A Generalizable Artificial Intelligence Model for COVID-19 Classification Task Using Chest X-ray Radiographs: Evaluated Over Four Clinical Datasets with 15,097 Patients

Purpose: To answer the long-standing question of whether a model trained from a single clinical site can be generalized to external sites. Materials and Methods: 17,537 chest x-ray radiographs (CXRs) from 3,264 COVID-19-positive patients and 4,802 COVID-19-negative patients were collected from a sin...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Zhang, Ran, Tie, Xin, Garrett, John W, Griner, Dalton, Qi, Zhihua, Bevins, Nicholas B, Reeder, Scott B, Chen, Guang-Hong
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page
container_issue
container_start_page
container_title
container_volume
creator Zhang, Ran
Tie, Xin
Garrett, John W
Griner, Dalton
Qi, Zhihua
Bevins, Nicholas B
Reeder, Scott B
Chen, Guang-Hong
description Purpose: To answer the long-standing question of whether a model trained from a single clinical site can be generalized to external sites. Materials and Methods: 17,537 chest x-ray radiographs (CXRs) from 3,264 COVID-19-positive patients and 4,802 COVID-19-negative patients were collected from a single site for AI model development. The generalizability of the trained model was retrospectively evaluated using four different real-world clinical datasets with a total of 26,633 CXRs from 15,097 patients (3,277 COVID-19-positive patients). The area under the receiver operating characteristic curve (AUC) was used to assess diagnostic performance. Results: The AI model trained using a single-source clinical dataset achieved an AUC of 0.82 (95% CI: 0.80, 0.84) when applied to the internal temporal test set. When applied to datasets from two external clinical sites, an AUC of 0.81 (95% CI: 0.80, 0.82) and 0.82 (95% CI: 0.80, 0.84) were achieved. An AUC of 0.79 (95% CI: 0.77, 0.81) was achieved when applied to a multi-institutional COVID-19 dataset collected by the Medical Imaging and Data Resource Center (MIDRC). A power-law dependence, N^(k )(k is empirically found to be -0.21 to -0.25), indicates a relatively weak performance dependence on the training data sizes. Conclusion: COVID-19 classification AI model trained using well-curated data from a single clinical site is generalizable to external clinical sites without a significant drop in performance.
doi_str_mv 10.48550/arxiv.2210.02189
format Article
fullrecord <record><control><sourceid>arxiv_GOX</sourceid><recordid>TN_cdi_arxiv_primary_2210_02189</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2210_02189</sourcerecordid><originalsourceid>FETCH-LOGICAL-a679-d121deca8528455f01622736ac5156e946d88c9fe5da7f987558c7641cc943623</originalsourceid><addsrcrecordid>eNot0E1OwzAQhuFsWKDCAVgxByAlduLEZlelP0QqKkIFsasGZ9JamKSy3UI5EcckLaxG-jR6Fm8UXbFkmEkhklt0X2Y_5LwfEs6kOo9-RjCjlhxa841vlmDkgmmMNmihagNZa9bUaoKHriYLTeegXLxU45gpKC16f3zGYLoWlujf4dmbdg3lhnyA19jhAZ6wNt3a4Xbj72CyR7vDQDUs9uRg2u16z5q2NyyMMaCn4OHThA0wcZOoAh57nNrgL6KzBq2ny_87iJbTybK8j-eLWVWO5jHmhYprxllNGqXgMhOiSVjOeZHmqAUTOaksr6XUqiFRY9EoWQghdZFnTGuVpTlPB9H1H3tKtdo684HusDomW52Spb90n2Z8</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype></control><display><type>article</type><title>A Generalizable Artificial Intelligence Model for COVID-19 Classification Task Using Chest X-ray Radiographs: Evaluated Over Four Clinical Datasets with 15,097 Patients</title><source>arXiv.org</source><creator>Zhang, Ran ; Tie, Xin ; Garrett, John W ; Griner, Dalton ; Qi, Zhihua ; Bevins, Nicholas B ; Reeder, Scott B ; Chen, Guang-Hong</creator><creatorcontrib>Zhang, Ran ; Tie, Xin ; Garrett, John W ; Griner, Dalton ; Qi, Zhihua ; Bevins, Nicholas B ; Reeder, Scott B ; Chen, Guang-Hong</creatorcontrib><description>Purpose: To answer the long-standing question of whether a model trained from a single clinical site can be generalized to external sites. Materials and Methods: 17,537 chest x-ray radiographs (CXRs) from 3,264 COVID-19-positive patients and 4,802 COVID-19-negative patients were collected from a single site for AI model development. The generalizability of the trained model was retrospectively evaluated using four different real-world clinical datasets with a total of 26,633 CXRs from 15,097 patients (3,277 COVID-19-positive patients). The area under the receiver operating characteristic curve (AUC) was used to assess diagnostic