Retrospective Study of Carebot AI CXR Performance in Preclinical Practice

NCT05594485 | Completed DMC

• 1 other identifier: 00001
• Study Type: observational
• Target: 127
• Locations: 1 country
• Sites: 1

Brief Summary

The purpose of this study is to describe the design, methodology and evaluation of the preclinical test of Carebot AI CXR software, and to provide evidence that the investigated medical device meets user requirements in accordance with its intended use. Carebot AI CXR is defined as a recommendation system (classification "prediction") based on computer-aided detection. The software can be used in a preclinical deployment at a selected site before interpretation (prioritization, display of all results and heatmaps) or after interpretation (verification of findings) of CXR images, and in accordance with the manufacturer's recommendations. Given this, a retrospective study is performed to test the clinical effectiveness on existing CXRs.

Conditions

Artificial Intelligence; Lung Diseases; Pneumothorax; Pleural Effusion; Cardiomegaly; Lung Cancer; Pulmonary Edema; Consolidation; Pneumonia; Atelectasis; Hilar Calcification; Fracture Rib

Outcome Measures

Primary Outcomes (1)

• Primary objective

  Comparison of the accuracy of radiologist and Carebot AI CXR image assessment.

  20-10-2022

Secondary Outcomes (1)

• Secondary objective

  20-10-2022

Study Arms (1)

Retrospective collection of DICOM patient files for the period 15-17 August

To collect the CXR data for retrospective study, we addressed a municipal hospital in the Czech Republic that provides healthcare services to up to 130,000 residents of a medium-sized city (approximately 70,000 inhabitants) and the surrounding area. 127 anonymized CXR images were collected between August 15 and 17, 2022, and subsequently submitted to five independent radiologists of varying experience for annotation. The selected radiologists were asked to assess whether the CXR image shows any of the 12 abnormalities mentioned above. Pediatric CXR images (under 18 years of age), scans with technical problems (poor image quality, rotation), and images in lateral projection were excluded from the dataset.

Device: Carebot AI CXR

Interventions

Carebot AI CXR DEVICE

Carebot AI CXR is a deep learning-based software that assists radiologists in the interpretation of chest radiographs in posterior-anterior (PA) or anterior-posterior (AP) projections. The solution with artificial intelligence automatically detects abnormality based on visual patterns for the following findings: atelectasis, consolidation, cardiomegaly, mediastinal widening, pneumoperitoneum, pneumothorax, pulmonary edema, pulmonary lesion, bone fracture, hilar enlargement, subcutaneous emphysema, and pleural effusion.

Retrospective collection of DICOM patient files for the period 15-17 August

Eligibility Criteria

• Age: 18 Years+
• Sex: all
• Healthy Volunteers: No
• Age Groups: Adult (18-64), Older Adult (65+)
• Sampling Method: Non-Probability Sample

Study Population

To collect the CXR data for retrospective study, we addressed a municipal hospital in the Czech Republic that provides healthcare services to up to 130,000 residents of a medium-sized city (approximately 70,000 inhabitants) and the surrounding area. 127 anonymized CXR images were collected between August 15 and 17, 2022.

You may qualify if:

• Hospital patients who were referred for chest radiography between August 15 and 17, 2022.

You may not qualify if:

• Pediatric CXR images (under 18 years of age)
• Scans with technical problems (poor image quality, rotation)
• Images in lateral projection

Sponsors & Collaborators

• Carebot s.r.o.: lead

Study Sites (1)

Nemocnice Havířov, p. o.

Havířov, 73601, Czechia

Location

MeSH Terms

Conditions

Lung Diseases; Pneumothorax; Pleural Effusion; Cardiomegaly; Lung Neoplasms; Pulmonary Edema; Pneumonia; Pulmonary Atelectasis; Rib Fractures

Condition Hierarchy (Ancestors)

Respiratory Tract Diseases; Pleural Diseases; Heart Diseases; Cardiovascular Diseases; Hypertrophy; Pathological Conditions, Anatomical; Pathological Conditions, Signs and Symptoms; Respiratory Tract Neoplasms; Thoracic Neoplasms; Neoplasms by Site; Neoplasms; Respiratory Tract Infections; Infections; Fractures, Bone; Wounds and Injuries; Thoracic Injuries

Study Design

• Study Type: observational
• Observational Model: COHORT
• Time Perspective: RETROSPECTIVE
• Sponsor Type: INDUSTRY
• Responsible Party: SPONSOR

Study Record Dates

• First Submitted: October 21, 2022
• First Posted: October 26, 2022
• Study Start: August 15, 2022
• Primary Completion: August 17, 2022
• Study Completion: October 20, 2022
• Last Updated: July 13, 2023

Record last verified: 2023-07

Data Sharing

• IPD Sharing: Will not share

Locations

CZ (1)