{"id":24780,"date":"2025-11-07T11:01:40","date_gmt":"2025-11-07T11:01:40","guid":{"rendered":"https:\/\/natus.com\/insights\/efficiency-advantages-neuro-ai-technology-for-eeg\/"},"modified":"2026-01-26T19:53:44","modified_gmt":"2026-01-26T19:53:44","slug":"avantages-defficacite-de-la-technologie-neuro-ai-pour-leeg","status":"publish","type":"insights","link":"https:\/\/natus.com\/fr\/insights\/avantages-defficacite-de-la-technologie-neuro-ai-pour-leeg\/","title":{"rendered":"Avantages d\u2019efficacit\u00e9 de la technologie neuro AI pour l\u2019EEG"},"content":{"rendered":"","protected":false},"author":2,"template":"","insight_type":[319],"insights_category":[446],"insights_tag":[481],"class_list":["post-24780","insights","type-insights","status-publish","hentry","insight_type-neuro","insights_category-eeg","insights_tag-ai-fr"],"acf":{"content_blocks":[{"acf_fc_layout":"hero_insights","_acfe_flexible_layout_title":null,"_acfe_flexible_toggle":null,"hero_insights":{"module_id":"n651a1bdf6995b","module_class":"","background_color":"#00aaa7","intro":"","h1":"Avantages d\u2019efficacit\u00e9 de la technologie neuro AI pour l\u2019EEG","insights_image":{"ID":14921,"id":14921,"title":"Efficiency AI_Insights 1300x500","filename":"Efficiency-AI_Insights-1300x500-1.png","filesize":963063,"url":"https:\/\/natus.com\/wp-content\/uploads\/Efficiency-AI_Insights-1300x500-1.png","link":"https:\/\/natus.com\/fr\/insights\/avantages-defficacite-de-la-technologie-neuro-ai-pour-leeg\/efficiency-ai_insights-1300x500-2\/","alt":"How can Ai help improve efficiency for EEG neurodiagnostic professionals?","author":"2","description":"","caption":"","name":"efficiency-ai_insights-1300x500-2","status":"inherit","uploaded_to":24780,"date":"2023-10-12 21:02:58","modified":"2023-10-12 21:03:25","menu_order":0,"mime_type":"image\/png","type":"image","subtype":"png","icon":"https:\/\/natus.com\/wp-includes\/images\/media\/default.png","width":1300,"height":500,"sizes":{"thumbnail":"https:\/\/natus.com\/wp-content\/uploads\/Efficiency-AI_Insights-1300x500-1.png","thumbnail-width":128,"thumbnail-height":49,"medium":"https:\/\/natus.com\/wp-content\/uploads\/Efficiency-AI_Insights-1300x500-1.png","medium-width":1300,"medium-height":500,"medium_large":"https:\/\/natus.com\/wp-content\/uploads\/Efficiency-AI_Insights-1300x500-1-768x295.png","medium_large-width":768,"medium_large-height":295,"large":"https:\/\/natus.com\/wp-content\/uploads\/Efficiency-AI_Insights-1300x500-1.png","large-width":1300,"large-height":500,"1536x1536":"https:\/\/natus.com\/wp-content\/uploads\/Efficiency-AI_Insights-1300x500-1.png","1536x1536-width":1300,"1536x1536-height":500,"2048x2048":"https:\/\/natus.com\/wp-content\/uploads\/Efficiency-AI_Insights-1300x500-1.png","2048x2048-width":1300,"2048x2048-height":500}}}},{"acf_fc_layout":"simple_content","_acfe_flexible_layout_title":null,"_acfe_flexible_toggle":null,"content_full_width_landing":{"module_options":{"":null,"module_id":"n65235aa0431c8","module_class":"","module_background_type":"color","module_background_color":"#f1f1f1","module_background_image":false,"module_background_video":"","activate_custom_padding":false,"padding_top_desktop":0,"padding_top_tablet":"","padding_top_mobile":"","padding_bottom_desktop":"","padding_bottom_tablet":"","padding_bottom_mobile":"","activate_custom_margin":false,"margin_top_desktop":"","margin_top_tablet":"","margin_top_mobile":"","margin_bottom_desktop":"","margin_bottom_tablet":"","margin_bottom_mobile":"","disable_on":[],"content_alignment_desktop":"left","content_alignment_tablet":"left","content_alignment_mobile":"left"},"content":"<p>Dans le paysage en rapide \u00e9volution de l\u2019informatique de sant\u00e9, l\u2019IA s&rsquo;est impos\u00e9e comme une force essentielle pour aider les professionnels de la sant\u00e9 \u00e0 devenir plus efficaces. L\u2019adoption de l\u2019IA dans le secteur m\u00e9dical a vari\u00e9 selon la sp\u00e9cialit\u00e9 et l\u2019application, certains domaines progressant plus rapidement que d\u2019autres. Depuis de nombreuses ann\u00e9es, la cardiologie, par exemple, utilise l\u2019IA pour les tests d\u2019ECG et d\u2019imagerie afin de d\u00e9tecter plus facilement les anomalies cardiaques subtiles et de fournir des \u00e9valuations plus rapides. Il en va de m\u00eame pour la radiologie et la mammographie, o\u00f9 l\u2019utilisation de la technologie de l\u2019IA<a href=\"https:\/\/www.ncbi.nlm.nih.gov\/pmc\/articles\/PMC7592467\/\" target=\"_blank\" rel=\"noopener\"> a connu une forte croissance au cours de la derni\u00e8re d\u00e9cennie<\/a>.<sup>i<\/sup><\/p>\n<p>&nbsp;<\/p>\n<p>Les <a href=\"https:\/\/www.neurologyindia.com\/article.asp?issn=0028-3886;year=2018;volume=66;issue=4;spage=934;epage=939;aulast=Ganapathy\" target=\"_blank\" rel=\"noopener\">applications de l\u2019IA en neurologie sont nombreuses<\/a>, de la chirurgie robotique autonome \u00e0 la pr\u00e9diction des r\u00e9sultats des op\u00e9rations d\u2019\u00e9pilepsie, en passant par l\u2019autoclassification des images pour les neuro-oncologues.<sup>ii<\/sup><a href=\"#_ftn1\" name=\"_ftnref1\"><\/a> Pourtant, dans le domaine de l\u2019IA neurologique, qui progresse rapidement, l\u2019utilisation de l\u2019IA pour l\u2019interpr\u00e9tation de <a href=\"https:\/\/jamanetwork.com\/journals\/jamaneurology\/fullarticle\/2806244\" target=\"_blank\" rel=\"noopener\">l\u2019EEG constitue l&rsquo;un des plus grands avantages.<\/a><sup>iii<\/sup> \u00c0 mesure que ces outils \u00e9voluent, passant d\u2019algorithmes d\u2019apprentissage automatique plus traditionnels \u00e0 une technologie int\u00e9grant l\u2019apprentissage profond, les neurologues, les \u00e9pileptologues, les personnels de neurodiagnostic, et d\u2019autres professionnels de la sant\u00e9 constatent une remarquable am\u00e9lioration de l\u2019efficacit\u00e9, ce qui permet de r\u00e9duire les co\u00fbts tout en am\u00e9liorant les r\u00e9sultats en mati\u00e8re de sant\u00e9.<\/p>\n<p>&nbsp;<\/p>\n<p>Les enregistrements EEG g\u00e9n\u00e8rent de grandes quantit\u00e9s de donn\u00e9es, il n\u2019est donc pas surprenant qu\u2019au cours des quatre derni\u00e8res d\u00e9cennies, l\u2019apprentissage automatique <a href=\"https:\/\/www.ncbi.nlm.nih.gov\/pmc\/articles\/PMC8615531\/\">ait \u00e9t\u00e9 utilis\u00e9 sous une forme ou une autre pour la classification EEG.