Multi-Reader Retrospective Study Examining Carebot AI CXR 2.0.21-v2.01 Implementation in Everyday Radiology Clinical Practice

Pleural Effusion Clinical Trial

Official title:

Multi-Reader Retrospective Study Examining Carebot AI CXR 2.0.21-v2.01 Implementation in Everyday Radiology Clinical Practice

Clinical Trial Details — Status: Completed

Administrative data

• NCT number: NCT05963945
• Other study ID #: 00002
• Status: Completed
• Start date: October 18, 2022
• Est. completion date: March 21, 2023

Study information

• Verified date: July 2023
• Source: Carebot s.r.o.
• Contact: n/a
• Is FDA regulated: No
• Study type: Observational

Clinical Trial Summary

The primary objective is to evaluate the performance parameters of the proposed DLAD (Carebot AI CXR) in comparison to individual radiologists.

Description:

In the period between October 18th, 2022, and November 17th, 2022, anonymized chest X-ray images of patients were collected at the Radiodiagnostic Department of the Havířov Hospital, p.o. The collection process involved utilizing the CloudPACS imaging and archiving system provided by OR-CZ spol. s r.o.

The collected X-ray images were subjected to the proposed DLAD (Carebot AI CXR) for analysis. Subsequently, the DLAD's performance was compared with the standard clinical practice, where radiologists assessed the CXR images in the simulated hospital setting with access to standard viewing tools (e.g., pan, zoom, WW/WL) and were given an unlimited amount of time to complete the review. Each radiologist determined the presence or absence of 7 indicated radiological findings, including atelectasis (ATE), consolidation (CON), pleural effusion (EFF), pulmonary lesion (LES), subcutaneous emphysema (SCE), cardiomegaly (CMG), and pneumothorax (PNO).

Recruitment information / eligibility

• Status: Completed
• Enrollment: 956
• Est. completion date: March 21, 2023
• Est. primary completion date: November 17, 2022
• Gender: All
• Age group: 18 Years and older

Eligibility

Inclusion Criteria:

• Hospital patients > 18 years who were referred for chest radiography October 18th, 2022, and November 17th, 2022 at the Radiodiagnostic Department of the Havírov Hospital, p.o.

Exclusion Criteria:

• Patients < 18 years

• Chest X-ray images in lateral positions

• Duplicated chest X-ray images

Related Conditions & MeSH terms

• Atelectasis
• Cardiomegaly
• Consolidation
• Emphysema
• Multiple Pulmonary Nodules
• Pleural Effusion
• Pneumothorax
• Pulmonary Atelectasis
• Pulmonary Nodule, Solitary
• Solitary Pulmonary Nodule
• Subcutaneous Emphysema

Intervention

Device:
• Carebot AI CXR
The proposed DLAD (Carebot AI CXR) is a deep learning-based medical device designed to assist radiologists in interpreting chest X-ray images acquired in anteroposterior (AP) or posteroanterior (PA) projection. By employing advanced deep learning algorithms, this solution enables automatic detection of abnormal findings by analyzing visual patterns associated with specific conditions. The targeted abnormalities include atelectasis (ATE), consolidation (CON), pleural effusion (EFF), pulmonary lesion (LES), subcutaneous emphysema (SCE), cardiomegaly (CMG), and pneumothorax (PNO). The DLAD functions as a prediction algorithm complemented by various application peripherals, such as web-based communication tools, DICOM file conversion capabilities, and storage and reporting libraries supporting both DICOM Structured Report and DICOM Presentation State formats.

Locations

Country	Name	City	State
Czechia	Nemocnice Havírov, p. o.	Havírov

Sponsors (1)

Lead Sponsor	Collaborator
Carebot s.r.o.

Country where clinical trial is conducted

Czechia, 

References & Publications (1)

KVAK, Daniel, Anna CHROMCOVÁ, Petra OVESNÁ, Jakub DANDÁR, Marek BIROŠ, Robert HRUBÝ, Daniel DUFEK a Marija PAJDAKOVIC. Can Deep Learning Reliably Recognize Abnormality Patterns on Chest X-rays? A Multi-Reader Study Examining One Month of AI Implementation

Outcome

Type	Measure	Description	Time frame	Safety issue
Primary	Performance test	The primary objective is to evaluate the performance parameters of the proposed DLAD (Carebot AI CXR) in comparison to individual radiologists. The performance test includes sensitivity and specificity, positive and negative likelihood ratio, and positive and negative predictive value. The aforementioned parameters are statistically compared using confidence intervals (CI) and p-Values. The comparison procedure consists of two steps: a global hypothesis test is conducted to determine whether there are significant differences between DLAD and radiologists. If the global hypothesis test yields a significant result, individual hypothesis tests are performed. Additionally, multiple comparison methods, such as McNemar with continuity correction for Se and Sp, Holm method for LRs, and weighted generalized score statistics for PVs, are applied to control the overall error rate. All tests are performed as two-tailed tests at the 5% significance level.	March 2023