Automated EEG-based prediction of delayed cerebral ischemia after subarachnoid hemorrhage
•A number of EEG features have been shown to be predictive of delayed cerebral ischemia (DCI), but a continuous assessment of multidimensional EEG features is lacking.•Combining spectral and epileptiform discharge feature information, using automated calculations, allows for dynamic prediction of DC...
Gespeichert in:
| Veröffentlicht in: | Clinical neurophysiology 2022-11, Vol.143, p.97-106 |
|---|---|
| Hauptverfasser: | , , , , , , , , |
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | 106 |
|---|---|
| container_issue | |
| container_start_page | 97 |
| container_title | Clinical neurophysiology |
| container_volume | 143 |
| creator | Zheng, Wei-Long Kim, Jennifer A. Elmer, Jonathan Zafar, Sahar F. Ghanta, Manohar Moura Junior, Valdery Patel, Aman Rosenthal, Eric Brandon Westover, M. |
| description | •A number of EEG features have been shown to be predictive of delayed cerebral ischemia (DCI), but a continuous assessment of multidimensional EEG features is lacking.•Combining spectral and epileptiform discharge feature information, using automated calculations, allows for dynamic prediction of DCI.•This dynamic multi-feature assessment increases the feasibility of implementing interventions in response to our EEG derived DCI risk probability.
Delayed cerebral ischemia (DCI) is a leading complication of aneurysmal subarachnoid hemorrhage (SAH) and electroencephalography (EEG) is increasingly used to evaluate DCI risk. Our goal is to develop an automated DCI prediction algorithm integrating multiple EEG features over time.
We assess 113 moderate to severe grade SAH patients to develop a machine learning model that predicts DCI risk using multiple EEG features.
Multiple EEG features discriminate between DCI and non-DCI patients when aligned either to SAH time or to DCI onset. DCI and non-DCI patients have significant differences in alpha-delta ratio (0.08 vs 0.05, p |
| doi_str_mv | 10.1016/j.clinph.2022.08.023 |
| format | Article |
| fullrecord | <record><control><sourceid>proquest_pubme</sourceid><recordid>TN_cdi_pubmedcentral_primary_oai_pubmedcentral_nih_gov_9847346</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><els_id>S138824572200877X</els_id><sourcerecordid>2720424290</sourcerecordid><originalsourceid>FETCH-LOGICAL-c463t-976bc43db57ec4ef4551165763c74fe85c3660a3697cc8834c960a77eb7e74763</originalsourceid><addsrcrecordid>eNp9kU1r3DAQhkVpaDZJ_0EpPvZiR5ZkSb4UlmWbBgK5JIechDwex1psayvZC_n31bJp2l5y0mg-3vl4CPlS0qKkpbzeFTC4ad8XjDJWUF1Qxj-QVakVy3VdsY_J5lrnTFTqnFzEuKOUKirYJ3LOZamZqtiKPK2X2Y92xjbbbm_yxsZk7QO2Dmbnp8x3WYuDfUlewIBNsEPmIvQ4OpvZbsaQxaWxwUI_eddmKeBD6O0zXpGzzg4RP7--l-Txx_Zh8zO_u7-53azvchCSz3mtZAOCt02lEAR2oqrKUlZKclCiQ10Bl5JaLmsFoDUXUKevUtgoVCKlXZLvJ9390ozYAk5zGtLsgxtteDHeOvN_ZHK9efYHU2uhuDgKfHsVCP7XgnE2Y9oQh8FO6JdomGLpaoLVNKWKUyoEH2PA7q1NSc2RitmZExVzpGKoNolKKvv674hvRX8w_N0B06EODoOJ4HCChCEgzKb17v0OvwFuHaFO</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2720424290</pqid></control><display><type>article</type><title>Automated EEG-based prediction of delayed cerebral ischemia after subarachnoid hemorrhage</title><source>MEDLINE</source><source>Elsevier ScienceDirect Journals</source><creator>Zheng, Wei-Long ; Kim, Jennifer A. ; Elmer, Jonathan ; Zafar, Sahar F. ; Ghanta, Manohar ; Moura Junior, Valdery ; Patel, Aman ; Rosenthal, Eric ; Brandon Westover, M.</creator><creatorcontrib>Zheng, Wei-Long ; Kim, Jennifer A. ; Elmer, Jonathan ; Zafar, Sahar F. ; Ghanta, Manohar ; Moura Junior, Valdery ; Patel, Aman ; Rosenthal, Eric ; Brandon Westover, M.</creatorcontrib><description>•A number of EEG features have been shown to be predictive of delayed cerebral ischemia (DCI), but a continuous assessment of multidimensional EEG features is lacking.•Combining spectral and epileptiform discharge feature information, using automated calculations, allows for dynamic prediction of DCI.•This dynamic multi-feature assessment increases the feasibility of implementing interventions in response to our EEG derived DCI risk probability.
