{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,10]],"date-time":"2026-11-10T12:22:47Z","timestamp":1794313367824,"version":"4.9.0"},"reference-count":25,"publisher":"SAGE Publications","issue":"6","license":[{"start":{"date-parts":[[2025,11,7]],"date-time":"2025-11-07T00:00:00Z","timestamp":1762473600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/journals.sagepub.com\/page\/policies\/text-and-data-mining-license"}],"content-domain":{"domain":["journals.sagepub.com"],"crossmark-restriction":true},"short-container-title":["Facial Plastic Surgery &amp; Aesthetic Medicine"],"published-print":{"date-parts":[[2026,11,1]]},"abstract":"<jats:sec>\n                    <jats:title>Background:<\/jats:title>\n                    <jats:p>Accurate assessment of facial paralysis is crucial for patient management and research, yet current clinician-graded scales are limited by subjectivity and variability.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Objective:<\/jats:title>\n                    <jats:p>To evaluate whether an automated video analysis pipeline using hemifacial mirroring and Facial Action Unit (AU) quantification could accurately classify facial paralysis severity (None, Incomplete, and Complete) when validated against expert clinical grading.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods:<\/jats:title>\n                    <jats:p>A custom Python pipeline processed 112 clinical videos (100 paralysis patients, 12 controls), generating mirrored hemifacial constructs. OpenFace 2.0 extracted AU intensities from these constructs, linked to voice-command-defined action epochs. Peak expression features trained XGBoost machine learning models to predict paralysis severity (None, Incomplete, and Complete) per facial zone (upper, mid, and lower), validated against multi-expert clinical assessment.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results:<\/jats:title>\n                    <jats:p>On held-out test sets, models achieved: upper face accuracy 0.83, weighted F1-score 0.83; mid-face accuracy 0.93, weighted F1-score 0.92; and lower face accuracy 0.84, weighted F1-score 0.82. Mirrored AU intensities significantly differed across expert-defined severity groups, validating feature relevance.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion:<\/jats:title>\n                    <jats:p>The automated pipeline using hemifacial mirroring and mirrored AU analysis accurately predicted facial paralysis severity from standard clinical videos.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1177\/26893614251394382","type":"journal-article","created":{"date-parts":[[2025,11,13]],"date-time":"2025-11-13T06:05:16Z","timestamp":1763013916000},"page":"607-613","update-policy":"https:\/\/doi.org\/10.1177\/sage-journals-update-policy","source":"Crossref","is-referenced-by-count":0,"title":["A Split-Face Computer Vision\/Machine Learning Assessment of Facial Paralysis Using Facial Action Units"],"prefix":"10.1177","volume":"28","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8553-9253","authenticated-orcid":false,"suffix":"IV","given":"John","family":"Wilson","sequence":"first","affiliation":[{"name":"Department of Otolaryngology\u2014Head and Neck Surgery, Icahn School of Medicine at Mount Sinai, New York, New York, USA."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Joshua","family":"Rosenberg","sequence":"additional","affiliation":[{"name":"Department of Otolaryngology\u2014Head and Neck Surgery, Icahn School of Medicine at Mount Sinai, New York, New York, USA."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mingyang L.","family":"Gray","sequence":"additional","affiliation":[{"name":"Department of Otolaryngology\u2014Head and Neck Surgery, Icahn School of Medicine at Mount Sinai, New York, New York, USA."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Christopher R.","family":"Razavi","sequence":"additional","affiliation":[{"name":"Department of Otolaryngology\u2014Head and Neck Surgery, Icahn School of Medicine at Mount Sinai, New York, New York, USA."}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"179","published-online":{"date-parts":[[2025,11,7]]},"reference":[{"key":"e_1_3_3_2_2","doi-asserted-by":"publisher","DOI":"10.1002\/lary.24542"},{"key":"e_1_3_3_3_2","doi-asserted-by":"publisher","DOI":"10.1097\/01.mlg.0000225980.38147.c6"},{"key":"e_1_3_3_4_2","doi-asserted-by":"publisher","DOI":"10.1097\/PRS.0000000000000905"},{"issue":"5","key":"e_1_3_3_5_2","first-page":"369","article-title":"The need for standardized assessment tools for acute flaccid paralysis of the face","volume":"21","author":"Nell\u012bs S","year":"2019","unstructured":"Nell\u012bs S, , Brennan P, , Ishii L, et al. The need for standardized assessment tools for acute flaccid paralysis of the face. JAMA Facial Plast Surg., 2019; 21(5):369\u2013370.","journal-title":"JAMA Facial Plast Surg."