Machine learning for image-based detection of patients with obstructive sleep apnea: an exploratory study
Purpose In 2-dimensional lateral cephalometric radiographs, patients with severe obstructive sleep apnea (OSA) exhibit a more crowded oropharynx in comparison with non-OSA. We tested the hypothesis that machine learning, an application of artificial intelligence (AI), could be used to detect patient...
Gespeichert in:
| Veröffentlicht in: | Sleep & breathing 2021-12, Vol.25 (4), p.2297-2305 |
|---|---|
| Hauptverfasser: | , , , , , , , |
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | 2305 |
|---|---|
| container_issue | 4 |
| container_start_page | 2297 |
| container_title | Sleep & breathing |
| container_volume | 25 |
| creator | Tsuiki, Satoru Nagaoka, Takuya Fukuda, Tatsuya Sakamoto, Yuki Almeida, Fernanda R. Nakayama, Hideaki Inoue, Yuichi Enno, Hiroki |
| description | Purpose
In 2-dimensional lateral cephalometric radiographs, patients with severe obstructive sleep apnea (OSA) exhibit a more crowded oropharynx in comparison with non-OSA. We tested the hypothesis that machine learning, an application of artificial intelligence (AI), could be used to detect patients with severe OSA based on 2-dimensional images.
Methods
A deep convolutional neural network was developed (
n
= 1258; 90%) and tested (
n
= 131; 10%) using data from 1389 (100%) lateral cephalometric radiographs obtained from individuals diagnosed with severe OSA (
n
= 867; apnea hypopnea index > 30 events/h sleep) or non-OSA (
n
= 522; apnea hypopnea index |
| doi_str_mv | 10.1007/s11325-021-02301-7 |
| format | Article |
| fullrecord | <record><control><sourceid>proquest_pubme</sourceid><recordid>TN_cdi_pubmedcentral_primary_oai_pubmedcentral_nih_gov_8590647</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2487749533</sourcerecordid><originalsourceid>FETCH-LOGICAL-c474t-62d8c6f3be518ed969e3102f9e70c3d93524fe180e1f6185697c4132702518553</originalsourceid><addsrcrecordid>eNp9UU1v1DAUjBCIlsIf4IAsceES8PNHHHNAqipoKxX1Us6W13nZdZW1g-0U9t_jdkspHDhYtjTzxjNvmuY10PdAqfqQATiTLWVQD6fQqifNIUjGWlBUP71701ZLYAfNi5yvKQXRa3jeHHAupaZUHDb-q3UbH5BMaFPwYU3GmIjf2jW2K5txIAMWdMXHQOJIZls8hpLJD182JK5ySUsFb5DkCXEmdg5oPxIbCP6cp5hsiWlHclmG3cvm2WinjK_u76Pm25fPVydn7cXl6fnJ8UXrhBKl7djQu27kK5TQ46A7jRwoGzUq6viguWRiROgpwthBLzutnKh7UJTVASn5UfNprzsvqy0OrtpNdjJzqqHSzkTrzd9I8BuzjjemryvphKoC7-4FUvy-YC5m67PDabIB45INE71SQkvOK_XtP9TruKRQ4xkmtaLANBOVxfYsl2LOCccHM0DNbZNm36SpTZq7Js2tizePYzyM_K6uEviekCsU1pj-_P0f2V9w3Knk</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2597012924</pqid></control><display><type>article</type><title>Machine learning for image-based detection of patients with obstructive sleep apnea: an exploratory study</title><source>MEDLINE</source><source>SpringerLink Journals - AutoHoldings</source><creator>Tsuiki, Satoru ; Nagaoka, Takuya ; Fukuda, Tatsuya ; Sakamoto, Yuki ; Almeida, Fernanda R. ; Nakayama, Hideaki ; Inoue, Yuichi ; Enno, Hiroki</creator><creatorcontrib>Tsuiki, Satoru ; Nagaoka, Takuya ; Fukuda, Tatsuya ; Sakamoto, Yuki ; Almeida, Fernanda R. ; Nakayama, Hideaki ; Inoue, Yuichi ; Enno, Hiroki</creatorcontrib><description>Purpose
In 2-dimensional lateral cephalometric radiographs, patients with severe obstructive sleep apnea (OSA) exhibit a more crowded oropharynx in comparison with non-OSA. We tested the hypothesis that machine learning, an application of artificial intelligence (AI), could be used to detect patients with severe OSA based on 2-dimensional images.