Delayed cerebral ischemia (DCI) is a leading complication of aneurysmal subarachnoid hemorrhage (SAH) and electroencephalography (EEG) is increasingly used to evaluate DCI risk. Our goal is to develop an automated DCI prediction algorithm integrating multiple EEG features over time.
We assess 113 moderate to severe grade SAH patients to develop a machine learning model that predicts DCI risk using multiple EEG features.
Multiple EEG features discriminate between DCI and non-DCI patients when aligned either to SAH time or to DCI onset. DCI and non-DCI patients have significant differences in alpha-delta ratio (0.08 vs 0.05, p < 0.05) and percent alpha variability (0.06 vs 0.04, p < 0.05), Shannon entropy (p < 0.05) and epileptiform discharge burden (205 vs 91 discharges per hour, p < 0.05) based on whole brain and vascular territory averaging. Our model improves predictions by emphasizing the most informative features at a given time with an area under the receiver-operator curve of 0.73, by day 5 after SAH and good calibration between 48–72 hours (calibration error 0.13).
Our proposed model obtains good performance in DCI prediction.
We leverage machine learning to enable rapid, automated, multi-featured EEG assessment and has the potential to increase the utility of EEG for DCI prediction.</description><identifier>ISSN: 1388-2457</identifier><identifier>EISSN: 1872-8952</identifier><identifier>DOI: 10.1016/j.clinph.2022.08.023</identifier><identifier>PMID: 36182752</identifier><language>eng</language><publisher>Netherlands: Elsevier B.V</publisher><subject>Biomarkers ; Brain ; Brain Ischemia - complications ; Brain Ischemia - etiology ; Cerebral Infarction ; Delayed cerebral ischemia ; EEG ; Electroencephalography - adverse effects ; Epileptiform discharges ; Humans ; Machine learning ; Subarachnoid hemorrhage ; Subarachnoid Hemorrhage - complications ; Subarachnoid Hemorrhage - diagnosis</subject><ispartof>Clinical neurophysiology, 2022-11, Vol.143, p.97-106</ispartof><rights>2022</rights><rights>Copyright © 2022. Published by Elsevier B.V.</rights><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c463t-976bc43db57ec4ef4551165763c74fe85c3660a3697cc8834c960a77eb7e74763</citedby><cites>FETCH-LOGICAL-c463t-976bc43db57ec4ef4551165763c74fe85c3660a3697cc8834c960a77eb7e74763</cites><orcidid>0000-0003-3072-6198 ; 0000-0003-3900-356X ; 0000-0002-9474-6369</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://www.sciencedirect.com/science/article/pii/S138824572200877X$$EHTML$$P50$$Gelsevier$$H</linktohtml><link.rule.ids>230,314,776,780,881,3537,27901,27902,65306</link.rule.ids><backlink>$$Uhttps://www.ncbi.nlm.nih.gov/pubmed/36182752$$D View this record in MEDLINE/PubMed$$Hfree_for_read</backlink></links><search><creatorcontrib>Zheng, Wei-Long</creatorcontrib><creatorcontrib>Kim, Jennifer A.</creatorcontrib><creatorcontrib>Elmer, Jonathan</creatorcontrib><creatorcontrib>Zafar, Sahar F.</creatorcontrib><creatorcontrib>Ghanta, Manohar</creatorcontrib><creatorcontrib>Moura Junior, Valdery</creatorcontrib><creatorcontrib>Patel, Aman</creatorcontrib><creatorcontrib>Rosenthal, Eric</creatorcontrib><creatorcontrib>Brandon Westover, M.</creatorcontrib><title>Automated EEG-based prediction of delayed cerebral ischemia after subarachnoid hemorrhage</title><title>Clinical neurophysiology</title><addtitle>Clin Neurophysiol</addtitle><description>•A number of EEG features have been shown to be predictive of delayed cerebral ischemia (DCI), but a continuous assessment of multidimensional EEG features is lacking.•Combining spectral and epileptiform discharge feature information, using automated calculations, allows for dynamic prediction of DCI.•This dynamic multi-feature assessment increases the feasibility of implementing interventions in response to our EEG derived DCI risk probability.