<sup>iv<\/sup><\/a> En identifiant rapidement les anomalies potentielles, les algorithmes traditionnels aident depuis longtemps les neurologues et les \u00e9quipes de soins neurologiques \u00e0 hi\u00e9rarchiser les cas critiques, permettant ainsi des interventions plus rapides pour les patients souffrant de troubles neurologiques graves. Il est extr\u00eamement utile qu\u2019un grand nombre d\u2019enregistrements EEG valid\u00e9s existent d\u00e9j\u00e0, ce qui offre aux outils d\u2019IA de nombreuses informations pour apprendre.<\/p>\n<h6><\/h6>\n<h6><span style=\"color: #008b96;\"><strong>Faire confiance \u00e0 l\u2019IA pour l\u2019examen de l\u2019EEG<\/strong><\/span><\/h6>\n<p>Les algorithmes avanc\u00e9s d\u2019aujourd\u2019hui sont entra\u00een\u00e9s sur d\u2019\u00e9normes ensembles de donn\u00e9es valid\u00e9es, ce qui leur permet de reconna\u00eetre des anomalies subtiles dans les formes d\u2019ondes EEG qui pourraient \u00e9chapper \u00e0 l\u2019observation humaine. <a href=\"https:\/\/www.ncbi.nlm.nih.gov\/pmc\/articles\/PMC6108188\/\" target=\"_blank\" rel=\"noopener\">L\u2019IA neurologique est particuli\u00e8rement utile dans les sc\u00e9narios de surveillance \u00e0 long terme,<\/a> lorsqu\u2019il est essentiel d\u2019identifier les tendances ou les changements au fil du temps.<sup>v<\/sup> En signalant automatiquement les \u00e9carts par rapport aux sch\u00e9mas de base, les algorithmes permettent aux neurologues de traiter rapidement les affections neurologiques, m\u00eame celles qui \u00e9voluent rapidement.<sup>vi<\/sup><\/p>\n<p>&nbsp;<\/p>\n<p>En outre, les algorithmes d\u2019apprentissage profond et les r\u00e9seaux neuronaux correctement entra\u00een\u00e9s sur de grands ensembles de donn\u00e9es bien annot\u00e9s peuvent r\u00e9duire consid\u00e9rablement le temps que les \u00e9quipes de soins neurologiques consacrent \u00e0 l\u2019interpr\u00e9tation de l\u2019EEG \u00e0 la suite d&rsquo;une surveillance \u00e0 long terme (LTM), d\u2019un EEG ambulatoire et d\u2019un EEG de routine.<\/p>\n<p>&nbsp;<\/p>\n<p>Plus pr\u00e9cis\u00e9ment, les outils d\u2019IA neurologique pour l\u2019EEG devraient permettre de r\u00e9duire le temps et d\u2019accro\u00eetre l\u2019efficacit\u00e9 dans plusieurs domaines d\u2019int\u00e9r\u00eat, notamment :<\/p>\n<ul>\n<li><span style=\"color: #008b96;\"><strong>Extraction des caract\u00e9ristiques.<\/strong> <\/span>Les signaux EEG sont complexes et contiennent de grandes quantit\u00e9s d\u2019informations, ce qui fait de l\u2019extraction des caract\u00e9ristiques des signaux EEG un \u00e9l\u00e9ment essentiel pour la r\u00e9ussite de l\u2019apprentissage automatique, et plus particuli\u00e8rement des algorithmes d\u2019apprentissage profond. <a href=\"https:\/\/iopscience.iop.org\/article\/10.1088\/1741-2552\/ab260c\" target=\"_blank\" rel=\"noopener\">Des revues syst\u00e9matiques sur l\u2019utilisation de l\u2019IA pour le d\u00e9codage neuronal des signaux EEG <\/a> ont montr\u00e9 un potentiel \u00e9norme, car les algorithmes d\u2019apprentissage profond excellent dans la reconnaissance de sch\u00e9mas complexes dans des ensembles de donn\u00e9es vastes et complexes, identifiant des corr\u00e9lations cach\u00e9es dans les mod\u00e8les de r\u00e9seaux neuronaux que les m\u00e9thodes traditionnelles d&rsquo;interpr\u00e9tation de l\u2019EEG manquent souvent.