{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,21]],"date-time":"2026-09-21T08:04:00Z","timestamp":1789977840773,"version":"4.0.1"},"reference-count":61,"publisher":"SAGE Publications","license":[{"start":{"date-parts":[[2026,9,18]],"date-time":"2026-09-18T00:00:00Z","timestamp":1789689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/journals.sagepub.com\/page\/policies\/text-and-data-mining-license"}],"funder":[{"name":"Johns Hopkins All Children\u2019s Foundation IRG Pilot Research Grant"}],"content-domain":{"domain":["journals.sagepub.com"],"crossmark-restriction":true},"short-container-title":["The Cleft Palate Craniofacial Journal"],"abstract":"<jats:sec>\n                    <jats:title>Objective<\/jats:title>\n                    <jats:p>Perceptual evaluation by speech-language pathologists (SLPs) is essential for initial evaluation of velopharyngeal dysfunction (VPD). Machine learning (ML) offers a promising avenue for developing accessible speech assessment tools when SLP expertise is limited. We aimed to develop a workflow and preliminary algorithm for AI-based hypernasality detection based on the Cleft Audit Protocol for Speech-Augmented-Americleft Modification (CAPS-A-AM), a standardized framework for auditory perceptual speech assessment.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Design<\/jats:title>\n                    <jats:p>In this prospective, single-center study, speech samples were collected during SLP-guided evaluation, with consensus CAPS-A-AM ratings established. Mel spectrograms for high vowels (\/i\/ and \/u\/) were generated from sustained vowels, isolated words, and sentences for model development. Three ML approaches were evaluated: logistic regression (LR), Convolutional Neural Network (CNN) Attention-Multiple Instance Learning (MIL) (EfficientNet-V2-S), and a CNN\u2013Extreme Gradient Boosting Hybrid (XGBoost).<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Patients\/Participants<\/jats:title>\n                    <jats:p>Forty pediatric participants aged 2 to 17, including individuals with VPD, conditions associated with VPD, and healthy participants.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Main Outcome Measure(s)<\/jats:title>\n                    <jats:p>Model performance was tested in binary hypernasality classification compared to SLP consensus at two CAPS-A-AM thresholds: absent (0) versus any hypernasality (1\u20134) and absent\/borderline (0-1) versus mild-to-severe hypernasality (2-4).<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>Multiple independent modeling approaches were able to detect clinically rated hypernasality. EfficientNet-V2-S achieved the highest observed performance estimates in this cohort (F1 score\u2009=\u20090.786-0.900). However, overlapping confidence intervals precluded demonstration of model superiority.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>ML-based hypernasality classification using mel spectrograms demonstrated promising feasibility. Future work will expand sample acquisition and refine model development with increasingly diverse speech inputs for training and sample rating.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1177\/10556656261487525","type":"journal-article","created":{"date-parts":[[2026,9,18]],"date-time":"2026-09-18T13:33:34Z","timestamp":1789738414000},"update-policy":"https:\/\/doi.org\/10.1177\/sage-journals-update-policy","source":"Crossref","is-referenced-by-count":0,"title":["Artificial Intelligence-Based Hypernasality Diagnosis Using CAPS-A-AM Rated Speech Samples in Pediatric Velopharyngeal Dysfunction"],"prefix":"10.1177","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5513-5162","authenticated-orcid":false,"given":"Jordan N.","family":"Halsey","sequence":"first","affiliation":[{"name":"Johns Hopkins All Children's Hospital"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-5958-6193","authenticated-orcid":false,"given":"Mbinui N.","family":"Ghogomu","sequence":"additional","affiliation":[{"name":"Johns Hopkins All Children's Hospital"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3632-4205","authenticated-orcid":false,"given":"Molly F.","family":"MacIsaac","sequence":"additional","affiliation":[{"name":"Johns Hopkins All Children's Hospital"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-6911-9849","authenticated-orcid":false,"given":"Jamilla","family":"Vieux","sequence":"additional","affiliation":[{"name":"Johns Hopkins All Children's Hospital"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5552-6312","authenticated-orcid":false,"given":"Chelsea L.","family":"Sommer","sequence":"additional","affiliation":[{"name":"Florida