Methods
A deep convolutional neural network was developed (
n
= 1258; 90%) and tested (
n
= 131; 10%) using data from 1389 (100%) lateral cephalometric radiographs obtained from individuals diagnosed with severe OSA (
n
= 867; apnea hypopnea index > 30 events/h sleep) or non-OSA (
n
= 522; apnea hypopnea index < 5 events/h sleep) at a single center for sleep disorders. Three kinds of data sets were prepared by changing the area of interest using a single image: the original image without any modification (full image), an image containing a facial profile, upper airway, and craniofacial soft/hard tissues (main region), and an image containing part of the occipital region (head only). A radiologist also performed a conventional manual cephalometric analysis of the full image for comparison.
Results
The sensitivity/specificity was 0.87/0.82 for full image, 0.88/0.75 for main region, 0.71/0.63 for head only, and 0.54/0.80 for the manual analysis. The area under the receiver-operating characteristic curve was the highest for main region 0.92, for full image 0.89, for head only 0.70, and for manual cephalometric analysis 0.75.
Conclusions
A deep convolutional neural network identified individuals with severe OSA with high accuracy. Future research on this concept using AI and images can be further encouraged when discussing triage of OSA.</description><identifier>ISSN: 1520-9512</identifier><identifier>EISSN: 1522-1709</identifier><identifier>DOI: 10.1007/s11325-021-02301-7</identifier><identifier>PMID: 33559004</identifier><language>eng</language><publisher>Cham: Springer International Publishing</publisher><subject>Adult ; Apnea ; Artificial intelligence ; Cephalometry - methods ; Cephalometry - standards ; Deep Learning ; Dentistry ; Dentistry • Original ; Dentistry • Original Article ; Female ; Humans ; Image processing ; Internal Medicine ; Learning algorithms ; Machine learning ; Male ; Medicine ; Medicine & Public Health ; Middle Aged ; Neural networks ; Neurology ; Oropharynx ; Otorhinolaryngology ; Pediatrics ; Pneumology/Respiratory System ; Radiography ; Radiography - methods ; Radiography - standards ; Sensitivity and Specificity ; Sleep ; Sleep apnea ; Sleep Apnea, Obstructive - diagnostic imaging ; Sleep disorders</subject><ispartof>Sleep & breathing, 2021-12, Vol.25 (4), p.2297-2305</ispartof><rights>The Author(s) 2021</rights><rights>2021. The Author(s).</rights><rights>The Author(s) 2021. This work is published under http://creativecommons.org/licenses/by/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><citedby>FETCH-LOGICAL-c474t-62d8c6f3be518ed969e3102f9e70c3d93524fe180e1f6185697c4132702518553</citedby><cites>FETCH-LOGICAL-c474t-62d8c6f3be518ed969e3102f9e70c3d93524fe180e1f6185697c4132702518553</cites></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktopdf>$$Uhttps://link.springer.com/content/pdf/10.1007/s11325-021-02301-7$$EPDF$$P50$$Gspringer$$Hfree_for_read</linktopdf><linktohtml>$$Uhttps://link.springer.com/10.1007/s11325-021-02301-7$$EHTML$$P50$$Gspringer$$Hfree_for_read</linktohtml><link.rule.ids>230,314,780,784,885,27924,27925,41488,42557,51319</link.rule.ids><backlink>$$Uhttps://www.ncbi.nlm.nih.gov/pubmed/33559004$$D View this record in MEDLINE/PubMed$$Hfree_for_read</backlink></links><search><creatorcontrib>Tsuiki, Satoru</creatorcontrib><creatorcontrib>Nagaoka, Takuya</creatorcontrib><creatorcontrib>Fukuda, Tatsuya</creatorcontrib><creatorcontrib>Sakamoto, Yuki</creatorcontrib><creatorcontrib>Almeida, Fernanda R.</creatorcontrib><creatorcontrib>Nakayama, Hideaki</creatorcontrib><creatorcontrib>Inoue, Yuichi</creatorcontrib><creatorcontrib>Enno, Hiroki</creatorcontrib><title>Machine learning for image-based detection of patients with obstructive sleep apnea: an exploratory study</title><title>Sleep & breathing</title><addtitle>Sleep Breath</addtitle><addtitle>Sleep Breath</addtitle><description>Purpose
In 2-dimensional lateral cephalometric radiographs, patients with severe obstructive sleep apnea (OSA) exhibit a more crowded oropharynx in comparison with non-OSA. We tested the hypothesis that machine learning, an application of artificial intelligence (AI), could be used to detect patients with severe OSA based on 2-dimensional images.