<sup>vii<\/sup><\/li>\n<\/ul>\n<ul>\n<li><strong><span style=\"color: #008b96;\">D\u00e9tection d\u2019\u00e9v\u00e9nements sp\u00e9cifiques. <\/span> <\/strong>Parce qu\u2019ils peuvent analyser de grandes quantit\u00e9s de donn\u00e9es, reconna\u00eetre des sch\u00e9mas complexes et faire des pr\u00e9dictions pr\u00e9cises, les algorithmes sont capables de reconna\u00eetre plus rapidement des \u00e9v\u00e9nements sp\u00e9cifiques dans les enregistrements EEG que les m\u00e9thodes traditionnelles. L\u2019apprentissage profond s\u2019est r\u00e9v\u00e9l\u00e9 tr\u00e8s efficace pour d\u00e9tecter les crises d\u2019\u00e9pilepsie, par exemple en r\u00e9duisant consid\u00e9rablement le temps consacr\u00e9 \u00e0 l\u2019examen des enregistrements EEG, qui peut prendre des heures, voire des jours, pour un seul sujet en crise. Gr\u00e2ce \u00e0 la capacit\u00e9 d\u2019extraire automatiquement les caract\u00e9ristiques pertinentes des donn\u00e9es EEG, <a href=\"https:\/\/www.ncbi.nlm.nih.gov\/pmc\/articles\/PMC8718399\/\" target=\"_blank\" rel=\"noopener\">les mod\u00e8les d\u2019apprentissage profond tels que les r\u00e9seaux neuronaux convolutifs ou r\u00e9currents <\/a>peuvent d\u00e9tecter plus rapidement et plus pr\u00e9cis\u00e9ment les crises d\u2019\u00e9pilepsie, m\u00eame dans les enregistrements bruyants ou complexes.<sup>viii<\/sup><\/li>\n<\/ul>\n<ul>\n<li><strong><span style=\"color: #008b96;\">Surveillance \u00e0 long terme. <\/span><\/strong>Les outils d\u2019EEG bas\u00e9s sur l\u2019IA sont de plus en plus pr\u00e9cieux pour la surveillance \u00e0 long terme (LTM), o\u00f9 de grands volumes de donn\u00e9es sont g\u00e9n\u00e9r\u00e9s pendant des heures ou des jours. Ces syst\u00e8mes peuvent automatiquement identifier et classer par ordre de priorit\u00e9 les \u00e9v\u00e9nements cliniquement pertinents, aidant ainsi les cliniciens \u00e0 g\u00e9rer les enregistrements prolong\u00e9s de mani\u00e8re plus efficace et efficiente. En reconnaissant les sch\u00e9mas EEG individualis\u00e9s qui sont en corr\u00e9lation avec des conditions sp\u00e9cifiques ou des r\u00e9ponses au traitement, l\u2019IA peut \u00e9galement soutenir des plans de soins plus personnalis\u00e9s, adapt\u00e9s au profil neurologique de chaque patient. Cela permet de s\u2019assurer que les \u00e9v\u00e9nements critiques ne sont pas manqu\u00e9s, m\u00eame lorsque le personnel n\u2019examine pas activement les donn\u00e9es.