An In Silico Trial to Evaluate Prospectively the Performance of a Radiomics Algorithm for UIP Compared to Medical Doctors

Completed

• Conditions: Idiopathic Pulmonary Fibrosis; Interstitial Lung Disease; Radiomics
• Interventions: Other: Radiomics model to classify between IPF with UIP pattern and ILDs without UIP pattern

• Registration Number: NCT05784207
• Lead Sponsor: Maastricht University

Brief Summary

The purpose of this study is to compare AI performance to doctor's performance in the evaluation of IPF/UIP and ILDs without UIP(proven by biopsy).

Detailed Description

Not available

Study Timeline

• Study Start: 2017-06-01
• Study First Submitted: 2021-05-19
• Primary Completion: 2021-12-30
• Study Completion: 2021-12-30
• Status Verified: 2023-03
• Study First Submitted QC: 2023-03-14
• Last Update Submitted: 2023-03-14
• Study First Posted: 2023-03-24
• Last Update Posted: 2023-03-24

Recruitment & Eligibility

• Status: COMPLETED
• Sex: All
• Target Recruitment: 145

Inclusion Criteria

• the availability of non-contrast-enhanced HRCT

Exclusion Criteria

• the use of contrast enhancement
• images containing metal or motion artifacts
• Images reconstructed with a slice thickness larger than 1.5 mm

Study & Design

• Study Type: OBSERVATIONAL
• Study Design: Not specified

Arm && Interventions

Group	Intervention	Description
Normal	Radiomics model to classify between IPF with UIP pattern and ILDs without UIP pattern	Normal healthy patients
IPF/UIP_Biopsy based	Radiomics model to classify between IPF with UIP pattern and ILDs without UIP pattern	patients with a final diagnosis of IPF but a less typical HRCT pattern( lung biopsy required for the diagnosis)
ILD but not IPF and prove by biopsy not UIP	Radiomics model to classify between IPF with UIP pattern and ILDs without UIP pattern	patients with an ILD and a pathological non-UIP pattern
IPF/UIP_CT based	Radiomics model to classify between IPF with UIP pattern and ILDs without UIP pattern	patients with an ILD and a pathological UIP pattern and a final diagnosis of IPF

Primary Outcome Measures

Name	Time	Method
The performance of Radiomics algorithm compared to the ground truth	May 2021	Reporting the performance measure: accuracy

Secondary Outcome Measures

Name	Time	Method
Comparing the performance of the radiomics algorithm to that of physicians	June 2021	Correctness of the diagnosis - the most probable thin-section pattern (dichotomous outcome: yes or no)

Trial Locations

Locations (1)

Maastricht University; 🇳🇱 Maastricht, Limburg, Netherlands