performance. Results: The AI model trained using a single-source clinical dataset achieved an AUC of 0.82 (95% CI: 0.80, 0.84) when applied to the internal temporal test set. When applied to datasets from two external clinical sites, an AUC of 0.81 (95% CI: 0.80, 0.82) and 0.82 (95% CI: 0.80, 0.84) were achieved. An AUC of 0.79 (95% CI: 0.77, 0.81) was achieved when applied to a multi-institutional COVID-19 dataset collected by the Medical Imaging and Data Resource Center (MIDRC). A power-law dependence, N^(k )(k is empirically found to be -0.21 to -0.25), indicates a relatively weak performance dependence on the training data sizes. Conclusion: COVID-19 classification AI model trained using well-curated data from a single clinical site is generalizable to external clinical sites without a significant drop in performance.</description><identifier>DOI: 10.48550/arxiv.2210.02189</identifier><language>eng</language><subject>Computer Science - Computer Vision and Pattern Recognition ; Computer Science - Learning</subject><creationdate>2022-10</creationdate><rights>http://arxiv.org/licenses/nonexclusive-distrib/1.0</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><link.rule.ids>228,230,776,881</link.rule.ids><linktorsrc>$$Uhttps://arxiv.org/abs/2210.02189$$EView_record_in_Cornell_University$$FView_record_in_$$GCornell_University$$Hfree_for_read</linktorsrc><backlink>$$Uhttps://doi.org/10.48550/arXiv.2210.02189$$DView paper in arXiv$$Hfree_for_read</backlink></links><search><creatorcontrib>Zhang, Ran</creatorcontrib><creatorcontrib>Tie, Xin</creatorcontrib><creatorcontrib>Garrett, John W</creatorcontrib><creatorcontrib>Griner, Dalton</creatorcontrib><creatorcontrib>Qi, Zhihua</creatorcontrib><creatorcontrib>Bevins, Nicholas B</creatorcontrib><creatorcontrib>Reeder, Scott B</creatorcontrib><creatorcontrib>Chen, Guang-Hong</creatorcontrib><title>A Generalizable Artificial Intelligence Model for COVID-19 Classification Task Using Chest X-ray Radiographs: Evaluated Over Four Clinical Datasets with 15,097 Patients</title><description>Purpose: To answer the long-standing question of whether a model trained from a single clinical site can be generalized to external sites. Materials and Methods: 17,537 chest x-ray radiographs (CXRs) from 3,264 COVID-19-positive patients and 4,802 COVID-19-negative patients were collected from a single site for AI model development. The generalizability of the trained model was retrospectively evaluated using four different real-world clinical datasets with a total of 26,633 CXRs from 15,097 patients (3,277 COVID-19-positive patients). The area under the receiver operating characteristic curve (AUC) was used to assess diagnostic performance. Results: The AI model trained using a single-source clinical dataset achieved an AUC of 0.82 (95% CI: 0.80, 0.84) when applied to the internal temporal test set. When applied to datasets from two external clinical sites, an AUC of 0.81 (95% CI: 0.80, 0.82) and 0.82 (95% CI: 0.80, 0.84) were achieved. An AUC of 0.79 (95% CI: 0.77, 0.81) was achieved when applied to a multi-institutional COVID-19 dataset collected by the Medical Imaging and Data Resource Center (MIDRC). A power-law dependence, N^(k )(k is empirically found to be -0.21 to -0.25), indicates a relatively weak performance dependence on the training data sizes. Conclusion: COVID-19 classification AI model trained using well-curated data from a single clinical site is generalizable to external clinical sites without a significant drop in performance.</description><subject>Computer Science - Computer Vision and Pattern Recognition</subject><subject>Computer Science - Learning</subject><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2022</creationdate><recordtype>article</recordtype><sourceid>GOX</sourceid><recordid>eNot0E1OwzAQhuFsWKDCAVgxByAlduLEZlelP0QqKkIFsasGZ9JamKSy3UI5EcckLaxG-jR6Fm8UXbFkmEkhklt0X2Y_5LwfEs6kOo9-RjCjlhxa841vlmDkgmmMNmihagNZa9bUaoKHriYLTeegXLxU45gpKC16f3zGYLoWlujf4dmbdg3lhnyA19jhAZ6wNt3a4Xbj72CyR7vDQDUs9uRg2u16z5q2NyyMMaCn4OHThA0wcZOoAh57nNrgL6KzBq2ny_87iJbTybK8j-eLWVWO5jHmhYprxllNGqXgMhOiSVjOeZHmqAUTOaksr6XUqiFRY9EoWQghdZFnTGuVpTlPB9H1H3tKtdo684HusDomW52Spb90n2Z8</recordid><startdate>20221004</startdate><enddate>20221004</enddate><creator>Zhang, Ran</creator><creator>Tie, Xin</creator><creator>Garrett, John