<\/li>\n<\/ul>\n<h6><\/h6>\n<h6><span style=\"color: #008b96;\"><strong>Interaction collaborative entre les humains et l\u2019IA<\/strong><\/span><\/h6>\n<p>L\u2019Institut Brookings d\u00e9finit le concept de collaboration homme-machine comme une relation compos\u00e9e de trois \u00e9l\u00e9ments : l\u2019humain, la machine, et les interactions et interd\u00e9pendances entre eux. Pour les t\u00e2ches tr\u00e8s complexes telles que l\u2019analyse EEG, l\u2019IA a le potentiel d\u2019am\u00e9liorer consid\u00e9rablement les r\u00e9sultats lorsqu\u2019elle est utilis\u00e9e pour augmenter et soutenir les capacit\u00e9s humaines. Une fois la confiance \u00e9tablie entre les \u00e9quipes de soins neurologiques et la technologie de l&rsquo;IA, ce partenariat d\u00e9bouche sur une approche synergique qui va bien au-del\u00e0 de ce que l&rsquo;une ou l&rsquo;autre pourrait r\u00e9aliser ind\u00e9pendamment. Par ailleurs, lorsque l\u2019expertise humaine est rare, les outils d\u2019IA peuvent r\u00e9duire consid\u00e9rablement le temps n\u00e9cessaire au diagnostic, am\u00e9liorant ainsi l\u2019acc\u00e8s aux soins neurologiques pour les communaut\u00e9s \u00e9loign\u00e9es et mal desservies.<\/p>\n<p>&nbsp;<\/p>\n<p>De nombreux outils d\u2019IA continuent d\u2019apprendre au fur et \u00e0 mesure qu\u2019ils re\u00e7oivent de nouvelles donn\u00e9es, en utilisant le retour d\u2019information humain pour affiner et acc\u00e9l\u00e9rer les performances de l\u2019algorithme. Dans le contexte d\u2019autoSCORE, cependant, le mod\u00e8le utilise un algorithme valid\u00e9, sans apprentissage, qui reste coh\u00e9rent dans le temps afin de garantir la fiabilit\u00e9 et la reproductibilit\u00e9. L\u2019immense valeur d\u2019<a href=\"https:\/\/natus.com\/neuro\/autoscore-ai\/\" target=\"_blank\" rel=\"noopener\">autoSCORE<\/a> r\u00e9side dans l\u2019application d\u2019un cadre coh\u00e9rent et valid\u00e9 pour la d\u00e9tection automatique d\u2019\u00e9v\u00e9nements, que l\u2019expert humain examine, valide et interpr\u00e8te ensuite. Cette r\u00e9partition des r\u00f4les permet de gagner en efficacit\u00e9 et en coh\u00e9rence sans compromettre la supervision ou le jugement clinique.<\/p>\n<p>&nbsp;<\/p>\n<p>L\u2019int\u00e9gration de l\u2019IA \u00e0 l\u2019analyse EEG acc\u00e9l\u00e8re les processus qui, traditionnellement, pouvaient prendre de nombreuses heures, augmentant ainsi consid\u00e9rablement l\u2019efficacit\u00e9 des \u00e9quipes de soins neurologiques. \u00c0 l\u2019avenir, les outils d\u2019IA pour la neurologie offrent une immense promesse. Les avanc\u00e9es en apprentissage profond et en reconnaissance des sch\u00e9mas continueront d\u2019affiner la d\u00e9tection des \u00e9v\u00e9nements et aideront \u00e0 identifier des anomalies encore plus subtiles dans des d\u00e9lais de plus en plus courts. Au fur et \u00e0 mesure de son \u00e9volution, l\u2019IA fa\u00e7onnera l\u2019avenir de l&rsquo;interpr\u00e9tation et de l\u2019analyse des EEG, en collaborant avec les cliniciens pour une approche plus pr\u00e9cise, plus efficace et plus centr\u00e9e sur le patient en mati\u00e8re de soins de sant\u00e9 neurologiques.<\/p>\n<p><!--HubSpot Call-to-Action Code --><span id=\"hs-cta-wrapper-a0cec4ab-373f-40cc-8133-bf16a3cf6595\" class=\"hs-cta-wrapper\"><span id=\"hs-cta-a0cec4ab-373f-40cc-8133-bf16a3cf6595\" class=\"hs-cta-node hs-cta-a0cec4ab-373f-40cc-8133-bf16a3cf6595\"><!