Methods
A deep convolutional neural network was developed (
n
= 1258; 90%) and tested (
n
= 131; 10%) using data from 1389 (100%) lateral cephalometric radiographs obtained from individuals diagnosed with severe OSA (
n
= 867; apnea hypopnea index > 30 events/h sleep) or non-OSA (
n
= 522; apnea hypopnea index < 5 events/h sleep) at a single center for sleep disorders. Three kinds of data sets were prepared by changing the area of interest using a single image: the original image without any modification (full image), an image containing a facial profile, upper airway, and craniofacial soft/hard tissues (main region), and an image containing part of the occipital region (head only). A radiologist also performed a conventional manual cephalometric analysis of the full image for comparison.
Results
The sensitivity/specificity was 0.87/0.82 for full image, 0.88/0.75 for main region, 0.71/0.63 for head only, and 0.54/0.80 for the manual analysis. The area under the receiver-operating characteristic curve was the highest for main region 0.92, for full image 0.89, for head only 0.70, and for manual cephalometric analysis 0.75.
Conclusions
A deep convolutional neural network identified individuals with severe OSA with high accuracy. Future research on this concept using AI and images can be further encouraged when discussing triage of OSA.</description><subject>Adult</subject><subject>Apnea</subject><subject>Artificial intelligence</subject><subject>Cephalometry - methods</subject><subject>Cephalometry - standards</subject><subject>Deep Learning</subject><subject>Dentistry</subject><subject>Dentistry • Original</subject><subject>Dentistry • Original Article</subject><subject>Female</subject><subject>Humans</subject><subject>Image processing</subject><subject>Internal Medicine</subject><subject>Learning algorithms</subject><subject>Machine learning</subject><subject>Male</subject><subject>Medicine</subject><subject>Medicine & Public Health</subject><subject>Middle Aged</subject><subject>Neural networks</subject><subject>Neurology</subject><subject>Oropharynx</subject><subject>Otorhinolaryngology</subject><subject>Pediatrics</subject><subject>Pneumology/Respiratory System</subject><subject>Radiography</subject><subject>Radiography - methods</subject><subject>Radiography - standards</subject><subject>Sensitivity and Specificity</subject><subject>Sleep</subject><subject>Sleep apnea</subject><subject>Sleep Apnea, Obstructive - diagnostic imaging</subject><subject>Sleep disorders</subject><issn>1520-9512</issn><issn>1522-1709</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2021</creationdate><recordtype>article</recordtype><sourceid>C6C</sourceid><sourceid>EIF</sourceid><sourceid>ABUWG</sourceid><sourceid>AFKRA</sourceid><sourceid>AZQEC</sourceid><sourceid>BENPR</sourceid><sourceid>CCPQU</sourceid><sourceid>DWQXO</sourceid><sourceid>GNUQQ</sourceid><recordid>eNp9UU1v1DAUjBCIlsIf4IAsceES8PNHHHNAqipoKxX1Us6W13nZdZW1g-0U9t_jdkspHDhYtjTzxjNvmuY10PdAqfqQATiTLWVQD6fQqifNIUjGWlBUP71701ZLYAfNi5yvKQXRa3jeHHAupaZUHDb-q3UbH5BMaFPwYU3GmIjf2jW2K5txIAMWdMXHQOJIZls8hpLJD182JK5ySUsFb5DkCXEmdg5oPxIbCP6cp5hsiWlHclmG3cvm2WinjK_u76Pm25fPVydn7cXl6fnJ8UXrhBKl7djQu27kK5TQ46A7jRwoGzUq6viguWRiROgpwthBLzutnKh7UJTVASn5UfNprzsvqy0OrtpNdjJzqqHSzkTrzd9I8BuzjjemryvphKoC7-4FUvy-YC5m67PDabIB45INE71SQkvOK_XtP9TruKRQ4xkmtaLANBOVxfYsl2LOCccHM0DNbZNm36SpTZq7Js2tizePYzyM_K6uEviekCsU1pj-_P0f2V9w3Knk</recordid><startdate>20211201</startdate><enddate>20211201</enddate><creator>Tsuiki, Satoru</creator><creator>Nagaoka, Takuya</creator><creator>Fukuda, Tatsuya</creator><creator>Sakamoto, Yuki</creator><creator>Almeida, Fernanda R.</creator><creator>Nakayama, Hideaki</creator><creator>Inoue, Yuichi</creator><creator>Enno, Hiroki</creator><general>Springer International Publishing</general><general>Springer Nature B.V</general><scope>C6C</scope><scope>CGR</scope><scope>CUY</scope><scope>CVF</scope><scope>ECM</scope><scope>EIF</scope><scope>NPM</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>0-V</scope><scope>3V.</scope><scope>7T5</scope><scope>7TK</scope><scope>7X7</scope><scope>7XB</scope><scope>88E</scope><scope>88G</scope><scope>88J</scope><scope>8AO</scope><scope>8FI</scope><scope>8FJ</scope><scope>8FK</scope><scope>ABUWG</scope><scope>AFKRA</scope><scope>ALSLI</scope><scope>AZQEC</scope><scope>BENPR</scope><scope>CCPQU</scope><scope>DWQXO</scope><scope>FYUFA</scope><scope>GHDGH</scope><scope>GNUQQ</scope><scope>H94</scope><scope>K9.