Delayed cerebral ischemia (DCI) is a leading complication of aneurysmal subarachnoid hemorrhage (SAH) and electroencephalography (EEG) is increasingly used to evaluate DCI risk. Our goal is to develop an automated DCI prediction algorithm integrating multiple EEG features over time.
We assess 113 moderate to severe grade SAH patients to develop a machine learning model that predicts DCI risk using multiple EEG features.
Multiple EEG features discriminate between DCI and non-DCI patients when aligned either to SAH time or to DCI onset. DCI and non-DCI patients have significant differences in alpha-delta ratio (0.08 vs 0.05, p < 0.05) and percent alpha variability (0.06 vs 0.04, p < 0.05), Shannon entropy (p < 0.05) and epileptiform discharge burden (205 vs 91 discharges per hour, p < 0.05) based on whole brain and vascular territory averaging. Our model improves predictions by emphasizing the most informative features at a given time with an area under the receiver-operator curve of 0.73, by day 5 after SAH and good calibration between 48–72 hours (calibration error 0.13).
Our proposed model obtains good performance in DCI prediction.
We leverage machine learning to enable rapid, automated, multi-featured EEG assessment and has the potential to increase the utility of EEG for DCI prediction.</description><subject>Biomarkers</subject><subject>Brain</subject><subject>Brain Ischemia - complications</subject><subject>Brain Ischemia - etiology</subject><subject>Cerebral Infarction</subject><subject>Delayed cerebral ischemia</subject><subject>EEG</subject><subject>Electroencephalography - adverse effects</subject><subject>Epileptiform discharges</subject><subject>Humans</subject><subject>Machine learning</subject><subject>Subarachnoid hemorrhage</subject><subject>Subarachnoid Hemorrhage - complications</subject><subject>Subarachnoid Hemorrhage - diagnosis</subject><issn>1388-2457</issn><issn>1872-8952</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2022</creationdate><recordtype>article</recordtype><sourceid>EIF</sourceid><recordid>eNp9kU1r3DAQhkVpaDZJ_0EpPvZiR5ZkSb4UlmWbBgK5JIechDwex1psayvZC_n31bJp2l5y0mg-3vl4CPlS0qKkpbzeFTC4ad8XjDJWUF1Qxj-QVakVy3VdsY_J5lrnTFTqnFzEuKOUKirYJ3LOZamZqtiKPK2X2Y92xjbbbm_yxsZk7QO2Dmbnp8x3WYuDfUlewIBNsEPmIvQ4OpvZbsaQxaWxwUI_eddmKeBD6O0zXpGzzg4RP7--l-Txx_Zh8zO_u7-53azvchCSz3mtZAOCt02lEAR2oqrKUlZKclCiQ10Bl5JaLmsFoDUXUKevUtgoVCKlXZLvJ9390ozYAk5zGtLsgxtteDHeOvN_ZHK9efYHU2uhuDgKfHsVCP7XgnE2Y9oQh8FO6JdomGLpaoLVNKWKUyoEH2PA7q1NSc2RitmZExVzpGKoNolKKvv674hvRX8w_N0B06EODoOJ4HCChCEgzKb17v0OvwFuHaFO</recordid><startdate>20221101</startdate><enddate>20221101</enddate><creator>Zheng, Wei-Long</creator><creator>Kim, Jennifer A.</creator><creator>Elmer, Jonathan</creator><creator>Zafar, Sahar F.</creator><creator>Ghanta, Manohar</creator><creator>Moura Junior, Valdery</creator><creator>Patel, Aman</creator><creator>Rosenthal, Eric</creator><creator>Brandon Westover, M.