Radiomics to Identify Patients at Risk for Developing Pneumonitis, Differentiate Immune Checkpoint Inhibitor-induced Pneumonitis From Other Lung Inflammation and Distinguish Tumour Pseudo-progression From Real Tumour Growth

Completed

• Conditions: Stage IV Non-small Cell Lung Cancer
• Interventions: Other: No interventions

• Registration Number: NCT03305380
• Lead Sponsor: Maastricht Radiation Oncology

Brief Summary

The investigators will develop a radiomics signature for immune checkpoint-induced pneumonitis in 40 patients with a pulmonary event under anti-PD1 or anti-PD-L1 (cases) and 40 patients without a pulmonary event under anti-PD1 or anti-PD-L1 (controls).

On the basis of the case-control study of patients treated with anti-PD1 or anti-PD-L1, they will further optimise the model using reinforcement machine learning. The model will then be validated in 300 prospective patients.

Detailed Description

Preliminary analyses on a dataset showed a clear distinction in radiomics features for patients with and without pneumonitis from anti-PD1 or anti-PD-L1. Prior experience of the investigators of training and validating radiomics signatures combined with their preliminary exploratory results presented here, will be used to develop a radiomics signature for immune checkpoint-induced pneumonitis in 40 patients with a pulmonary event under anti-PD1 or anti-PD-L1 (cases) and 40 patients without a pulmonary event under anti-PD1 or anti-PD-L1 (controls).

On the basis of the case-control study of patients treated with anti-PD1 or anti-PD-L1, the investigators will be able to further optimise the model using reinforcement machine learning. The model will then be validated in 300 prospective patients.

Study Timeline

• Study Start: 2017-09-01
• Study First Submitted: 2017-09-21
• Study First Submitted QC: 2017-10-03
• Study First Posted: 2017-10-10
• Primary Completion: 2021-01-01
• Study Completion: 2021-04-01
• Status Verified: 2021-09
• Last Update Submitted: 2021-09-15
• Last Update Posted: 2021-09-16

Recruitment & Eligibility

• Status: COMPLETED
• Sex: All
• Target Recruitment: 637

Inclusion Criteria

• Patients who receive standard anti-PD1 or anti-PD-L1 treatment in routine clinical practice for first or second line stage IV non-small cell lung cancer

Exclusion Criteria

• The opposite of the above

Study & Design

• Study Type: OBSERVATIONAL
• Study Design: Not specified

Arm && Interventions

Group	Intervention	Description
Patients with a pulmonary event	No interventions	(under anti-PD1 or anti-PD-L1) This is the first group of the retrospective part of the study.
Patients without a pulmonary event	No interventions	(under anti-PD1 or anti-PD-L1) This is the second group of the retrospective part of the study.

Primary Outcome Measures

Name	Time	Method
Cause of pneumonitis	6 months	Determining cause of the pneumonitis by medical status of the patient

Secondary Outcome Measures

Name	Time	Method
Predictive accuracy of radiomics for determining the cause of pneumonitis	6 months	Three subgroups of immune checkpoint induced pneumonitis: 1. Immune checkpoint-induced pneumonitis from tumour progression; 2. Immune checkpoint-induced pneumonitis from other types of pneumonitis; 3. Patients with interstitial lung disease that are at risk to develop immune checkpoint-induced pneumonitis and those who are not.; Radiomics will be used to predict the cause of pneumonitis

Trial Locations

Locations (2)

Zuyderland Medical Center; 🇳🇱 Heerlen, Netherlands

MUMC+; 🇳🇱 Maastricht, Netherlands