</scope><scope>M0S</scope><scope>M1P</scope><scope>M2M</scope><scope>M2R</scope><scope>PQEST</scope><scope>PQQKQ</scope><scope>PQUKI</scope><scope>PSYQQ</scope><scope>Q9U</scope><scope>7X8</scope><scope>5PM</scope></search><sort><creationdate>20211201</creationdate><title>Machine learning for image-based detection of patients with obstructive sleep apnea: an exploratory study</title><author>Tsuiki, Satoru ; Nagaoka, Takuya ; Fukuda, Tatsuya ; Sakamoto, Yuki ; Almeida, Fernanda R. ; Nakayama, Hideaki ; Inoue, Yuichi ; Enno, Hiroki</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c474t-62d8c6f3be518ed969e3102f9e70c3d93524fe180e1f6185697c4132702518553</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2021</creationdate><topic>Adult</topic><topic>Apnea</topic><topic>Artificial intelligence</topic><topic>Cephalometry - methods</topic><topic>Cephalometry - standards</topic><topic>Deep Learning</topic><topic>Dentistry</topic><topic>Dentistry • Original</topic><topic>Dentistry • Original Article</topic><topic>Female</topic><topic>Humans</topic><topic>Image processing</topic><topic>Internal Medicine</topic><topic>Learning algorithms</topic><topic>Machine learning</topic><topic>Male</topic><topic>Medicine</topic><topic>Medicine & Public Health</topic><topic>Middle Aged</topic><topic>Neural networks</topic><topic>Neurology</topic><topic>Oropharynx</topic><topic>Otorhinolaryngology</topic><topic>Pediatrics</topic><topic>Pneumology/Respiratory System</topic><topic>Radiography</topic><topic>Radiography - methods</topic><topic>Radiography - standards</topic><topic>Sensitivity and Specificity</topic><topic>Sleep</topic><topic>Sleep apnea</topic><topic>Sleep Apnea, Obstructive - diagnostic imaging</topic><topic>Sleep disorders</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Tsuiki, Satoru</creatorcontrib><creatorcontrib>Nagaoka, Takuya</creatorcontrib><creatorcontrib>Fukuda, Tatsuya</creatorcontrib><creatorcontrib>Sakamoto, Yuki</creatorcontrib><creatorcontrib>Almeida, Fernanda R.</creatorcontrib><creatorcontrib>Nakayama, Hideaki</creatorcontrib><creatorcontrib>Inoue, Yuichi</creatorcontrib><creatorcontrib>Enno, Hiroki</creatorcontrib><collection>Springer Nature OA Free Journals</collection><collection>Medline</collection><collection>MEDLINE</collection><collection>MEDLINE (Ovid)</collection><collection>MEDLINE</collection><collection>MEDLINE</collection><collection>PubMed</collection><collection>CrossRef</collection><collection>ProQuest Social Sciences Premium Collection</collection><collection>ProQuest Central (Corporate)</collection><collection>Immunology Abstracts</collection><collection>Neurosciences Abstracts</collection><collection>Health & Medical Collection</collection><collection>ProQuest Central (purchase pre-March 2016)</collection><collection>Medical Database (Alumni Edition)</collection><collection>Psychology Database (Alumni)</collection><collection>Social Science Database (Alumni Edition)</collection><collection>ProQuest Pharma Collection</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 Edition)</collection><collection>ProQuest Central UK/Ireland</collection><collection>Social Science Premium Collection</collection><collection>ProQuest Central Essentials</collection><collection>ProQuest Central</collection><collection>ProQuest One Community College</collection><collection>ProQuest Central Korea</collection><collection>Health Research Premium Collection</collection><collection>Health Research Premium Collection (Alumni)</collection><collection>ProQuest Central Student</collection><collection>AIDS and Cancer Research Abstracts</collection><collection>ProQuest Health & Medical Complete (Alumni)</collection><collection>Health & Medical Collection (Alumni Edition)</collection><collection>Medical Database</collection><collection>Psychology Database</collection><collection>Social Science 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 One Psychology</collection><collection>ProQuest Central Basic</collection><collection>MEDLINE - Academic</collection><collection>PubMed Central (Full Participant titles)</collection><jtitle>Sleep & breathing</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Tsuiki, Satoru</au><au>Nagaoka, Takuya</au><au>Fukuda, Tatsuya</au><au>Sakamoto, Yuki</au><au>Almeida, Fernanda R.</au><au>Nakayama, Hideaki</au><au>Inoue, Yuichi</au><au>Enno, Hiroki</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Machine learning for image-based detection of patients with obstructive sleep apnea: an exploratory study</atitle><jtitle>Sleep & breathing</jtitle><stitle>Sleep Breath</stitle><addtitle>Sleep Breath</addtitle><date>2021-12-01</date><risdate>2021</risdate><volume>25</volume><issue>4</issue><spage>2297</spage><epage>2305</epage><pages>2297-2305</pages><issn>1520-9512</issn><eissn>1522-1709</eissn><abstract>Purpose
In 2-dimensional lateral cephalometric radiographs, patients with severe obstructive sleep apnea (OSA) exhibit a more crowded oropharynx in comparison with non-OSA. We tested the hypothesis that machine learning, an application of artificial intelligence (AI), could be used to detect patients with severe OSA based on 2-dimensional images.
