The Added Effect of Artificial Intelligence on Physicians’ Performance in Detecting Thoracic Pathologies on CT and Chest X-ray: A Systematic Review
Our systematic review investigated the additional effect of artificial intelligence-based devices on human observers when diagnosing and/or detecting thoracic pathologies using different diagnostic imaging modalities, such as chest X-ray and CT. Peer-reviewed, original research articles from EMBASE,...
Main Authors: | , , , , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2021-11-01
|
Series: | Diagnostics |
Subjects: | |
Online Access: | https://www.mdpi.com/2075-4418/11/12/2206 |
_version_ | 1797505545905635328 |
---|---|
author | Dana Li Lea Marie Pehrson Carsten Ammitzbøl Lauridsen Lea Tøttrup Marco Fraccaro Desmond Elliott Hubert Dariusz Zając Sune Darkner Jonathan Frederik Carlsen Michael Bachmann Nielsen |
author_facet | Dana Li Lea Marie Pehrson Carsten Ammitzbøl Lauridsen Lea Tøttrup Marco Fraccaro Desmond Elliott Hubert Dariusz Zając Sune Darkner Jonathan Frederik Carlsen Michael Bachmann Nielsen |
author_sort | Dana Li |
collection | DOAJ |
description | Our systematic review investigated the additional effect of artificial intelligence-based devices on human observers when diagnosing and/or detecting thoracic pathologies using different diagnostic imaging modalities, such as chest X-ray and CT. Peer-reviewed, original research articles from EMBASE, PubMed, Cochrane library, SCOPUS, and Web of Science were retrieved. Included articles were published within the last 20 years and used a device based on artificial intelligence (AI) technology to detect or diagnose pulmonary findings. The AI-based device had to be used in an observer test where the performance of human observers with and without addition of the device was measured as sensitivity, specificity, accuracy, AUC, or time spent on image reading. A total of 38 studies were included for final assessment. The quality assessment tool for diagnostic accuracy studies (QUADAS-2) was used for bias assessment. The average sensitivity increased from 67.8% to 74.6%; specificity from 82.2% to 85.4%; accuracy from 75.4% to 81.7%; and Area Under the ROC Curve (AUC) from 0.75 to 0.80. Generally, a faster reading time was reported when radiologists were aided by AI-based devices. Our systematic review showed that performance generally improved for the physicians when assisted by AI-based devices compared to unaided interpretation. |
first_indexed | 2024-03-10T04:20:08Z |
format | Article |
id | doaj.art-901abb2228944cfcb0ac54e6029a41e9 |
institution | Directory Open Access Journal |
issn | 2075-4418 |
language | English |
last_indexed | 2024-03-10T04:20:08Z |
publishDate | 2021-11-01 |
publisher | MDPI AG |
record_format | Article |
series | Diagnostics |
spelling | doaj.art-901abb2228944cfcb0ac54e6029a41e92023-11-23T07:52:52ZengMDPI AGDiagnostics2075-44182021-11-011112220610.3390/diagnostics11122206The Added Effect of Artificial Intelligence on Physicians’ Performance in Detecting Thoracic Pathologies on CT and Chest X-ray: A Systematic ReviewDana Li0Lea Marie Pehrson1Carsten Ammitzbøl Lauridsen2Lea Tøttrup3Marco Fraccaro4Desmond Elliott5Hubert Dariusz Zając6Sune Darkner7Jonathan Frederik Carlsen8Michael Bachmann Nielsen9Department of Diagnostic Radiology, Copenhagen University Hospital, Rigshospitalet, 2100 Copenhagen, DenmarkDepartment of Diagnostic Radiology, Copenhagen University Hospital, Rigshospitalet, 2100 Copenhagen, DenmarkDepartment of Diagnostic Radiology, Copenhagen University Hospital, Rigshospitalet, 2100 Copenhagen, DenmarkUnumed Aps, 1055 Copenhagen, DenmarkUnumed Aps, 1055 Copenhagen, DenmarkDepartment of Computer Science, University of Copenhagen, 2100 Copenhagen, DenmarkDepartment of Computer Science, University of Copenhagen, 2100 Copenhagen, DenmarkDepartment of Computer Science, University of Copenhagen, 2100 Copenhagen, DenmarkDepartment of Diagnostic Radiology, Copenhagen University Hospital, Rigshospitalet, 2100 Copenhagen, DenmarkDepartment of Diagnostic Radiology, Copenhagen University Hospital, Rigshospitalet, 2100 Copenhagen, DenmarkOur systematic review investigated the additional effect of artificial intelligence-based devices on human observers when diagnosing and/or detecting thoracic pathologies using different diagnostic imaging modalities, such as chest X-ray and CT. Peer-reviewed, original research articles from EMBASE, PubMed, Cochrane library, SCOPUS, and Web of Science were retrieved. Included articles were published within the last 20 years and used a device based on artificial intelligence (AI) technology to detect or diagnose pulmonary findings. The AI-based device had to be used in an observer test where the performance of human observers with and without addition of the device was measured as sensitivity, specificity, accuracy, AUC, or time spent on image reading. A total of 38 studies were included for final assessment. The quality assessment tool for diagnostic accuracy studies (QUADAS-2) was used for bias assessment. The average sensitivity increased from 67.8% to 74.6%; specificity from 82.2% to 85.4%; accuracy from 75.4% to 81.7%; and Area Under the ROC Curve (AUC) from 0.75 to 0.80. Generally, a faster reading time was reported when radiologists were aided by AI-based devices. Our systematic review showed that performance generally improved for the physicians when assisted by AI-based devices compared to unaided interpretation.https://www.mdpi.com/2075-4418/11/12/2206artificial intelligencedeep learningcomputer-based devicesradiologythoracic diagnostic imagingchest X-ray |
