Artificial intelligence for detection of intracranial haemorrhage on head computed tomography scans: diagnostic accuracy in Hong Kong

Introduction: The use of artificial intelligence (AI) to identify acute intracranial haemorrhage (ICH) on computed tomography (CT) scans may facilitate initial imaging interpretation in the accident and emergency department. However, AI model construction requires a large amount of annotated data fo...

Full description

Saved in:
Bibliographic Details
Published in:Hong Kong medical journal = Xianggang yi xue za zhi 2023-04, Vol.29 (2), p.112
Main Authors: Abrigo, Jill M, Ka-long, Ko, Chen, Qianyun, Lai, Billy MH, Cheung, Tom CY, Winnie CW Chu, Yu, Simon CH
Format: Article
Language:chi ; eng
Subjects:
Accuracy
Artificial intelligence
Datasets
Emergency medical care
Hemorrhage
Hospitals
Medical imaging
Physicians
Software
Statistical analysis
Tomography
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
cited_by
cites
container_end_page
container_issue 2
container_start_page 112
container_title Hong Kong medical journal = Xianggang yi xue za zhi
container_volume 29
creator Abrigo, Jill M
Ka-long, Ko
Chen, Qianyun
Lai, Billy MH
Cheung, Tom CY
Winnie CW Chu
Yu, Simon CH
description Introduction: The use of artificial intelligence (AI) to identify acute intracranial haemorrhage (ICH) on computed tomography (CT) scans may facilitate initial imaging interpretation in the accident and emergency department. However, AI model construction requires a large amount of annotated data for training, and validation with real-world data has been limited. We developed an algorithm using an open-access dataset of CT slices, then assessed its utility in clinical practice by validating its performance on CT scans from our institution. Methods: Using a publicly available international dataset of >750 000 expert-labelled CT slices, we developed an AI model which determines ICH probability for each CT scan and nominates five potential ICH-positive CT slices for review. We validated the model using retrospective data from 1372 non-contrast head CT scans (84 [6.1%] with ICH) collected at our institution. Results: The model achieved an area under the curve of 0.842 (95% confidence interval=0.791-0.894; P
doi_str_mv 10.12809/hkmj209053
format article
fullrecord <record><control><sourceid>proquest</sourceid><recordid>TN_cdi_proquest_journals_3111033505</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>3111033505</sourcerecordid><originalsourceid>FETCH-proquest_journals_31110335053</originalsourceid><addsrcrecordid>eNqNj81KxDAUhYMoWHRW8wIXXFeTdPrnTkQZmK374Zrethnb3Jqki3kA39sM-ABuzll8HweOEFslH5VuZPs0fs0nLVtZFlci01pXeVPL-lpkSupdrmvZ3IpNCPZTyqqsdVtXmfh58dH21licwLpI02QHcoagZw8dRTLRsgPuL9Sj8egu6og0s_cjDgQJj4QdGJ6XNVIHkWcePC7jGYJBF56hszg4DtEaQGPWtHNOe7BnN8Ahxb246XEKtPnrO_Hw_vbxus8Xz98rhXg88epdQsdCKSWLokwv_2f9AraDWg8</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>3111033505</pqid></control><display><type>article</type><title>Artificial intelligence for detection of intracranial haemorrhage on head computed tomography scans: diagnostic accuracy in Hong Kong</title><source>ProQuest - Publicly Available Content Database</source><creator>Abrigo, Jill M ; Ka-long, Ko ; Chen, Qianyun ; Lai, Billy MH ; Cheung, Tom CY ; Winnie CW Chu ; Yu, Simon CH</creator><creatorcontrib>Abrigo, Jill M ; Ka-long, Ko ; Chen, Qianyun ; Lai, Billy MH ; Cheung, Tom CY ; Winnie CW Chu ; Yu, Simon CH</creatorcontrib><description>Introduction: The use of artificial intelligence (AI) to identify acute intracranial haemorrhage (ICH) on computed tomography (CT) scans may facilitate initial imaging interpretation in the accident and emergency department. However, AI model construction requires a large amount of annotated data for training, and validation with real-world data has been limited. We developed an algorithm using an open-access dataset of CT slices, then assessed its utility in clinical practice by validating its performance on CT scans from our institution. Methods: Using a publicly available international dataset of &gt;750 000 expert-labelled CT slices, we developed an AI model which determines ICH probability for each CT scan and nominates five potential ICH-positive CT slices for review. We validated the model using retrospective data from 1372 non-contrast head CT scans (84 [6.1%] with ICH) collected at our institution. Results: The model achieved an area under the curve of 0.842 (95% confidence interval=0.791-0.894; P&lt;0.001</description><identifier>ISSN: 1024-2708</identifier><identifier>EISSN: 2226-8707</identifier><identifier>DOI: 10.12809/hkmj209053</identifier><language>chi ; eng</language><publisher>Hong Kong: Hong Kong Academy of Medicine</publisher><subject>Accuracy ; Artificial intelligence ; Datasets ; Emergency medical care ; Hemorrhage ; Hospitals ; Medical imaging ; Physicians ; Software ; Statistical analysis ; Tomography</subject><ispartof>Hong Kong medical journal = Xianggang yi xue za zhi, 2023-04, Vol.29 (2), p.112</ispartof><rights>2023. This work is published under https://creativecommons.org/licenses/by-nc-nd/4.