International University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2225-3247","authenticated-orcid":false,"given":"Joshua M.","family":"Wright","sequence":"additional","affiliation":[{"name":"Johns Hopkins All Children's Hospital"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7164-4685","authenticated-orcid":false,"given":"Ruth H.","family":"Bahr","sequence":"additional","affiliation":[{"name":"University of South Florida"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6856-6698","authenticated-orcid":false,"given":"Luis M.","family":"Ahumada","sequence":"additional","affiliation":[{"name":"Center for Pediatric Data Science and Analytics Methodology, Johns Hopkins All Children's Hospital, St. Petersburg, FL, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7209-1966","authenticated-orcid":false,"given":"S.","family":"Alex Rottgers","sequence":"additional","affiliation":[{"name":"Johns Hopkins All Children's Hospital"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"179","published-online":{"date-parts":[[2026,9,18]]},"reference":[{"key":"e_1_3_2_2_2","doi-asserted-by":"publisher","DOI":"10.1055\/s-0031-1277717"},{"key":"e_1_3_2_3_2","doi-asserted-by":"publisher","DOI":"10.1097\/SCS.0b013e31803ecf3b"},{"key":"e_1_3_2_4_2","doi-asserted-by":"publisher","DOI":"10.1097\/SCS.0000000000009555"},{"key":"e_1_3_2_5_2","doi-asserted-by":"publisher","DOI":"10.1097\/PRS.0000000000005210"},{"key":"e_1_3_2_6_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.bjps.2024.01.034"},{"key":"e_1_3_2_7_2","doi-asserted-by":"publisher","DOI":"10.1177\/1055665618799906"},{"key":"e_1_3_2_8_2","doi-asserted-by":"publisher","DOI":"10.1177\/10556656211026861"},{"key":"e_1_3_2_9_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.oooo.2013.12.409"},{"key":"e_1_3_2_10_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijporl.2014.12.036"},{"key":"e_1_3_2_11_2","doi-asserted-by":"publisher","DOI":"10.1044\/2019_PERS-SIG5-2019-0003"},{"key":"e_1_3_2_12_2","doi-asserted-by":"publisher","DOI":"10.1597\/06-086.1"},{"key":"e_1_3_2_13_2","doi-asserted-by":"publisher","DOI":"10.1597\/14-027"},{"key":"e_1_3_2_14_2","doi-asserted-by":"publisher","DOI":"10.1597\/04-141.1"},{"key":"e_1_3_2_15_2","doi-asserted-by":"publisher","DOI":"10.1097\/SCS.0000000000010606"},{"key":"e_1_3_2_16_2","doi-asserted-by":"publisher","DOI":"10.1044\/2023_LSHSS-23-00071"},{"key":"e_1_3_2_17_2","doi-asserted-by":"publisher","DOI":"10.1177\/10556656231189940"},{"key":"e_1_3_2_18_2","doi-asserted-by":"publisher","DOI":"10.1097\/PRS.0000000000011410"},{"key":"e_1_3_2_19_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.joms.2021.02.043"},{"key":"e_1_3_2_20_2","doi-asserted-by":"publisher","DOI":"10.1097\/SCS.0000000000007988"},{"key":"e_1_3_2_21_2","doi-asserted-by":"publisher","DOI":"10.1177\/10556656261445320"},{"key":"e_1_3_2_22_2","doi-asserted-by":"publisher","DOI":"10.1097\/SCS.0000000000010147"},{"key":"e_1_3_2_23_2","doi-asserted-by":"publisher","DOI":"10.1097\/SAP.0000000000004460"},{"key":"e_1_3_2_24_2","doi-asserted-by":"publisher","DOI":"10.3389\/fdgth.2025.1552746"},{"key":"e_1_3_2_25_2","doi-asserted-by":"publisher","DOI":"10.3390\/diagnostics13162714"},{"key":"e_1_3_2_26_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.jcms.2018.09.014"},{"key":"e_1_3_2_27_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijmedinf.2019.05.023"},{"key":"e_1_3_2_28_2","doi-asserted-by":"publisher","DOI":"10.1007\/s00034-019-01141-x"},{"key":"e_1_3_2_29_2","doi-asserted-by":"publisher","DOI":"10.1109\/TBME.2021.3058424"},{"key":"e_1_3_2_30_2","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2018-1631"},{"key":"e_1_3_2_31_2","unstructured":"Song K Wan T Wang B Huiqiang J. Improving hypernasality estimation with automatic speech recognition in cleft palate speech. arXiv. Preprint posted online August 2022. June 10 2026. https:\/\/arxiv.org\/abs\/2208.05122"},{"key":"e_1_3_2_32_2","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2151"},{"key":"e_1_3_2_33_2","doi-asserted-by":"publisher","DOI":"10.1121\/1.5134433"},{"key":"e_1_3_2_34_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2024.106689"},{"key":"e_1_3_2_35_2","first-page":"1","volume-title":"Cross-lingual evaluation of hypernasality using Wav2Vec2 featuresProceedings of the ICASSP 2025: IEEE International Conference on Acoustics, Speech and Signal Processing; April 6-11, 2025","author":"Kothadia K","year":"2025","unstructured":"Kothadia K, Vikram CM, Abraham A, Mariswamy P, Prasanna SR, Scherer N, Chapman K, Liss J, Berisha V. Cross-lingual evaluation of hypernasality using Wav2Vec2 features. In: Proceedings of the ICASSP 2025: IEEE International Conference on Acoustics, Speech and Signal Processing; April 6-11, 2025. Hyderabad, India: IEEE; 2025, 1-5."