{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T06:14:14Z","timestamp":1784268854318,"version":"3.55.0"},"reference-count":31,"publisher":"Ovid Technologies (Wolters Kluwer Health)","issue":"1S","content-domain":{"domain":["lww.com","ovid.com"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,7]]},"abstract":"<jats:sec>\n                    <jats:title>Background:<\/jats:title>\n                    <jats:p>The diagnosis and management of velopharyngeal dysfunction (VPD) is a particularly challenging part of the cleft care timeline, particularly in resource-limited settings. Although machine learning (ML) models offer promising results as screening tools, their real-world clinical viability has yet to be reliably demonstrated. This study aims to systematically compare the capability of several ML models to detect VPD in nonstandardized conditions to simulate real-world clinical testing.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods:<\/jats:title>\n                    <jats:p>Eighty-two patients were enrolled under standardized acoustic conditions and partitioned into an in-domain 60-subject training set and a 22-subject test set. For the out-of-domain test set, audio samples were obtained from publicly available Internet sources. A total of 131 case samples (70 control, 61 case) were obtained from multiple publicly available sources. Recording scenarios were highly variable, nonstandardized and largely not described, thereby introducing extreme heterogeneity.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results:<\/jats:title>\n                    <jats:p>On the hold-out testing dataset, multiple deep learning models, particularly those using Whisper and HuBERT features, achieved near-perfect performance, with the Whisper\/Support Vector Machine (SVM) pipeline reaching 100% accuracy and a 1.0 macro F1-score. The traditional MFCC baseline model also performed exceptionally well, achieving 99.2% accuracy and a 0.95 macro F1-score. Cross-domain generalization testing on the out-of-domain dataset demonstrated severe performance degradation. State-of-the-art deep learning models failed to generalize. The simpler baseline MFCC\/SVM pipeline proved to be the most robust in real-world simulation, achieving an accuracy of 64.1% and a macro F1-score of 0.61.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion:<\/jats:title>\n                    <jats:p>The results of this study demonstrate that pretrained ML models can achieve near-perfect VPD detection in highly standardized acoustic environments. However, models are highly susceptible to domain shift caused by variations in recording devices and acoustic environments. Out-of-domain testing results were mediocre but suggest that real-world clinical detection of VPD by ML models is feasible. These results shed light on the difficulties of real-world model generalization and emphasize that for clinically deployable diagnostic tools, cross-domain robustness is as important as, if not more important than, achieving maximal accuracy on a benchmark dataset. The development of a software-based screening tool has the power to improve VPD screening, particularly in low- and middle-income countries.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1097\/sap.0000000000004633","type":"journal-article","created":{"date-parts":[[2026,1,9]],"date-time":"2026-01-09T22:00:20Z","timestamp":1767996020000},"page":"S76-S80","update-policy":"https:\/\/doi.org\/10.1097\/lww.0000000000001000","source":"Crossref","is-referenced-by-count":1,"title":["Out of the Laboratory and Into the Clinic"],"prefix":"10.1097","volume":"97","author":[{"given":"Weixin","family":"Liu","sequence":"first","affiliation":[{"name":"Electrical Computer Engineering"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bowen","family":"Qu","sequence":"additional","affiliation":[{"name":"Computer Science, Vanderbilt University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Amy","family":"Stone","sequence":"additional","affiliation":[{"name":"Department of Otolaryngology\u2014Head and Neck Surgery, Vanderbilt University Medical Center"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Maria","family":"Powell","sequence":"additional","affiliation":[{"name":"Department of Otolaryngology\u2014Head and Neck Surgery, Vanderbilt University Medical Center"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shama","family":"Dufresne","sequence":"additional","affiliation":[{"name":"School of Medicine, Vanderbilt University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Stephane","family":"Braun","sequence":"additional","affiliation":[{"name":"Department of Plastic Surgery, Vanderbilt University Medical Center"},{"name":"Division of Pediatric