Assessment of a combined musculoskeletal and chest deep learning-based detection solution in an emergency setting
Rationale and objectives: Triage and diagnostic deep learning-based support solutions have started to take hold in everyday emergency radiology practice with the hope of alleviating workflows. Although previous works had proven that artificial intelligence (AI) may increase radiologist and/or emerge...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Elsevier
2023-01-01
|
Series: | European Journal of Radiology Open |
Subjects: | |
Online Access: | http://www.sciencedirect.com/science/article/pii/S2352047723000084 |
_version_ | 1797802213329862656 |
---|---|
author | Alexandre Parpaleix Clémence Parsy Marina Cordari Mehdi Mejdoubi |
author_facet | Alexandre Parpaleix Clémence Parsy Marina Cordari Mehdi Mejdoubi |
author_sort | Alexandre Parpaleix |
collection | DOAJ |
description | Rationale and objectives: Triage and diagnostic deep learning-based support solutions have started to take hold in everyday emergency radiology practice with the hope of alleviating workflows. Although previous works had proven that artificial intelligence (AI) may increase radiologist and/or emergency physician reading performances, they were restricted to finding, bodypart and/or age subgroups, without evaluating a routine emergency workflow composed of chest and musculoskeletal adult and pediatric cases. We aimed at evaluating a multiple musculoskeletal and chest radiographic findings deep learning-based commercial solution on an adult and pediatric emergency workflow, focusing on discrepancies between emergency and radiology physicians. Material and methods: This retrospective, monocentric and observational study included 1772 patients who underwent an emergency radiograph between July and October 2020, excluding spine, skull and plain abdomen procedures. Emergency and radiology reports, obtained without AI as part of the clinical workflow, were collected and discordant cases were reviewed to obtain the radiology reference standard. Case-level AI outputs and emergency reports were compared to the reference standard. DeLong and Wald tests were used to compare ROC-AUC and Sensitivity/Specificity, respectively. Results: Results showed an overall AI ROC-AUC of 0.954 with no difference across age or body part subgroups. Real-life emergency physicians’ sensitivity was 93.7 %, not significantly different to the AI model (P = 0.105), however in 172/1772 (9.7 %) cases misdiagnosed by emergency physicians. In this subset, AI accuracy was 90.1 %. Conclusion: This study highlighted that multiple findings AI solution for emergency radiographs is efficient and complementary to emergency physicians, and could help reduce misdiagnosis in the absence of immediate radiological expertize. |
first_indexed | 2024-03-13T05:02:45Z |
format | Article |
id | doaj.art-fa8b26aba2fa4b61b60e6f0b9850b557 |
institution | Directory Open Access Journal |
issn | 2352-0477 |
language | English |
last_indexed | 2024-03-13T05:02:45Z |
publishDate | 2023-01-01 |
publisher | Elsevier |
record_format | Article |
series | European Journal of Radiology Open |
spelling | doaj.art-fa8b26aba2fa4b61b60e6f0b9850b5572023-06-17T05:18:52ZengElsevierEuropean Journal of Radiology Open2352-04772023-01-0110100482Assessment of a combined musculoskeletal and chest deep learning-based detection solution in an emergency settingAlexandre Parpaleix0Clémence Parsy1Marina Cordari2Mehdi Mejdoubi3Department of Radiology, Valenciennes General Hospital, Valenciennes, France; Correspondence to: Département de radiologie, Centre Hospitalier de Valenciennes, 114 Av. Desandrouin, 59300 Valenciennes, France.Department of Radiology, Valenciennes General Hospital, Valenciennes, FranceArterys Inc., San Francisco, CA, USADepartment of Radiology, Valenciennes General Hospital, Valenciennes, FranceRationale and objectives: Triage and diagnostic deep learning-based support solutions have started to take hold in everyday emergency radiology practice with the hope of alleviating workflows. Although previous works had proven that artificial intelligence (AI) may increase radiologist and/or emergency physician reading performances, they were restricted to finding, bodypart and/or age subgroups, without evaluating a routine emergency workflow composed of chest and musculoskeletal adult and pediatric cases. We aimed at evaluating a multiple musculoskeletal and chest radiographic findings deep learning-based commercial solution on an adult and pediatric emergency workflow, focusing on discrepancies between emergency and radiology physicians. Material and methods: This retrospective, monocentric and observational study included 1772 patients who underwent an emergency radiograph between July and October 2020, excluding spine, skull and plain abdomen procedures. Emergency and radiology reports, obtained without AI as part of the clinical workflow, were collected and discordant cases were reviewed to obtain the radiology reference standard. Case-level AI outputs and emergency reports were compared to the reference standard. DeLong and Wald tests were used to compare ROC-AUC and Sensitivity/Specificity, respectively. Results: Results showed an overall AI ROC-AUC of 0.954 with no difference across age or body part subgroups. Real-life emergency physicians’ sensitivity was 93.7 %, not significantly different to the AI model (P = 0.105), however in 172/1772 (9.7 %) cases misdiagnosed by emergency physicians. In this subset, AI accuracy was 90.1 %. Conclusion: This study highlighted that multiple findings AI solution for emergency radiographs is efficient and complementary to emergency physicians, and could help reduce misdiagnosis in the absence of immediate radiological expertize.http://www.sciencedirect.com/science/article/pii/S2352047723000084Deep learningEmergencyXrayMusculoskeletalChestAdd-on |
spellingShingle | Alexandre Parpaleix Clémence Parsy Marina Cordari Mehdi Mejdoubi Assessment of a combined musculoskeletal and chest deep learning-based detection solution in an emergency setting European Journal of Radiology Open Deep learning Emergency Xray Musculoskeletal Chest Add-on |
title | Assessment of a combined musculoskeletal and chest deep learning-based detection solution in an emergency setting |
title_full | Assessment of a combined musculoskeletal and chest deep learning-based detection solution in an emergency setting |
title_fullStr | Assessment of a combined musculoskeletal and chest deep learning-based detection solution in an emergency setting |
title_full_unstemmed | Assessment of a combined musculoskeletal and chest deep learning-based detection solution in an emergency setting |
title_short | Assessment of a combined musculoskeletal and chest deep learning-based detection solution in an emergency setting |
title_sort | assessment of a combined musculoskeletal and chest deep learning based detection solution in an emergency setting |
topic | Deep learning Emergency Xray Musculoskeletal Chest Add-on |
url | http://www.sciencedirect.com/science/article/pii/S2352047723000084 |
work_keys_str_mv | AT alexandreparpaleix assessmentofacombinedmusculoskeletalandchestdeeplearningbaseddetectionsolutioninanemergencysetting AT clemenceparsy assessmentofacombinedmusculoskeletalandchestdeeplearningbaseddetectionsolutioninanemergencysetting AT marinacordari assessmentofacombinedmusculoskeletalandchestdeeplearningbaseddetectionsolutioninanemergencysetting AT mehdimejdoubi assessmentofacombinedmusculoskeletalandchestdeeplearningbaseddetectionsolutioninanemergencysetting |