-- [if lte IE 8]>\n\n\n<div id=\"hs-cta-ie-element\"><\/div>\n\n\n<![endif]--><a href=\"https:\/\/cta-redirect.hubspot.com\/cta\/redirect\/3002890\/a0cec4ab-373f-40cc-8133-bf16a3cf6595\" target=\"_blank\" rel=\"noopener\"><img decoding=\"async\" id=\"hs-cta-img-a0cec4ab-373f-40cc-8133-bf16a3cf6595\" class=\"hs-cta-img alignright\" style=\"border-width: 0px;\" src=\"https:\/\/no-cache.hubspot.com\/cta\/default\/3002890\/a0cec4ab-373f-40cc-8133-bf16a3cf6595.png\" alt=\"practical applications of artificial intelligence in EEG\" \/><\/a><\/span><\/span><br \/>\n<span id=\"hs-cta-wrapper-a0cec4ab-373f-40cc-8133-bf16a3cf6595\" class=\"hs-cta-wrapper\"><script src=\"https:\/\/js.hscta.net\/cta\/current.js\" charset=\"utf-8\"><\/script><script type=\"text\/javascript\"> hbspt.cta.load(3002890, 'a0cec4ab-373f-40cc-8133-bf16a3cf6595', {\"useNewLoader\":\"true\",\"region\":\"na1\"}); <\/script><\/span><!-- end HubSpot Call-to-Action Code --><\/p>\n<hr \/>\n<p><span style=\"font-size: 12px;\"><strong><span style=\"color: #008b96;\">SOURCES<\/span><\/strong><\/span><\/p>\n<p><span style=\"font-size: 11px;\">1. Dobkin PL. Art of medicine, art as medicine, and art for medical education. Can Med Educ J. 2020 Dec 7;11(6):e172-e175. doi: 10.36834\/cmej.70298. PMID: 33349773; PMCID: PMC7749674.<br \/>\n2. Ganapathy Krishnan, Abdul Shabbir Syed, Nursetyo Aldilas Achmad \u201cArtificial intelligence in neurosciences: A clinician&rsquo;s perspective\u201d Neurology India 2018, Volume 66, Issue Number 4, Page 934-939<br \/>\n3. Saeidi M, Karwowski W, Farahani FV, Fiok K, Taiar R, Hancock PA, Al-Juaid A. Neural Decoding of EEG Signals with Machine Learning: A Systematic Review. Brain Sci. 2021 Nov 18;11(11):1525. doi: 10.3390\/brainsci11111525. PMID: 34827524; PMCID: PMC8615531.<br \/>\n4. Varatharajah Y, Berry B, Cimbalnik J, Kremen V, Van Gompel J, Stead M, Brinkmann B, Iyer R, Worrell G. Integrating artificial intelligence with real-time intracranial EEG monitoring to automate interictal identification of seizure onset zones in focal epilepsy. Neural Eng. 2018 Aug;15(4):046035. doi: 10.1088\/1741-2552\/aac960. Epub 2018 Jun 1. PMID: 29855436; PMCID: PMC6108188.<br \/>\n5. Deep learning-based electroencephalography analysis: a systematic review. Yannick Roy5,1, Hubert Banville5,2,3, Isabela Albuquerque4, Alexandre Gramfort2, Tiago H Falk4 and Jocelyn Faubert1. Published 14 August 2019 \u2022 \u00a9 2019 IOP Publishing Ltd. Journal of Neural Engineering, Volume 16, Number 5Citation Yannick Roy et al 2019 J. Neural Eng. 16 051001DOI 10.1088\/1741-2552\/ab260c<br \/>\n6. He C, Liu J, Zhu Y, Du W. Data Augmentation for Deep Neural Networks Model in EEG Classification Task: A Review. Front Hum Neurosci. 2021 Dec 17;15:765525. doi: 10.3389\/fnhum.2021.765525. PMID: 34975434; PMCID: PMC8718399.<br \/>\n7. Djanian S, Bruun A, Nielsen TD. Sleep classification using Consumer Sleep Technologies and AI: A review of the current landscape. Sleep Med. 2022 Dec;100:390-403. doi: 10.1016\/j.sleep.2022.09.004. Epub 2022 Sep 22. PMID: 36206600.