},{"key":"e_1_3_3_6_2","doi-asserted-by":"publisher","DOI":"10.1177\/019459988509300202"},{"key":"e_1_3_3_7_2","doi-asserted-by":"publisher","DOI":"10.1097\/PRS.0000000000001447"},{"key":"e_1_3_3_8_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.otohns.2006.05.748"},{"key":"e_1_3_3_9_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.otohns.2008.11.021"},{"key":"e_1_3_3_10_2","doi-asserted-by":"publisher","DOI":"10.1001\/jamafacial.2016.1620"},{"issue":"2","key":"e_1_3_3_11_2","first-page":"97","article-title":"Computerized quantitative dynamic analysis of facial motion in the paralyzed and recovering face","volume":"13","author":"Neely JG","year":"1992","unstructured":"Neely JG, , Cheung JY, , Wood M, et al. Computerized quantitative dynamic analysis of facial motion in the paralyzed and recovering face. Am J Otol., 1992; 13(2):97\u2013107.","journal-title":"Am J Otol."},{"key":"e_1_3_3_12_2","doi-asserted-by":"publisher","DOI":"10.1097\/00006534-199406000-00002"},{"key":"e_1_3_3_13_2","doi-asserted-by":"publisher","DOI":"10.1097\/00006534-199912000-00013"},{"key":"e_1_3_3_14_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.bjps.2007.03.037"},{"key":"e_1_3_3_15_2","doi-asserted-by":"publisher","DOI":"10.1001\/archfaci.2012.111"},{"key":"e_1_3_3_16_2","doi-asserted-by":"publisher","DOI":"10.1001\/jamafacial.2018.0030"},{"issue":"7","key":"e_1_3_3_17_2","first-page":"1298","article-title":"Reliability and validity of emotrics in the assessment of facial palsy","volume":"59","author":"Kim J","year":"2023","unstructured":"Kim J, , Jang SY, , Kim J, et al. Reliability and validity of emotrics in the assessment of facial palsy. Medicina (Kaunas). 2023; 59(7):1298.","journal-title":"Medicina (Kaunas)"},{"issue":"21","key":"e_1_3_3_18_2","first-page":"8760","article-title":"Automatic facial palsy detection\u2014from mathematical modeling to deep learning","volume":"23","author":"Psyllos A","year":"2023","unstructured":"Psyllos A, , Antoniou I, , Tsakanikas V, et al. Automatic facial palsy detection\u2014from mathematical modeling to deep learning. Sensors (Basel)., 2023; 23(21):8760.","journal-title":"Sensors (Basel)."},{"key":"e_1_3_3_19_2","doi-asserted-by":"publisher","DOI":"10.1097\/PRS.0000000000007572"},{"key":"e_1_3_3_20_2","doi-asserted-by":"crossref","unstructured":"Baltrusaitis T Zadeh A Lim YC et al. OpenFace 2.0: facial behavior analysis toolkit. Paper presented at: 2018 IEEE 13th International Conference on Automatic Face & Gesture Recognition (FG 2018); 2018:59\u201366.","DOI":"10.1109\/FG.2018.00019"},{"key":"e_1_3_3_21_2","volume-title":"Facial Action Coding System: A Technique for the Measurement of Facial Movement","author":"Ekman P","year":"1978","unstructured":"Ekman P, , Friesen WV. Facial Action Coding System: A Technique for the Measurement of Facial Movement. Consulting Psychologists Press; 1978."},{"key":"e_1_3_3_22_2","doi-asserted-by":"publisher","DOI":"10.1109\/T-AFFC.2013.4"},{"key":"e_1_3_3_23_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2014.06.002"},{"key":"e_1_3_3_24_2","doi-asserted-by":"publisher","DOI":"10.3390\/s23229076"},{"key":"e_1_3_3_25_2","doi-asserted-by":"publisher","DOI":"10.1089\/fpsam.2024.0381"},{"key":"e_1_3_3_26_2","doi-asserted-by":"crossref","unstructured":"Kreiensieck E Ai Y Zhang L. A comprehensive evaluation of openface 2.0 gaze tracking. In: Kurosu M Hashizume A eds. Human-Computer Interaction. HCII 2023. Lecture Notes in Computer Science 14011. Springer; 2023:531\u2013547.","DOI":"10.1007\/978-3-031-35596-7_34"}],"container-title":["Facial Plastic Surgery &amp; Aesthetic Medicine"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.1177\/26893614251394382","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/full-xml\/10.1177\/26893614251394382","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.1177\/26893614251394382","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,11,10]],"date-time":"2026-11-10T11:30:45Z","timestamp":1794310245000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.sagepub.com\/doi\/10.1177\/26893614251394382"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,7]]},"references-count":25,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2026,11,1]]}},"alternative-id":["10.1177\/26893614251394382"],"URL":"https:\/\/doi.org\/10.1177\/26893614251394382","relation":{},"ISSN":["2689-3614","2689-3622"],"issn-type":[{"value":"2689-3614","type":"print"},{"value":"2689-3622","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11,7]]}}}