Post-deployment performance of a deep learning algorithm for normal and abnormal chest X-ray classification: A study at visa screening centers in the United Arab Emirates

Background: Chest radiographs (CXRs) are widely used to screen for infectious diseases like tuberculosis and COVID-19 among migrants. At such high-volume settings, manual CXR reporting is challenging and integrating artificial intelligence (AI) algorithms into the workflow help to rule out normal fi...

Full description

Saved in:
Bibliographic Details
Main Authors: Amina Abdelqadir Mohamed AlJasmi, Hatem Ghonim, Mohyi Eldin Fahmy, Aswathy Nair, Shamie Kumar, Dennis Robert, Afrah Abdikarim Mohamed, Hany Abdou, Anumeha Srivastava, Bhargava Reddy
Format: Article
Language:English
Published: Elsevier 2024-12-01
Series:European Journal of Radiology Open
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S2352047724000613
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846122150463799296
author Amina Abdelqadir Mohamed AlJasmi
Hatem Ghonim
Mohyi Eldin Fahmy
Aswathy Nair
Shamie Kumar
Dennis Robert
Afrah Abdikarim Mohamed
Hany Abdou
Anumeha Srivastava
Bhargava Reddy
author_facet Amina Abdelqadir Mohamed AlJasmi
Hatem Ghonim
Mohyi Eldin Fahmy
Aswathy Nair
Shamie Kumar
Dennis Robert
Afrah Abdikarim Mohamed
Hany Abdou
Anumeha Srivastava
Bhargava Reddy
author_sort Amina Abdelqadir Mohamed AlJasmi
collection DOAJ
description Background: Chest radiographs (CXRs) are widely used to screen for infectious diseases like tuberculosis and COVID-19 among migrants. At such high-volume settings, manual CXR reporting is challenging and integrating artificial intelligence (AI) algorithms into the workflow help to rule out normal findings in minutes, allowing radiologists to focus on abnormal cases. Methods: In this post-deployment study, all the CXRs acquired during the visa screening process across 33 centers in United Arab Emirates from January 2021 to June 2022 (18 months) were included. The qXR v2.1 chest X-ray interpretation software was used to classify the scans into normal and abnormal, and its agreement against radiologist was evaluated. Additionally, a digital survey was conducted among 20 healthcare professionals with prior AI experience to understand real-world implementation challenges and impact. Results: The analysis of 1309,443 CXRs from 1309,431 patients (median age: 35 years; IQR [29–42]; 1030,071 males [78.7 %]) in this study revealed a Negative Predictive Value (NPV) of 99.92 % (95 % CI: 99.92, 99.93), Positive Predictive Value (PPV) of 5.06 % (95 % CI: 4.99, 5.13) and overall percent agreement of the AI with radiologists of 72.90 % (95 % CI: 72.82, 72.98). In the survey, majority (88.2 %) of the radiologists agreed to turnaround time reduction after AI integration, while 82 % suggested that the AI improved their diagnostic accuracy. Discussion: In contrast with the existing studies, this research uses a substantially large data. A high NPV and satisfactory agreement with human readers indicate that AI can reliably identify normal CXRs, making it suitable for routine applications.
format Article
id doaj-art-fbcaf92bcf6f4b19a639e38a043165f5
institution Kabale University
issn 2352-0477
language English
publishDate 2024-12-01
publisher Elsevier
record_format Article
series European Journal of Radiology Open
spelling doaj-art-fbcaf92bcf6f4b19a639e38a043165f52024-12-15T06:15:49ZengElsevierEuropean Journal of Radiology Open2352-04772024-12-0113100606Post-deployment performance of a deep learning algorithm for normal and abnormal chest X-ray classification: A study at visa screening centers in the United Arab EmiratesAmina Abdelqadir Mohamed AlJasmi0Hatem Ghonim1Mohyi Eldin Fahmy2Aswathy Nair3Shamie Kumar4Dennis Robert5Afrah Abdikarim Mohamed6Hany Abdou7Anumeha Srivastava8Bhargava Reddy9Emirates Health Services, DSO Digital Park Building A8, Dubai Silicon Oasis, Dubai, UAEUnison Capital Investment LLC, Park Heights Square, Dubai Hills Estate, UAEUnison Capital Investment LLC, Park Heights Square, Dubai Hills Estate, UAEQure.ai Technologies Pvt Ltd, Prestige Summit, 6, St Johns Rd, Halasuru, Bengaluru, India; Correspondence to: Qure.ai, Bengaluru, Karnataka, India.Qure.ai Technologies Pvt Ltd, Prestige Summit, 6, St Johns Rd, Halasuru, Bengaluru, IndiaQure.ai Technologies Pvt Ltd, Prestige Summit, 6, St Johns Rd, Halasuru, Bengaluru, IndiaEmirates Health Services, DSO Digital Park Building A8, Dubai Silicon Oasis, Dubai, UAEUnison Capital Investment LLC, Park Heights Square, Dubai Hills Estate, UAEQure.ai Technologies Pvt Ltd, Prestige Summit, 6, St Johns Rd, Halasuru, Bengaluru, IndiaQure.ai Technologies Pvt Ltd, Prestige Summit, 6, St Johns Rd, Halasuru, Bengaluru, IndiaBackground: Chest radiographs (CXRs) are widely used to screen for infectious diseases like tuberculosis and COVID-19 among migrants. At such high-volume settings, manual CXR reporting is challenging and integrating artificial intelligence (AI) algorithms