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.</rights><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktopdf>$$Uhttps://www.proquest.com/docview/3111033505/fulltextPDF?pq-origsite=primo$$EPDF$$P50$$Gproquest$$Hfree_for_read</linktopdf><linktohtml>$$Uhttps://www.proquest.com/docview/3111033505?pq-origsite=primo$$EHTML$$P50$$Gproquest$$Hfree_for_read</linktohtml><link.rule.ids>314,780,784,25753,27924,27925,37012,44590,75126</link.rule.ids></links><search><creatorcontrib>Abrigo, Jill M</creatorcontrib><creatorcontrib>Ka-long, Ko</creatorcontrib><creatorcontrib>Chen, Qianyun</creatorcontrib><creatorcontrib>Lai, Billy MH</creatorcontrib><creatorcontrib>Cheung, Tom CY</creatorcontrib><creatorcontrib>Winnie CW Chu</creatorcontrib><creatorcontrib>Yu, Simon CH</creatorcontrib><title>Artificial intelligence for detection of intracranial haemorrhage on head computed tomography scans: diagnostic accuracy in Hong Kong</title><title>Hong Kong medical journal = Xianggang yi xue za zhi</title><description>Introduction: The use of artificial intelligence (AI) to identify acute intracranial haemorrhage (ICH) on computed tomography (CT) scans may facilitate initial imaging interpretation in the accident and emergency department. However, AI model construction requires a large amount of annotated data for training, and validation with real-world data has been limited. We developed an algorithm using an open-access dataset of CT slices, then assessed its utility in clinical practice by validating its performance on CT scans from our institution. Methods: Using a publicly available international dataset of &gt;750 000 expert-labelled CT slices, we developed an AI model which determines ICH probability for each CT scan and nominates five potential ICH-positive CT slices for review. We validated the model using retrospective data from 1372 non-contrast head CT scans (84 [6.1%] with ICH) collected at our institution. Results: The model achieved an area under the curve of 0.842 (95% confidence interval=0.791-0.894; P&lt;0.001</description><subject>Accuracy</subject><subject>Artificial intelligence</subject><subject>Datasets</subject><subject>Emergency medical care</subject><subject>Hemorrhage</subject><subject>Hospitals</subject><subject>Medical imaging</subject><subject>Physicians</subject><subject>Software</subject><subject>Statistical analysis</subject><subject>Tomography</subject><issn>1024-2708</issn><issn>2226-8707</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2023</creationdate><recordtype>article</recordtype><sourceid>PIMPY</sourceid><recordid>eNqNj81KxDAUhYMoWHRW8wIXXFeTdPrnTkQZmK374Zrethnb3Jqki3kA39sM-ABuzll8HweOEFslH5VuZPs0fs0nLVtZFlci01pXeVPL-lpkSupdrmvZ3IpNCPZTyqqsdVtXmfh58dH21licwLpI02QHcoagZw8dRTLRsgPuL9Sj8egu6og0s_cjDgQJj4QdGJ6XNVIHkWcePC7jGYJBF56hszg4DtEaQGPWtHNOe7BnN8Ahxb246XEKtPnrO_Hw_vbxus8Xz98rhXg88epdQsdCKSWLokwv_2f9AraDWg8</recordid><startdate>20230401</startdate><enddate>20230401</enddate><creator>Abrigo, Jill M</creator><creator>Ka-long, Ko</creator><creator>Chen, Qianyun</creator><creator>Lai, Billy MH</creator><creator>Cheung, Tom CY</creator><creator>Winnie CW Chu</creator><creator>Yu, Simon CH</creator><general>Hong Kong Academy of Medicine</general><scope>3V.</scope><scope>7X7</scope><scope>7XB</scope><scope>8FI</scope><scope>8FJ</scope><scope>8FK</scope><scope>ABUWG</scope><scope>AFKRA</scope><scope>AZQEC</scope><scope>BENPR</scope><scope>BVBZV</scope><scope>CCPQU</scope><scope>DWQXO</scope><scope>FYUFA</scope><scope>GHDGH</scope><scope>K9.</scope><scope>M0S</scope><scope>PIMPY</scope><scope>PQEST</scope><scope>PQQKQ</scope><scope>PQUKI</scope><scope>PRINS</scope></search><sort><creationdate>20230401</creationdate><title>Artificial intelligence for detection of intracranial haemorrhage on head computed tomography scans: diagnostic accuracy in Hong Kong</title><author>Abrigo, Jill M ; Ka-long, Ko ; Chen, Qianyun ; Lai, Billy MH ; Cheung, Tom CY ; Winnie CW Chu ; Yu, Simon CH</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-proquest_journals_31110335053</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>chi ; eng</language><creationdate>2023</creationdate><topic>Accuracy</topic><topic>Artificial intelligence</topic><topic>Datasets</topic><topic>Emergency medical care</topic><topic>Hemorrhage</topic><topic>Hospitals</topic><topic>Medical imaging</topic><topic>Physicians</topic><topic>Software</topic><topic>Statistical analysis</topic><topic>Tomography</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Abrigo, Jill