<br \/>\n8. Kent Jessica, HealthITAnalytics. (2020, June 30). Artificial intelligence detects epileptic seizures in real time. https:\/\/healthitanalytics.com\/news\/artificial-intelligence-detects-epileptic-seizures-in-real-time<br \/>\n9.Resnick, D., &amp; Wessel, D. (2021, February 18). Building Trust in human-machine teams. Brookings. https:\/\/www.brookings.edu\/articles\/building-trust-in-human-machine-teams\/<\/span><\/p>\n<p><span style=\"font-size: 11px;\">052214 RevC<\/span><\/p>\n"}},{"acf_fc_layout":"related_articles","_acfe_flexible_layout_title":null,"_acfe_flexible_toggle":null,"related_articles":{"module_options":{"":null,"module_id":"n651a1bdf93439","module_class":"","module_background_type":"color","module_background_color":"","module_background_image":false,"module_background_video":"","activate_custom_padding":false,"padding_top_desktop":0,"padding_top_tablet":"","padding_top_mobile":"","padding_bottom_desktop":"","padding_bottom_tablet":"","padding_bottom_mobile":"","activate_custom_margin":false,"margin_top_desktop":"","margin_top_tablet":"","margin_top_mobile":"","margin_bottom_desktop":"","margin_bottom_tablet":"","margin_bottom_mobile":"","disable_on":[],"content_alignment_desktop":"left","content_alignment_tablet":"left","content_alignment_mobile":"left"},"intro_text":"Articles li\u00e9s","intro_text_color":"#005e63","intro_link":{"type":"post","value":"1527","url":"https:\/\/natus.com\/insights\/","name":"Insights","title":"Afficher tous les articles","target":""},"source_type":"taxonomies","tiles":false,"news":[{"ID":12831,"post_author":"2","post_date":"2023-10-16 17:42:56","post_date_gmt":"2023-10-16 17:42:56","post_content":"","post_title":"Using continuous EEG monitoring in the ICU","post_excerpt":"","post_status":"publish","comment_status":"closed","ping_status":"closed","post_password":"","post_name":"using-continuous-eeg-monitoring-in-icu-benefits-obstacles","to_ping":"","pinged":"","post_modified":"2025-03-27 19:00:28","post_modified_gmt":"2025-03-27 19:00:28","post_content_filtered":"","post_parent":0,"guid":"https:\/\/natus.com\/?post_type=insights&#038;p=12831","menu_order":0,"post_type":"insights","post_mime_type":"","comment_count":"0","filter":"raw"},{"ID":24761,"post_author":"2","post_date":"2025-10-31 11:02:31","post_date_gmt":"2025-10-31 11:02:31","post_content":"","post_title":"4 raisons pour lesquelles les neurologues peuvent avoir confiance en l\u2019IA pour l\u2019EEG","post_excerpt":"","post_status":"publish","comment_status":"closed","ping_status":"closed","post_password":"","post_name":"4-raisons-pour-lesquelles-les-neurologues-peuvent-avoir-confiance-en-lia-pour-leeg","to_ping":"","pinged":"","post_modified":"2025-08-27 16:15:11","post_modified_gmt":"2025-08-27 16:15:11","post_content_filtered":"","post_parent":0,"guid":"https:\/\/natus.com\/insights\/4-reasons-neurologists-can-trust-ai-for-eeg\/","menu_order":0,"post_type":"insights","post_mime_type":"","comment_count":"0","filter":"raw"},{"ID":24726,"post_author":"2","post_date":"2023-10-18 11:00:05","post_date_gmt":"2023-10-18 11:00:05","post_content":"","post_title":"5 avantages cl\u00e9s de l\u2019intelligence artificielle pour l\u2019EEG","post_excerpt":"","post_status":"publish","comment_status":"closed","ping_status":"closed","post_password":"","post_name":"5-avantages-cles-de-lintelligence-artificielle-pour-leeg","to_ping":"","pinged":"","post_modified":"2025-08-26 