Methods
A deep convolutional neural network was developed (
n
= 1258; 90%) and tested (
n
= 131; 10%) using data from 1389 (100%) lateral cephalometric radiographs obtained from individuals diagnosed with severe OSA (
n
= 867; apnea hypopnea index > 30 events/h sleep) or non-OSA (
n
= 522; apnea hypopnea index < 5 events/h sleep) at a single center for sleep disorders. Three kinds of data sets were prepared by changing the area of interest using a single image: the original image without any modification (full image), an image containing a facial profile, upper airway, and craniofacial soft/hard tissues (main region), and an image containing part of the occipital region (head only). A radiologist also performed a conventional manual cephalometric analysis of the full image for comparison.
Results
The sensitivity/specificity was 0.87/0.82 for full image, 0.88/0.75 for main region, 0.71/0.63 for head only, and 0.54/0.80 for the manual analysis. The area under the receiver-operating characteristic curve was the highest for main region 0.92, for full image 0.89, for head only 0.70, and for manual cephalometric analysis 0.75.
Conclusions
A deep convolutional neural network identified individuals with severe OSA with high accuracy. Future research on this concept using AI and images can be further encouraged when discussing triage of OSA.</abstract><cop>Cham</cop><pub>Springer International Publishing</pub><pmid>33559004</pmid><doi>10.1007/s11325-021-02301-7</doi><tpages>9</tpages><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext |
| identifier | ISSN: 1520-9512 |
| ispartof | Sleep & breathing, 2021-12, Vol.25 (4), p.2297-2305 |
| issn | 1520-9512 1522-1709 |
| language | eng |
| recordid | cdi_pubmedcentral_primary_oai_pubmedcentral_nih_gov_8590647 |
| source | MEDLINE; SpringerLink Journals - AutoHoldings |
| subjects | Adult Apnea Artificial intelligence Cephalometry - methods Cephalometry - standards Deep Learning Dentistry Dentistry • Original Dentistry • Original Article Female Humans Image processing Internal Medicine Learning algorithms Machine learning Male Medicine Medicine & Public Health Middle Aged Neural networks Neurology Oropharynx Otorhinolaryngology Pediatrics Pneumology/Respiratory System Radiography Radiography - methods Radiography - standards Sensitivity and Specificity Sleep Sleep apnea Sleep Apnea, Obstructive - diagnostic imaging Sleep disorders |
| title | Machine learning for image-based detection of patients with obstructive sleep apnea: an exploratory study |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-06T01%3A37%3A12IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_pubme&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Machine%20learning%20for%20image-based%20detection%20of%20patients%20with%20obstructive%20sleep%20apnea:%20an%20exploratory%20study&rft.jtitle=Sleep%20&%20breathing&rft.au=Tsuiki,%20Satoru&rft.date=2021-12-01&rft.volume=25&rft.issue=4&rft.spage=2297&rft.epage=2305&rft.pages=2297-2305&rft.issn=1520-9512&rft.eissn=1522-1709&rft_id=info:doi/10.1007/s11325-021-02301-7&rft_dat=%3Cproquest_pubme%3E2487749533%3C/proquest_pubme%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2597012924&rft_id=info:pmid/33559004&rfr_iscdi=true |