</creator><general>Elsevier B.V</general><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>7X8</scope><scope>5PM</scope><orcidid>https://orcid.org/0000-0003-3072-6198</orcidid><orcidid>https://orcid.org/0000-0003-3900-356X</orcidid><orcidid>https://orcid.org/0000-0002-9474-6369</orcidid></search><sort><creationdate>20221101</creationdate><title>Automated EEG-based prediction of delayed cerebral ischemia after subarachnoid hemorrhage</title><author>Zheng, Wei-Long ; Kim, Jennifer A. ; Elmer, Jonathan ; Zafar, Sahar F. ; Ghanta, Manohar ; Moura Junior, Valdery ; Patel, Aman ; Rosenthal, Eric ; Brandon Westover, M.</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c463t-976bc43db57ec4ef4551165763c74fe85c3660a3697cc8834c960a77eb7e74763</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2022</creationdate><topic>Biomarkers</topic><topic>Brain</topic><topic>Brain Ischemia - complications</topic><topic>Brain Ischemia - etiology</topic><topic>Cerebral Infarction</topic><topic>Delayed cerebral ischemia</topic><topic>EEG</topic><topic>Electroencephalography - adverse effects</topic><topic>Epileptiform discharges</topic><topic>Humans</topic><topic>Machine learning</topic><topic>Subarachnoid hemorrhage</topic><topic>Subarachnoid Hemorrhage - complications</topic><topic>Subarachnoid Hemorrhage - diagnosis</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Zheng, Wei-Long</creatorcontrib><creatorcontrib>Kim, Jennifer A.</creatorcontrib><creatorcontrib>Elmer, Jonathan</creatorcontrib><creatorcontrib>Zafar, Sahar F.</creatorcontrib><creatorcontrib>Ghanta, Manohar</creatorcontrib><creatorcontrib>Moura Junior, Valdery</creatorcontrib><creatorcontrib>Patel, Aman</creatorcontrib><creatorcontrib>Rosenthal, Eric</creatorcontrib><creatorcontrib>Brandon Westover, M.</creatorcontrib><collection>Medline</collection><collection>MEDLINE</collection><collection>MEDLINE (Ovid)</collection><collection>MEDLINE</collection><collection>MEDLINE</collection><collection>PubMed</collection><collection>CrossRef</collection><collection>MEDLINE - Academic</collection><collection>PubMed Central (Full Participant titles)</collection><jtitle>Clinical neurophysiology</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Zheng, Wei-Long</au><au>Kim, Jennifer A.</au><au>Elmer, Jonathan</au><au>Zafar, Sahar F.</au><au>Ghanta, Manohar</au><au>Moura Junior, Valdery</au><au>Patel, Aman</au><au>Rosenthal, Eric</au><au>Brandon Westover, M.</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Automated EEG-based prediction of delayed cerebral ischemia after subarachnoid hemorrhage</atitle><jtitle>Clinical neurophysiology</jtitle><addtitle>Clin Neurophysiol</addtitle><date>2022-11-01</date><risdate>2022</risdate><volume>143</volume><spage>97</spage><epage>106</epage><pages>97-106</pages><issn>1388-2457</issn><eissn>1872-8952</eissn><abstract>•A number of EEG features have been shown to be predictive of delayed cerebral ischemia (DCI), but a continuous assessment of multidimensional EEG features is lacking.•Combining spectral and epileptiform discharge feature information, using automated calculations, allows for dynamic prediction of DCI.•This dynamic multi-feature assessment increases the feasibility of implementing interventions in response to our EEG derived DCI risk probability.
