{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,26]],"date-time":"2026-08-26T23:27:43Z","timestamp":1787786863283,"version":"build-2784847793"},"reference-count":21,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,1,12]],"date-time":"2026-01-12T00:00:00Z","timestamp":1768176000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Neurosci."],"abstract":"<jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>The WHO Surgical Safety Checklist reduces preventable errors, but real operating rooms are characterized by overlapping speech, high ambient noise, similar vocalizations, uncertain speaker identity, and occasional omission of checklist items. ASR-only systems that ignore identity constraints and semantic\u2013temporal structure are therefore prone to misrecognition and incorrect verification.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Method<\/jats:title>\n                    <jats:p>We design an integrated verification framework that couples automatic speech recognition and speaker verification (ASR\u202f+\u202fSV) with a knowledge-driven rule engine derived from the WHO checklist. Multichannel audio is processed by a Conformer-based ASR module and an ECAPA-TDNN speaker verification model, after which a rule layer enforces consistency across the semantic content, speaker role, and checklist phase using an explicit ontology and conflict-resolution rules. The system generates real-time prompts in four states (\u201cpass,\u201d \u201cfault,\u201d \u201calarm,\u201d \u201cuncertain\u201d). Performance is evaluated primarily in high-fidelity simulated operating-room scenarios with controlled noise levels, speaking distances, and multi-speaker interactions, using word error rate (WER), equal error rate (EER), checklist verification accuracy, and alarm rate. Three configurations are compared on the same held-out sessions\u2014\u201cASR-only,\u201d \u201cASR\u202f+\u202fSV,\u201d and the full knowledge-driven method\u2014and ablation experiments isolate the contribution of the rule layer.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>Under medium-to-high noise and multi-speaker interference, the full framework reduced WER from 18.7% to approximately 13.5% and achieved an EER of about 3.1% relative to the ASR-only baseline. Checklist verification accuracy reached 93.8%, while the alarm rate decreased to roughly 2.7%. The knowledge layer corrected errors arising from homophones, accent drift, and role confusion by constraining \u201crole\u2013semantics\u2013process\u201d relations, and maintained robust performance at speaking distances up to 1.5\u202fm and background noise of 60\u202fdB. Residual failures were mainly associated with extreme speech overlap and unseen vocabulary, suggesting that lexicon adaptation and speech separation will be necessary for further gains.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>The proposed knowledge-driven ASR\u202f+\u202fSV framework jointly addresses semantic correctness and speaker identity while remaining interpretable, auditable, and suitable for embedded deployment. It provides a technical foundation for \u201ctime-out\u201d and \u201coperation review\u201d functions in intelligent operating rooms. Because the present validation is based largely on simulated scenarios with limited real-world testing and no formal user or ethical evaluation, future work will focus on clinical pilot studies, integration with electronic medical records and multimodal OR data, and a deeper analysis of privacy, accountability, and workflow acceptance.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fnins.2025.1726720","type":"journal-article","created":{"date-parts":[[2026,1,12]],"date-time":"2026-01-12T08:12:49Z","timestamp":1768205569000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["A knowledge-driven framework for surgical safety check integration using speech recognition and speaker verification"],"prefix":"10.3389","volume":"19","author":[{"given":"Wen","family":"Shi","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rui","family":"Fan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jian","family":"Hu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jingrong","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mei","family":"Bian","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wei","family":"Jiang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,1,12]]},"reference":[{"key":"ref1","doi-asserted-by":"publisher","first-page":"108281","DOI":"10.1016\/j.bspc.2025.108281","article-title":"A knowledge-driven evidence fusion network for pancreatic tumor segmentation in CT images","volume":"111","author":"Dong","year":"2026","journal-title":"Biomed. Signal Process. Control"},{"key":"ref2","author":"Feng","year":"2022"},{"key":"ref3","doi-asserted-by":"publisher","first-page":"209","DOI":"10.1136\/bmjqs-2023-016617","article-title":"Lost in translation: does measuring \u2018adherence\u2019to the surgical safety checklist indicate true implementation fidelity?","volume":"33","author":"Gillespie","year":"2024","journal-title":"BMJ Qual. Saf."},{"key":"ref4","first-page":"41","article-title":"Artificial intelligence in healthcare industry: a transformation from model-driven to knowledge-driven DSS","volume":"2","author":"H\u0131z\u0131ro\u011flu","year":"2022","journal-title":"Artif. Intell. Theory Appl."