllungcancer AT marvinlerousseau integrationofclinicalpathologicalradiologicalandtranscriptomicdataimprovespredictionforfirstlineimmunotherapyoutcomeinmetastaticnonsmallcelllungcancer AT fannyorlhac integrationofclinicalpathologicalradiologicalandtranscriptomicdataimprovespredictionforfirstlineimmunotherapyoutcomeinmetastaticnonsmallcelllungcancer AT narineehovhannisyanbaghdasarian integrationofclinicalpathologicalradiologicalandtranscriptomicdataimprovespredictionforfirstlineimmunotherapyoutcomeinmetastaticnonsmallcelllungcancer AT marieluporsi integrationofclinicalpathologicalradiologicalandtranscriptomicdataimprovespredictionforfirstlineimmunotherapyoutcomeinmetastaticnonsmallcelllungcancer AT erwinwoff integrationofclinicalpathologicalradiologicalandtranscriptomicdataimprovespredictionforfirstlineimmunotherapyoutcomeinmetastaticnonsmallcelllungcancer AT sarahlagha integrationofclinicalpathologicalradiologicalandtranscriptomicdataimprovespredictionforfirstlineimmunotherapyoutcomeinmetastaticnonsmallcelllungcancer AT paulettesalamounfeghali integrationofclinicalpathologicalradiologicalandtranscriptomicdataimprovespredictionforfirstlineimmunotherapyoutcomeinmetastaticnonsmallcelllungcancer AT christinelonjou integrationofclinicalpathologicalradiologicalandtranscriptomicdataimprovespredictionforfirstlineimmunotherapyoutcomeinmetastaticnonsmallcelllungcancer AT clementbeaulaton integrationofclinicalpathologicalradiologicalandtranscriptomicdataimprovespredictionforfirstlineimmunotherapyoutcomeinmetastaticnonsmallcelllungcancer AT andreizinovyev integrationofclinicalpathologicalradiologicalandtranscriptomicdataimprovespredictionforfirstlineimmunotherapyoutcomeinmetastaticnonsmallcelllungcancer AT helenesalmon integrationofclinicalpathologicalradiologicalandtranscriptomicdataimprovespredictionforfirstlineimmunotherapyoutcomeinmetastaticnonsmallcelllungcancer AT thomaswalter integrationofclinicalpathologicalradiologicalandtranscriptomicdataimprovespredictionforfirstlineimmunotherapyoutcomeinmetastaticnonsmallcelllungcancer AT irenebuvat integrationofclinicalpathologicalradiologicalandtranscriptomicdataimprovespredictionforfirstlineimmunotherapyoutcomeinmetastaticnonsmallcelllungcancer AT nicolasgirard integrationofclinicalpathologicalradiologicalandtranscriptomicdataimprovespredictionforfirstlineimmunotherapyoutcomeinmetastaticnonsmallcelllungcancer AT emmanuelbarillot integrationofclinicalpathologicalradiologicalandtranscriptomicdataimprovespredictionforfirstlineimmunotherapyoutcomeinmetastaticnonsmallcelllungcancer |