NCT05711914: Onc AI

Predicting Response to PD-1 Checkpoint Blockade Using Deep Learning Analysis of Imaging and Clinical Data

Completed Last updated 3 February 2023

What this trial tests

trial in Non-small Cell Lung Cancer (NSCLC) in 300 participants. Completed in 31 December 2022.

Timeline

31 January 2021

Primary endpoint
31 March 2022

31 December 2022

Quick facts

Lead sponsor	Centre Hospitalier Universitaire de Nīmes
Status	Completed
Study type	OBSERVATIONAL
Enrollment	300
Start date	31 January 2021
Primary completion	31 March 2022
Estimated completion	31 December 2022
Sites	1 location across France

Conditions studied

• Non-small Cell Lung Cancer (NSCLC) — all drugs for Non-small Cell Lung Cancer (NSCLC) →

Sponsor

Centre Hospitalier Universitaire de Nīmes

Who can join

Adults 18 to 100, any sex, with Non-small Cell Lung Cancer (NSCLC). Patients with the condition only — healthy volunteers not accepted.

Sponsor's own description

Immunotherapy has transformed cancer treatment with the PD-1 class of checkpoint inhibitors - pembrolizumab and nivolumab -- demonstrating durable responses in Stage IV metastatic tumors such as non-small cell lung cancer and melanoma. Despite these numerous successes, PD-1/PD-L1 checkpoint blockade therapies do have a number of shortcomings.

Many approaches to predict response to PD-1/PD-L1 checkpoint therapy have been investigated with limited success. Recent efforts exploring the utility of quantitative imaging biomarkers to predict response to PD-\[L\]1 immunotherapy have shown promise. The purpose of this retrospective multicenter study is to develop a multi-omic classifier to predict response to PD-1/PD-L1 checkpoint blockade for mutation negative (EGFR, ALK and ROS1) NSCLC

Publications & conference data

No peer-reviewed publications indexed yet for this trial. Completed trials usually publish results within 12-18 months.