},{"key":"e_1_3_2_36_2","first-page":"6754","volume-title":"Single frequency filter bank-based long-term average spectra for hypernasality detection and assessment in cleft lip and palate speechICASSP 2020: IEEE International Conference on Acoustics, Speech and Signal Processing; May 4-8, 2020","author":"Javid MH","year":"2020","unstructured":"Javid MH, Gurugubelli K, Vuppala AK. Single frequency filter bank-based long-term average spectra for hypernasality detection and assessment in cleft lip and palate speech. In: ICASSP 2020: IEEE International Conference on Acoustics, Speech and Signal Processing; May 4-8, 2020. Barcelona, Spain: IEEE, 2020, 6754-6758."},{"key":"e_1_3_2_37_2","doi-asserted-by":"publisher","DOI":"10.3390\/app11198809"},{"key":"e_1_3_2_38_2","doi-asserted-by":"publisher","DOI":"10.1109\/TBME.2006.889191"},{"key":"e_1_3_2_39_2","doi-asserted-by":"publisher","DOI":"10.1044\/1092-4388(2009\/08-0161)"},{"key":"e_1_3_2_40_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2020.08.001"},{"key":"e_1_3_2_41_2","doi-asserted-by":"publisher","DOI":"10.4103\/2228-7477.128302"},{"key":"e_1_3_2_42_2","doi-asserted-by":"publisher","DOI":"10.14569\/IJACSA.2016.070928"},{"key":"e_1_3_2_43_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-21326-7_19"},{"key":"e_1_3_2_44_2","doi-asserted-by":"publisher","DOI":"10.1109\/IEMBS.2006.260572"},{"key":"e_1_3_2_45_2","doi-asserted-by":"publisher","DOI":"10.17533\/udea.redin.n80a12"},{"key":"e_1_3_2_46_2","doi-asserted-by":"publisher","DOI":"10.1121\/1.4976056"},{"key":"e_1_3_2_47_2","doi-asserted-by":"publisher","DOI":"10.1109\/10.477699"},{"key":"e_1_3_2_48_2","doi-asserted-by":"publisher","DOI":"10.1114\/1.1380422"},{"key":"e_1_3_2_49_2","first-page":"277","volume-title":"Hypernasality in speech of children with cleft lip and palate: Automatic evaluationProceedings of the 8th International Seminar on Speech Production","author":"Maier A","year":"2008","unstructured":"Maier A, Schuster M, Haderlein T, N\u00f6th E. Hypernasality in speech of children with cleft lip and palate: Automatic evaluation. In: Sock R, Fuchs S, Laprie Y (eds) Proceedings of the 8th International Seminar on Speech Production. Strasbourg, France: Institut de Phon\u00e9tique de Strasbourg, 2008, 277-280."},{"key":"e_1_3_2_50_2","doi-asserted-by":"publisher","DOI":"10.1007\/s10916-015-0242-2"},{"key":"e_1_3_2_51_2","doi-asserted-by":"publisher","DOI":"10.1121\/1.5039718"},{"key":"e_1_3_2_52_2","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1251"},{"key":"e_1_3_2_53_2","doi-asserted-by":"publisher","DOI":"10.7275\/cnem-ab98"},{"key":"e_1_3_2_54_2","doi-asserted-by":"publisher","DOI":"10.1177\/10556656241271646"},{"key":"e_1_3_2_55_2","volume-title":"Goldman-Fristoe test of articulation \u2013 third edition (GFTA-3)","author":"Goldman R","year":"2015","unstructured":"Goldman R, Fristoe M. Goldman-Fristoe test of articulation \u2013 third edition (GFTA-3). 3rd ed. Bloomington, MN: Pearson; 2015.","edition":"3"},{"key":"e_1_3_2_56_2","doi-asserted-by":"publisher","DOI":"10.2307\/2529310"},{"key":"e_1_3_2_57_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.jvoice.2024.08.029"},{"key":"e_1_3_2_58_2","doi-asserted-by":"publisher","DOI":"10.1044\/2024_JSLHR-23-00759"},{"key":"e_1_3_2_59_2","doi-asserted-by":"publisher","DOI":"10.1080\/2000656X.2016.1254645"},{"key":"e_1_3_2_60_2","doi-asserted-by":"publisher","DOI":"10.1080\/13682820801890400"},{"key":"e_1_3_2_61_2","doi-asserted-by":"publisher","DOI":"10.1121\/1.5008854"},{"key":"e_1_3_2_62_2","doi-asserted-by":"publisher","DOI":"10.1044\/2014_JSLHR-S-14-0077"}],"container-title":["The Cleft Palate Craniofacial Journal"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.1177\/10556656261487525","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/full-xml\/10.1177\/10556656261487525","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.1177\/10556656261487525","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,21]],"date-time":"2026-09-21T07:19:09Z","timestamp":1789975149000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.sagepub.com\/doi\/10.1177\/10556656261487525"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,18]]},"references-count":61,"alternative-id":["10.1177\/10556656261487525"],"URL":"https:\/\/doi.org\/10.1177\/10556656261487525","relation":{},"ISSN":["1055-6656","1545-1569"],"issn-type":[{"value":"1055-6656","type":"print"},{"value":"1545-1569","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,18]]},"article-number":"10556656261487525"}}