Delayed cerebral ischemia (DCI) is a leading complication of aneurysmal subarachnoid hemorrhage (SAH) and electroencephalography (EEG) is increasingly used to evaluate DCI risk. Our goal is to develop an automated DCI prediction algorithm integrating multiple EEG features over time.
We assess 113 moderate to severe grade SAH patients to develop a machine learning model that predicts DCI risk using multiple EEG features.
Multiple EEG features discriminate between DCI and non-DCI patients when aligned either to SAH time or to DCI onset. DCI and non-DCI patients have significant differences in alpha-delta ratio (0.08 vs 0.05, p < 0.05) and percent alpha variability (0.06 vs 0.04, p < 0.05), Shannon entropy (p < 0.05) and epileptiform discharge burden (205 vs 91 discharges per hour, p < 0.05) based on whole brain and vascular territory averaging. Our model improves predictions by emphasizing the most informative features at a given time with an area under the receiver-operator curve of 0.73, by day 5 after SAH and good calibration between 48–72 hours (calibration error 0.13).
Our proposed model obtains good performance in DCI prediction.
We leverage machine learning to enable rapid, automated, multi-featured EEG assessment and has the potential to increase the utility of EEG for DCI prediction.</abstract><cop>Netherlands</cop><pub>Elsevier B.V</pub><pmid>36182752</pmid><doi>10.1016/j.clinph.2022.08.023</doi><tpages>10</tpages><orcidid>https://orcid.org/0000-0003-3072-6198</orcidid><orcidid>https://orcid.org/0000-0003-3900-356X</orcidid><orcidid>https://orcid.org/0000-0002-9474-6369</orcidid><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext |
| identifier | ISSN: 1388-2457 |
| ispartof | Clinical neurophysiology, 2022-11, Vol.143, p.97-106 |
| issn | 1388-2457 1872-8952 |
| language | eng |
| recordid | cdi_pubmedcentral_primary_oai_pubmedcentral_nih_gov_9847346 |
| source | MEDLINE; Elsevier ScienceDirect Journals |
| subjects | Biomarkers Brain Brain Ischemia - complications Brain Ischemia - etiology Cerebral Infarction Delayed cerebral ischemia EEG Electroencephalography - adverse effects Epileptiform discharges Humans Machine learning Subarachnoid hemorrhage Subarachnoid Hemorrhage - complications Subarachnoid Hemorrhage - diagnosis |
| title | Automated EEG-based prediction of delayed cerebral ischemia after subarachnoid hemorrhage |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-09T12%3A49%3A39IST&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=Automated%20EEG-based%20prediction%20of%20delayed%20cerebral%20ischemia%20after%20subarachnoid%20hemorrhage&rft.jtitle=Clinical%20neurophysiology&rft.au=Zheng,%20Wei-Long&rft.date=2022-11-01&rft.volume=143&rft.spage=97&rft.epage=106&rft.pages=97-106&rft.issn=1388-2457&rft.eissn=1872-8952&rft_id=info:doi/10.1016/j.clinph.2022.08.023&rft_dat=%3Cproquest_pubme%3E2720424290%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=2720424290&rft_id=info:pmid/36182752&rft_els_id=S138824572200877X&rfr_iscdi=true |