W</creator><creator>Griner, Dalton</creator><creator>Qi, Zhihua</creator><creator>Bevins, Nicholas B</creator><creator>Reeder, Scott B</creator><creator>Chen, Guang-Hong</creator><scope>AKY</scope><scope>GOX</scope></search><sort><creationdate>20221004</creationdate><title>A Generalizable Artificial Intelligence Model for COVID-19 Classification Task Using Chest X-ray Radiographs: Evaluated Over Four Clinical Datasets with 15,097 Patients</title><author>Zhang, Ran ; Tie, Xin ; Garrett, John W ; Griner, Dalton ; Qi, Zhihua ; Bevins, Nicholas B ; Reeder, Scott B ; Chen, Guang-Hong</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-a679-d121deca8528455f01622736ac5156e946d88c9fe5da7f987558c7641cc943623</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2022</creationdate><topic>Computer Science - Computer Vision and Pattern Recognition</topic><topic>Computer Science - Learning</topic><toplevel>online_resources</toplevel><creatorcontrib>Zhang, Ran</creatorcontrib><creatorcontrib>Tie, Xin</creatorcontrib><creatorcontrib>Garrett, John W</creatorcontrib><creatorcontrib>Griner, Dalton</creatorcontrib><creatorcontrib>Qi, Zhihua</creatorcontrib><creatorcontrib>Bevins, Nicholas B</creatorcontrib><creatorcontrib>Reeder, Scott B</creatorcontrib><creatorcontrib>Chen, Guang-Hong</creatorcontrib><collection>arXiv Computer Science</collection><collection>arXiv.org</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Zhang, Ran</au><au>Tie, Xin</au><au>Garrett, John W</au><au>Griner, Dalton</au><au>Qi, Zhihua</au><au>Bevins, Nicholas B</au><au>Reeder, Scott B</au><au>Chen, Guang-Hong</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>A Generalizable Artificial Intelligence Model for COVID-19 Classification Task Using Chest X-ray Radiographs: Evaluated Over Four Clinical Datasets with 15,097 Patients</atitle><date>2022-10-04</date><risdate>2022</risdate><abstract>Purpose: To answer the long-standing question of whether a model trained from a single clinical site can be generalized to external sites. Materials and Methods: 17,537 chest x-ray radiographs (CXRs) from 3,264 COVID-19-positive patients and 4,802 COVID-19-negative patients were collected from a single site for AI model development. The generalizability of the trained model was retrospectively evaluated using four different real-world clinical datasets with a total of 26,633 CXRs from 15,097 patients (3,277 COVID-19-positive patients). The area under the receiver operating characteristic curve (AUC) was used to assess diagnostic performance. Results: The AI model trained using a single-source clinical dataset achieved an AUC of 0.82 (95% CI: 0.80, 0.84) when applied to the internal temporal test set. When applied to datasets from two external clinical sites, an AUC of 0.81 (95% CI: 0.80, 0.82) and 0.82 (95% CI: 0.80, 0.84) were achieved. An AUC of 0.79 (95% CI: 0.77, 0.81) was achieved when applied to a multi-institutional COVID-19 dataset collected by the Medical Imaging and Data Resource Center (MIDRC). A power-law dependence, N^(k )(k is empirically found to be -0.21 to -0.25), indicates a relatively weak performance dependence on the training data sizes. Conclusion: COVID-19 classification AI model trained using well-curated data from a single clinical site is generalizable to external clinical sites without a significant drop in performance.</abstract><doi>10.48550/arxiv.2210.02189</doi><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier DOI: 10.48550/arxiv.2210.02189
ispartof
issn
language eng
recordid cdi_arxiv_primary_2210_02189
source arXiv.org
subjects Computer Science - Computer Vision and Pattern Recognition
Computer Science - Learning
title A Generalizable Artificial Intelligence Model for COVID-19 Classification Task Using Chest X-ray Radiographs: Evaluated Over Four Clinical Datasets with 15,097 Patients
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-05T11%3A38%3A28IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-arxiv_GOX&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=A%20Generalizable%20Artificial%20Intelligence%20Model%20for%20COVID-19%20Classification%20Task%20Using%20Chest%20X-ray%20Radiographs:%20Evaluated%20Over%20Four%20Clinical%20Datasets%20with%2015,097%20Patients&rft.au=Zhang,%20Ran&rft.date=2022-10-04&rft_id=info:doi/10.48550/arxiv.2210.02189&rft_dat=%3Carxiv_GOX%3E2210_02189%3C/arxiv_GOX%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true