into the workflow help to rule out normal findings in minutes, allowing radiologists to focus on abnormal cases. Methods: In this post-deployment study, all the CXRs acquired during the visa screening process across 33 centers in United Arab Emirates from January 2021 to June 2022 (18 months) were included. The qXR v2.1 chest X-ray interpretation software was used to classify the scans into normal and abnormal, and its agreement against radiologist was evaluated. Additionally, a digital survey was conducted among 20 healthcare professionals with prior AI experience to understand real-world implementation challenges and impact. Results: The analysis of 1309,443 CXRs from 1309,431 patients (median age: 35 years; IQR [29–42]; 1030,071 males [78.7 %]) in this study revealed a Negative Predictive Value (NPV) of 99.92 % (95 % CI: 99.92, 99.93), Positive Predictive Value (PPV) of 5.06 % (95 % CI: 4.99, 5.13) and overall percent agreement of the AI with radiologists of 72.90 % (95 % CI: 72.82, 72.98). In the survey, majority (88.2 %) of the radiologists agreed to turnaround time reduction after AI integration, while 82 % suggested that the AI improved their diagnostic accuracy. Discussion: In contrast with the existing studies, this research uses a substantially large data. A high NPV and satisfactory agreement with human readers indicate that AI can reliably identify normal CXRs, making it suitable for routine applications.http://www.sciencedirect.com/science/article/pii/S2352047724000613Chest radiographAbnormalityVisa screeningArtificial intelligenceWorkflowAgreement
spellingShingle Amina Abdelqadir Mohamed AlJasmi
Hatem Ghonim
Mohyi Eldin Fahmy
Aswathy Nair
Shamie Kumar
Dennis Robert
Afrah Abdikarim Mohamed
Hany Abdou
Anumeha Srivastava
Bhargava Reddy
Post-deployment performance of a deep learning algorithm for normal and abnormal chest X-ray classification: A study at visa screening centers in the United Arab Emirates
European Journal of Radiology Open
Chest radiograph
Abnormality
Visa screening
Artificial intelligence
Workflow
Agreement
title Post-deployment performance of a deep learning algorithm for normal and abnormal chest X-ray classification: A study at visa screening centers in the United Arab Emirates
title_full Post-deployment performance of a deep learning algorithm for normal and abnormal chest X-ray classification: A study at visa screening centers in the United Arab Emirates
title_fullStr Post-deployment performance of a deep learning algorithm for normal and abnormal chest X-ray classification: A study at visa screening centers in the United Arab Emirates
title_full_unstemmed Post-deployment performance of a deep learning algorithm for normal and abnormal chest X-ray classification: A study at visa screening centers in the United Arab Emirates
title_short Post-deployment performance of a deep learning algorithm for normal and abnormal chest X-ray classification: A study at visa screening centers in the United Arab Emirates
title_sort post deployment performance of a deep learning algorithm for normal and abnormal chest x ray classification a study at visa screening centers in the united arab emirates
topic Chest radiograph
Abnormality
Visa screening
Artificial intelligence
Workflow
Agreement
url http://www.sciencedirect.com/science/article/pii/S2352047724000613
work_keys_str_mv AT aminaabdelqadirmohamedaljasmi postdeploymentperformanceofadeeplearningalgorithmfornormalandabnormalchestxrayclassificationastudyatvisascreeningcentersintheunitedarabemirates
AT hatemghonim postdeploymentperformanceofadeeplearningalgorithmfornormalandabnormalchestxrayclassificationastudyatvisascreeningcentersintheunitedarabemirates
AT mohyieldinfahmy postdeploymentperformanceofadeeplearningalgorithmfornormalandabnormalchestxrayclassificationastudyatvisascreeningcentersintheunitedarabemirates
AT aswathynair postdeploymentperformanceofadeeplearningalgorithmfornormalandabnormalchestxrayclassificationastudyatvisascreeningcentersintheunitedarabemirates
AT shamiekumar postdeploymentperformanceofadeeplearningalgorithmfornormalandabnormalchestxrayclassificationastudyatvisascreeningcentersintheunitedarabemirates
AT dennisrobert postdeploymentperformanceofadeeplearningalgorithmfornormalandabnormalchestxrayclassificationastudyatvisascreeningcentersintheunitedarabemirates
AT afrahabdikarimmohamed postdeploymentperformanceofadeeplearningalgorithmfornormalandabnormalchestxrayclassificationastudyatvisascreeningcentersintheunitedarabemirates
AT hanyabdou postdeploymentperformanceofadeeplearningalgorithmfornormalandabnormalchestxrayclassificationastudyatvisascreeningcentersintheunitedarabemirates
AT anumehasrivastava postdeploymentperformanceofadeeplearningalgorithmfornormalandabnormalchestxrayclassificationastudyatvisascreeningcentersintheunitedarabemirates
AT bhargavareddy postdeploymentperformanceofadeeplearningalgorithmfornormalandabnormalchestxrayclassificationastudyatvisascreeningcentersintheunitedarabemirates