},{"key":"ref5","doi-asserted-by":"publisher","first-page":"771","DOI":"10.1007\/s10845-021-01826-8","article-title":"Knowledge-driven framework for industrial robotic systems","volume":"34","author":"Hoebert","year":"2023","journal-title":"J. Intell. Manuf."},{"key":"ref6","doi-asserted-by":"publisher","first-page":"454","DOI":"10.1109\/TCCN.2021.3128597","article-title":"Knowledge-driven machine learning and applications in wireless communications","volume":"8","author":"Li","year":"2021","journal-title":"IEEE Trans. Cogn. Commun. Netw."},{"key":"ref7","doi-asserted-by":"publisher","first-page":"106267","DOI":"10.1016\/j.neunet.2024.106267","article-title":"Cosine convolutional neural network and its application for seizure detection","volume":"174","author":"Liu","year":"2024","journal-title":"Neural Netw."},{"key":"ref8","doi-asserted-by":"publisher","first-page":"20002","DOI":"10.1109\/JIOT.2024.3368029","article-title":"TCM-KDIF: an information interaction framework driven by knowledge\u2013data and its clinical application in traditional Chinese medicine","volume":"11","author":"Liu","year":"2024","journal-title":"IEEE Internet Things J."},{"key":"ref9","doi-asserted-by":"publisher","first-page":"4121","DOI":"10.1109\/JBHI.2025.3536212","article-title":"Fine-grained spatial-frequency-time framework for motor imagery brain-computer Interface","volume":"29","author":"Liu","year":"2025","journal-title":"IEEE J. Biomed. Health Inform."},{"key":"ref10","doi-asserted-by":"publisher","first-page":"28","DOI":"10.1038\/s41539-025-00316-3","article-title":"Understanding the role of eye movement pattern and consistency during face recognition through EEG decoding","volume":"10","author":"Liu","year":"2025","journal-title":"NPJ Sci. Learn."},{"key":"ref11","doi-asserted-by":"publisher","first-page":"1950024","DOI":"10.1142\/S0129065719500242","article-title":"Automatic seizure detection based on S-transform and deep convolutional neural network","volume":"30","author":"Liu","year":"2020","journal-title":"Int. J. Neural Syst."},{"key":"ref12","doi-asserted-by":"publisher","first-page":"09494","DOI":"10.48550\/arXiv.2201.09494","article-title":"Data and knowledge-driven approaches for multilingual training to improve the performance of speech recognition systems of Indian languages","volume":"2022","author":"Madhavaraj","year":"2022","journal-title":"arXiv"},{"key":"ref13","doi-asserted-by":"crossref","first-page":"2","DOI":"10.3233\/SHTI250207","article-title":"VoiceCheck: an intelligent assistant for enhancing surgical safety through guided checklist use","volume-title":"Healthcare of the future 2025","author":"Medroa Inacio","year":"2025"},{"key":"ref14","doi-asserted-by":"publisher","first-page":"20014","DOI":"10.48550\/arXiv.2508.20014","article-title":"CataractSurg-80K: knowledge-driven benchmarking for structured reasoning in ophthalmic surgery planning","volume":"2025","author":"Meng","year":"2025","journal-title":"arXiv"},{"key":"ref15","author":"M\u00fcller","year":"2010"},{"key":"ref16","doi-asserted-by":"publisher","first-page":"1740007","DOI":"10.1142\/S2424905X17400074","article-title":"Toward a knowledge-driven context-aware system for surgical assistance","volume":"2","author":"Nakawala","year":"2017","journal-title":"J. Med. Robot. Res."},{"key":"ref17","doi-asserted-by":"publisher","first-page":"3403","DOI":"10.3390\/buildings14113403","article-title":"Systematic literature review on knowledge-driven approaches for construction safety analysis and accident prevention","volume":"14","author":"Pandithawatta","year":"2024","journal-title":"Buildings"},{"key":"ref18","doi-asserted-by":"publisher","first-page":"12049","DOI":"10.48550\/arXiv.2107.12049","article-title":"SVEva fair: a framework for evaluating fairness in speaker verification","volume":"2021","author":"Toussaint","year":"2021","journal-title":"arXiv"},{"key":"ref19","doi-asserted-by":"publisher","first-page":"e2317183","DOI":"10.1001\/jamanetworkopen.2023.17183","article-title":"International perspectives on modifications to the surgical safety checklist","volume":"6","author":"Turley","year":"2023","journal-title":"JAMA Netw. Open"},{"key":"ref20","doi-asserted-by":"publisher","first-page":"2218","DOI":"10.1109\/TMI.2025.3529294","article-title":"Knowledge-driven framework for anatomical landmark annotation in laparoscopic surgery","volume":"44","author":"Zhang","year":"2025","journal-title":"IEEE Trans. Med. Imaging"},{"key":"ref21","author":"Zhou","year":"2022"}],"container-title":["Frontiers in Neuroscience"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fnins.2025.1726720\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,12]],"date-time":"2026-01-12T08:12:50Z","timestamp":1768205570000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fnins.2025.1726720\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1,12]]},"references-count":21,"alternative-id":["10.3389\/fnins.2025.1726720"],"URL":"https:\/\/doi.org\/10.3389\/fnins.2025.1726720","relation":{},"ISSN":["1662-453X"],"issn-type":[{"value":"1662-453X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1,12]]},"article-number":"1726720"}}