Integration of clinical, pathological, radiological, and transcriptomic data improves prediction for first-line immunotherapy outcome in metastatic non-small cell lung cancer
Inserm · Université Paris Sciences et Lettres · +5 more institutions
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…
Citation impact
- FWCI
- 50.09
- Percentile
- 100%
- References
- 49
Authors
16- NCNicolas CaptierCorresponding
Inserm, Université Paris Sciences et Lettres, Institut Curie
- MLMarvin Lerousseau
Inserm, ParisTech, Université Paris Sciences et Lettres, Institut Curie
- FOFanny Orlhac
Inserm, Université Paris Sciences et Lettres, Institut Curie
- NHNarinée Hovhannisyan‐Baghdasarian
Inserm, Université Paris Sciences et Lettres, Institut Curie
- MLMarie Luporsi
Inserm, Université Paris Sciences et Lettres, Institut Curie
Topics & keywords
- Immunotherapy
- Multimodal therapy
- Univariate
- Medicine
- Clinical trial
- Lung cancer
- Oncology
- Pathological