M</creatorcontrib><creatorcontrib>Ka-long, Ko</creatorcontrib><creatorcontrib>Chen, Qianyun</creatorcontrib><creatorcontrib>Lai, Billy MH</creatorcontrib><creatorcontrib>Cheung, Tom CY</creatorcontrib><creatorcontrib>Winnie CW Chu</creatorcontrib><creatorcontrib>Yu, Simon CH</creatorcontrib><collection>ProQuest Central (Corporate)</collection><collection>Health &amp; Medical Collection (Proquest)</collection><collection>ProQuest Central (purchase pre-March 2016)</collection><collection>Hospital Premium Collection</collection><collection>Hospital Premium Collection (Alumni Edition)</collection><collection>ProQuest Central (Alumni) (purchase pre-March 2016)</collection><collection>ProQuest Central (Alumni)</collection><collection>ProQuest Central</collection><collection>ProQuest Central Essentials</collection><collection>AUTh Library subscriptions: ProQuest Central</collection><collection>East &amp; South Asia Database</collection><collection>ProQuest One Community College</collection><collection>ProQuest Central</collection><collection>Health Research Premium Collection</collection><collection>Health Research Premium Collection (Alumni)</collection><collection>ProQuest Health &amp; Medical Complete (Alumni)</collection><collection>Health &amp; Medical Collection (Alumni Edition)</collection><collection>ProQuest - Publicly Available Content Database</collection><collection>ProQuest One Academic Eastern Edition (DO NOT USE)</collection><collection>ProQuest One Academic</collection><collection>ProQuest One Academic UKI Edition</collection><collection>ProQuest Central China</collection><jtitle>Hong Kong medical journal = Xianggang yi xue za zhi</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Abrigo, Jill M</au><au>Ka-long, Ko</au><au>Chen, Qianyun</au><au>Lai, Billy MH</au><au>Cheung, Tom CY</au><au>Winnie CW Chu</au><au>Yu, Simon CH</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Artificial intelligence for detection of intracranial haemorrhage on head computed tomography scans: diagnostic accuracy in Hong Kong</atitle><jtitle>Hong Kong medical journal = Xianggang yi xue za zhi</jtitle><date>2023-04-01</date><risdate>2023</risdate><volume>29</volume><issue>2</issue><spage>112</spage><pages>112-</pages><issn>1024-2708</issn><eissn>2226-8707</eissn><abstract>Introduction: The use of artificial intelligence (AI) to identify acute intracranial haemorrhage (ICH) on computed tomography (CT) scans may facilitate initial imaging interpretation in the accident and emergency department. However, AI model construction requires a large amount of annotated data for training, and validation with real-world data has been limited. We developed an algorithm using an open-access dataset of CT slices, then assessed its utility in clinical practice by validating its performance on CT scans from our institution. Methods: Using a publicly available international dataset of &gt;750 000 expert-labelled CT slices, we developed an AI model which determines ICH probability for each CT scan and nominates five potential ICH-positive CT slices for review. We validated the model using retrospective data from 1372 non-contrast head CT scans (84 [6.1%] with ICH) collected at our institution. Results: The model achieved an area under the curve of 0.842 (95% confidence interval=0.791-0.894; P&lt;0.001</abstract><cop>Hong Kong</cop><pub>Hong Kong Academy of Medicine</pub><doi>10.12809/hkmj209053</doi><oa>free_for_read</oa></addata></record>
fulltext fulltext
identifier ISSN: 1024-2708
ispartof Hong Kong medical journal = Xianggang yi xue za zhi, 2023-04, Vol.29 (2), p.112
issn 1024-2708
2226-8707
language chi ; eng
recordid cdi_proquest_journals_3111033505
source ProQuest - Publicly Available Content Database
subjects Accuracy
Artificial intelligence
Datasets
Emergency medical care
Hemorrhage
Hospitals
Medical imaging
Physicians
Software
Statistical analysis
Tomography
title Artificial intelligence for detection of intracranial haemorrhage on head computed tomography scans: diagnostic accuracy in Hong Kong
url http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-05T02%3A32%3A09IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Artificial%20intelligence%20for%20detection%20of%20intracranial%20haemorrhage%20on%20head%20computed%20tomography%20scans:%20diagnostic%20accuracy%20in%20Hong%20Kong&rft.jtitle=Hong%20Kong%20medical%20journal%20=%20Xianggang%20yi%20xue%20za%20zhi&rft.au=Abrigo,%20Jill%20M&rft.date=2023-04-01&rft.volume=29&rft.issue=2&rft.spage=112&rft.pages=112-&rft.issn=1024-2708&rft.eissn=2226-8707&rft_id=info:doi/10.12809/hkmj209053&rft_dat=%3Cproquest%3E3111033505%3C/proquest%3E%3Cgrp_id%3Ecdi_FETCH-proquest_journals_31110335053%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_pqid=3111033505&rft_id=info:pmid/&rfr_iscdi=true