15:22:34","post_modified_gmt":"2025-08-26 15:22:34","post_content_filtered":"","post_parent":0,"guid":"https:\/\/natus.com\/insights\/5-key-benefits-artificial-intelligence-for-eeg\/","menu_order":0,"post_type":"insights","post_mime_type":"","comment_count":"0","filter":"raw"}],"taxonomies":["481"],"how_many_posts":"2","read_more_button_title":""}}],"category_image":{"ID":14916,"id":14916,"title":"Efficiency AI_Insights 500x400","filename":"Efficiency-AI_Insights-500x400-1.png","filesize":333131,"url":"https:\/\/natus.com\/wp-content\/uploads\/Efficiency-AI_Insights-500x400-1.png","link":"https:\/\/natus.com\/fr\/insights\/avantages-defficacite-de-la-technologie-neuro-ai-pour-leeg\/efficiency-ai_insights-500x400-2\/","alt":"How can Ai help improve efficiency for EEG neurodiagnostic professionals?","author":"2","description":"","caption":"","name":"efficiency-ai_insights-500x400-2","status":"inherit","uploaded_to":24780,"date":"2023-10-12 21:02:38","modified":"2024-07-30 14:58:56","menu_order":0,"mime_type":"image\/png","type":"image","subtype":"png","icon":"https:\/\/natus.com\/wp-includes\/images\/media\/default.png","width":500,"height":400,"sizes":{"thumbnail":"https:\/\/natus.com\/wp-content\/uploads\/Efficiency-AI_Insights-500x400-1.png","thumbnail-width":120,"thumbnail-height":96,"medium":"https:\/\/natus.com\/wp-content\/uploads\/Efficiency-AI_Insights-500x400-1.png","medium-width":500,"medium-height":400,"medium_large":"https:\/\/natus.com\/wp-content\/uploads\/Efficiency-AI_Insights-500x400-1.png","medium_large-width":500,"medium_large-height":400,"large":"https:\/\/natus.com\/wp-content\/uploads\/Efficiency-AI_Insights-500x400-1.png","large-width":500,"large-height":400,"1536x1536":"https:\/\/natus.com\/wp-content\/uploads\/Efficiency-AI_Insights-500x400-1.png","1536x1536-width":500,"1536x1536-height":400,"2048x2048":"https:\/\/natus.com\/wp-content\/uploads\/Efficiency-AI_Insights-500x400-1.png","2048x2048-width":500,"2048x2048-height":400}}},"_links":{"self":[{"href":"https:\/\/natus.com\/fr\/wp-json\/natus\/insights\/24780","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/natus.com\/fr\/wp-json\/natus\/insights"}],"about":[{"href":"https:\/\/natus.com\/fr\/wp-json\/wp\/v2\/types\/insights"}],"author":[{"embeddable":true,"href":"https:\/\/natus.com\/fr\/wp-json\/wp\/v2\/users\/2"}],"version-history":[{"count":5,"href":"https:\/\/natus.com\/fr\/wp-json\/natus\/insights\/24780\/revisions"}],"predecessor-version":[{"id":26074,"href":"https:\/\/natus.com\/fr\/wp-json\/natus\/insights\/24780\/revisions\/26074"}],"wp:attachment":[{"href":"https:\/\/natus.com\/fr\/wp-json\/wp\/v2\/media?parent=24780"}],"wp:term":[{"taxonomy":"insight_type","embeddable":true,"href":"https:\/\/natus.com\/fr\/wp-json\/natus\/insight_type?post=24780"},{"taxonomy":"insights_category","embeddable":true,"href":"https:\/\/natus.com\/fr\/wp-json\/natus\/insights_category?post=24780"},{"taxonomy":"insights_tag","embeddable":true,"href":"https:\/\/natus.com\/fr\/wp-json\/wp\/v2\/insights_tag?post=24780"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}