spellingShingle | Dana Li Lea Marie Pehrson Carsten Ammitzbøl Lauridsen Lea Tøttrup Marco Fraccaro Desmond Elliott Hubert Dariusz Zając Sune Darkner Jonathan Frederik Carlsen Michael Bachmann Nielsen The Added Effect of Artificial Intelligence on Physicians’ Performance in Detecting Thoracic Pathologies on CT and Chest X-ray: A Systematic Review Diagnostics artificial intelligence deep learning computer-based devices radiology thoracic diagnostic imaging chest X-ray |
title | The Added Effect of Artificial Intelligence on Physicians’ Performance in Detecting Thoracic Pathologies on CT and Chest X-ray: A Systematic Review |
title_full | The Added Effect of Artificial Intelligence on Physicians’ Performance in Detecting Thoracic Pathologies on CT and Chest X-ray: A Systematic Review |
title_fullStr | The Added Effect of Artificial Intelligence on Physicians’ Performance in Detecting Thoracic Pathologies on CT and Chest X-ray: A Systematic Review |
title_full_unstemmed | The Added Effect of Artificial Intelligence on Physicians’ Performance in Detecting Thoracic Pathologies on CT and Chest X-ray: A Systematic Review |
title_short | The Added Effect of Artificial Intelligence on Physicians’ Performance in Detecting Thoracic Pathologies on CT and Chest X-ray: A Systematic Review |
title_sort | added effect of artificial intelligence on physicians performance in detecting thoracic pathologies on ct and chest x ray a systematic review |
topic | artificial intelligence deep learning computer-based devices radiology thoracic diagnostic imaging chest X-ray |
url | https://www.mdpi.com/2075-4418/11/12/2206 |
work_keys_str_mv | AT danali theaddedeffectofartificialintelligenceonphysiciansperformanceindetectingthoracicpathologiesonctandchestxrayasystematicreview AT leamariepehrson theaddedeffectofartificialintelligenceonphysiciansperformanceindetectingthoracicpathologiesonctandchestxrayasystematicreview AT carstenammitzbøllauridsen theaddedeffectofartificialintelligenceonphysiciansperformanceindetectingthoracicpathologiesonctandchestxrayasystematicreview AT leatøttrup theaddedeffectofartificialintelligenceonphysiciansperformanceindetectingthoracicpathologiesonctandchestxrayasystematicreview AT marcofraccaro theaddedeffectofartificialintelligenceonphysiciansperformanceindetectingthoracicpathologiesonctandchestxrayasystematicreview AT desmondelliott theaddedeffectofartificialintelligenceonphysiciansperformanceindetectingthoracicpathologiesonctandchestxrayasystematicreview AT hubertdariuszzajac theaddedeffectofartificialintelligenceonphysiciansperformanceindetectingthoracicpathologiesonctandchestxrayasystematicreview AT sunedarkner theaddedeffectofartificialintelligenceonphysiciansperformanceindetectingthoracicpathologiesonctandchestxrayasystematicreview AT jonathanfrederikcarlsen theaddedeffectofartificialintelligenceonphysiciansperformanceindetectingthoracicpathologiesonctandchestxrayasystematicreview AT michaelbachmannnielsen theaddedeffectofartificialintelligenceonphysiciansperformanceindetectingthoracicpathologiesonctandchestxrayasystematicreview AT danali addedeffectofartificialintelligenceonphysiciansperformanceindetectingthoracicpathologiesonctandchestxrayasystematicreview AT leamariepehrson addedeffectofartificialintelligenceonphysiciansperformanceindetectingthoracicpathologiesonctandchestxrayasystematicreview AT carstenammitzbøllauridsen addedeffectofartificialintelligenceonphysiciansperformanceindetectingthoracicpathologiesonctandchestxrayasystematicreview AT leatøttrup addedeffectofartificialintelligenceonphysiciansperformanceindetectingthoracicpathologiesonctandchestxrayasystematicreview AT marcofraccaro addedeffectofartificialintelligenceonphysiciansperformanceindetectingthoracicpathologiesonctandchestxrayasystematicreview AT desmondelliott addedeffectofartificialintelligenceonphysiciansperformanceindetectingthoracicpathologiesonctandchestxrayasystematicreview AT hubertdariuszzajac addedeffectofartificialintelligenceonphysiciansperformanceindetectingthoracicpathologiesonctandchestxrayasystematicreview AT sunedarkner addedeffectofartificialintelligenceonphysiciansperformanceindetectingthoracicpathologiesonctandchestxrayasystematicreview AT jonathanfrederikcarlsen addedeffectofartificialintelligenceonphysiciansperformanceindetectingthoracicpathologiesonctandchestxrayasystematicreview AT michaelbachmannnielsen addedeffectofartificialintelligenceonphysiciansperformanceindetectingthoracicpathologiesonctandchestxrayasystematicreview |