DEEP-Lung-IV study

Utilize a robust deep learning approach to understand NSCLC prognosis and treatment responses

Discover the DEEP-Lung-IV study

In today’s intricate healthcare landscape, the evaluation of patient data is often compartmentalized, restricting analysis to one modality at a time. This segmented approach presents a substantial challenge in identifying cohorts of metastatic non-small cell lung cancer (NSCLC) patients. DEEP-Lung-IV represents a global effort to tackle this challenge. It is a multicentric and multimodal observational study focused on unraveling intricate signals linked to treatment responses and prognosis in stage IV NSCLC. By integrating and analyzing clinical, biological, genomics, and radiomics biomarkers, we aim to unlock predictive signatures and precise and invaluable insights from longitudinal study subject data.

Study type: Observational

Cohorts:
• Pembrolizumab monotherapy
• Chemotherapy
• Combination therapy

Clinical Trials Identifier: NCT04994795

Start date: July 16, 2021

Study Sponsor: SOPHiA GENETICS

International study coordinator:
Jacques Cadranel

In-depth study goals of DEEP-Lung-IV

DEEP-Lung-IV is an observational study combining data from different modalities at multiple time points to:

Stratify cohorts based on Progression Free Survival (PFS) and Overall Survival (OS)

Build algorithms aiming to predict treatment response at the first evaluation

In this study, we aim to integrate multimodal biomarkers within a unified workflow to enhance the precision of prognosis and optimize first-line treatment planning. Our approach harnesses real-world data to build and train predictive algorithms. Using routine standard-of-care data sources minimizes disruptions and facilitates widespread adoption of the predictive algorithms rather than introducing novel tests. These advanced predictive algorithms will result in new insights into the outcome of different treatments.

DEEP-Lung-IV in numbers:

∼2,000

Enrolled patients

Participating sites

Countries

France

Avicenne Hospital
CHU Bordeaux
Ambroise Paré Hospital
Hospices Civils de Lyon
CHU de Nantes
La Pitié Salpêtrière
Tenon Hospital
Foch Hospital
Centre Hospitalier de Toulon

Spain

Fundacion Jimenez Diaz
Puerta De Hierro Hospital
Instituto Valenciano De Oncologia

Italy

University Hospital Of Parma
Azienda Sanitaria Universitaria Friuli Centrale (ASU FC)
Fondazione Policlinico Gemelli

Germany

University Hospital Leipzig

Israel

Shaare Zedek Medical Center
Sourasky Medical Center

USA

Holden Comprehensive Cancer Center at University of Iowa Health Care
UMASS Memorial Health
Mayo Clinic
Roswell Park Comprehensive Cancer Center
Huntsman Cancer Institute
Carbone Comprehensive Cancer Center at University of Wisconsin

Canada

Sunnybrook Health Sciences Centre Toronto

Brazil

DASA - Hospital Brasilia
DASA - Hospital de Niteroi
DASA - Hospital São Lucas
DASA - Hospital Nove De Julho
AC Camargo

“This international and multicentric project addresses an important translational research question in a pragmatic way. In the first-line treatment setting for metastatic non-small cell lung cancer (NSCLC), we are now faced with multiple treatment options and yet, the absence of robust predictors of the efficacy of immunotherapy may lead us to prescribe combination therapy to almost all our patients. Despite the abundance of predictive signals, we currently lack the ability to identify which patients will derive maximum benefits from specific treatments. In the DEEP-Lung-IV study, we aim to integrate these individual and discrete signals into a deep learning-based framework to decipher valuable information.”

Prof. Jacques Cadranel

International study coordinator, Department of Pulmonology and Thoracic Oncology, Tenon Hospital, AP-HP and Sorbonne University, Paris, France

“This international and multicentric project addresses an important translational research question in a pragmatic way. In the first-line treatment setting for metastatic non-small cell lung cancer (NSCLC), we are now faced with multiple treatment options and yet, the absence of robust predictors of the efficacy of immunotherapy may lead us to prescribe combination therapy to almost all our patients. Despite the abundance of predictive signals, we currently lack the ability to identify which patients will derive maximum benefits from specific treatments. In the DEEP-Lung-IV study, we aim to integrate these individual and discrete signals into a deep learning-based framework to decipher valuable information.”
Prof. Jacques Cadranel
International study coordinator, Department of Pulmonology and Thoracic Oncology, Tenon Hospital, AP-HP and Sorbonne University, Paris, France

Enhancing analysis for stage IV NSCLC

From comprehensive data visualization…

In addition to aggregating biological, clinical, and genomics data, DEEP-Lung-IV also capitalizes on routine medical imaging to source new biomarkers. Imaging is non-invasive, readily available, and repeatable, but it can be difficult to translate test results into quantitative features. By developing a comprehensive visualization environment, DEEP-Lung-IV aims to bridge this gap and generate data sets for the identification of biomarkers.

… to algorithm training and validation

To understand the impact of immunotherapy on NSCLC treatment response and prognosis, the study was split into three cohorts based on treatment type.

Two-thirds of each cohort was randomized into a training cohort, while the remaining one-third served as an independent evaluation set to assess the accuracy and performance. This rigorous methodology ensures an objective and comprehensive evaluation of our predictive algorithms.

SOPHiA GENETICS products are for Research Use Only and not for use in diagnostic procedures unless specified otherwise.

SOPHiA DDM™ Dx Hereditary Cancer Solution, SOPHiA DDM™ Dx RNAtarget Oncology Solution and SOPHiA DDM™ Dx Homologous Recombination Deficiency Solution are available as CE-IVD products for In Vitro Diagnostic Use in the European Economic Area (EEA), the United Kingdom and Switzerland. SOPHiA DDM™ Dx Myeloid Solution and SOPHiA DDM™ Dx Solid Tumor Solution are available as CE-IVD products for In Vitro Diagnostic Use in the EEA, the United Kingdom, Switzerland, and Israel. Information about products that may or may not be available in different countries and if applicable, may or may not have received approval or market clearance by a governmental regulatory body for different indications for use. Please contact us at [email protected] to obtain the appropriate product information for your country of residence.

All third-party trademarks listed by SOPHiA GENETICS remain the property of their respective owners. Unless specifically identified as such, SOPHiA GENETICS’ use of third-party trademarks does not indicate any relationship, sponsorship, or endorsement between SOPHiA GENETICS and the owners of these trademarks. Any references by SOPHiA GENETICS to third-party trademarks is to identify the corresponding third-party goods and/or services and shall be considered nominative fair use under the trademark law.

DEEP-Lung-IV study

Utilize a robust deep learning approach to understand NSCLC prognosis and treatment responses

Discover the DEEP-Lung-IV study

In-depth study goals of DEEP-Lung-IV

DEEP-Lung-IV in numbers:

Prof. Jacques Cadranel

Prof. Jacques Cadranel

Enhancing analysis for stage IV NSCLC

From comprehensive data visualization…

… to algorithm training and validation

SOPHiA DDM™ Overview

SOPHiA DDM™ for Genomics

SOPHiA DDM™ for Radiomics

SOPHiA DDM™ for Multimodal

Professional Services