Plastic Surgery, Monroe Carell Jr. Children's Hospital"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Izabela","family":"Galdyn","sequence":"additional","affiliation":[{"name":"Department of Plastic Surgery, Vanderbilt University Medical Center"},{"name":"Division of Pediatric Plastic Surgery, Monroe Carell Jr. Children's Hospital"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Michael","family":"Golinko","sequence":"additional","affiliation":[{"name":"Department of Plastic Surgery, Vanderbilt University Medical Center"},{"name":"Division of Pediatric Plastic Surgery, Monroe Carell Jr. Children's Hospital"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhijun","family":"Yin","sequence":"additional","affiliation":[{"name":"Electrical Computer Engineering"},{"name":"Computer Science, Vanderbilt University"},{"name":"Department of Biomedical Informatics, Vanderbilt University Medical Center, Nashville, TN"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2329-9899","authenticated-orcid":false,"given":"Matthew E.","family":"Pontell","sequence":"additional","affiliation":[{"name":"Department of Otolaryngology\u2014Head and Neck Surgery, Vanderbilt University Medical Center"},{"name":"School of Medicine, Vanderbilt University"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"276","published-online":{"date-parts":[[2026,1,9]]},"reference":[{"key":"bib1-20260717","doi-asserted-by":"crossref","first-page":"852e","DOI":"10.1097\/PRS.0000000000000184","article-title":"Cleft palate repair and velopharyngeal dysfunction","volume":"133","author":"Hopper","year":"2014","journal-title":"Plast Reconstr Surg"},{"key":"bib2-20260717","doi-asserted-by":"crossref","first-page":"2089","DOI":"10.3390\/jpm12122089","article-title":"Current concepts and challenges in the treatment of cleft lip and palate patients\u2014a comprehensive review","volume":"12","author":"Paradowska-Stolarz","year":"2022","journal-title":"J Pers Med"},{"key":"bib3-20260717","doi-asserted-by":"crossref","first-page":"224","DOI":"10.1001\/archotol.133.3.224","article-title":"Quality of life in children with velopharyngeal insufficiency","volume":"133","author":"Barr","year":"2007","journal-title":"Arch Otolaryngol Head Neck Surg"},{"key":"bib4-20260717","doi-asserted-by":"crossref","first-page":"406","DOI":"10.1001\/jamafacial.2017.0639","article-title":"Association of velopharyngeal insufficiency with quality of life and patient-reported outcomes after speech surgery","volume":"19","author":"Bhuskute","year":"2017","journal-title":"JAMA Facial Plast Surg"},{"key":"bib5-20260717","doi-asserted-by":"crossref","first-page":"2570","DOI":"10.3390\/jcm13092570","article-title":"Contemporary prevalence of oral clefts in the US: geographic and socioeconomic considerations","volume":"13","author":"Brydges","year":"2024","journal-title":"J Clin Med"},{"key":"bib6-20260717","doi-asserted-by":"crossref","first-page":"161","DOI":"10.1196\/annals.1425.011","article-title":"Poverty and access to health care in developing countries","volume":"1136","author":"Peters","year":"2008","journal-title":"Ann N Y Acad Sci"},{"key":"bib7-20260717","first-page":"CD011086","article-title":"Implementation strategies for health systems in low-income countries: an overview of systematic reviews","volume":"9","author":"Pantoja","year":"2017","journal-title":"Cochrane Database Syst Rev"},{"key":"bib8-20260717","article-title":"It's time to define the global burden of velopharyngeal insufficiency","author":"Alter","journal-title":"Cleft Palate Craniofac J"},{"key":"bib9-20260717","doi-asserted-by":"crossref","first-page":"6972","DOI":"10.3390\/s23156972","article-title":"A CNN sound classification mechanism using data augmentation","volume":"23","author":"Chu","year":"2023","journal-title":"Sensors (Basel)"},{"key":"bib10-20260717","doi-asserted-by":"crossref","first-page":"676490","DOI":"10.3389\/fmed.2021.676490","article-title":"Current applications of artificial intelligence in cleft care: a scoping review","volume":"8","author":"Dhillon","year":"2021","journal-title":"Front Med (Lausanne)"},{"key":"bib11-20260717","first-page":"12449","article-title":"wav2vec 2.0: a framework for self-supervised learning of speech representations","volume":"33","author":"Baevski","year":"2020","journal-title":"Adv Neural Inform Process Syst"},{"issue":"3S Suppl 1","key":"bib12-20260717","doi-asserted-by":"crossref","first-page":"S55","DOI":"10.1097\/SAP.0000000000004460","article-title":"From support vector machines to neural networks: advancing automated velopharyngeal dysfunction detection in patients with cleft palate","volume":"95","author":"Alter","year":"2025","journal-title":"Ann Plast Surg"},{"key":"bib13-20260717","doi-asserted-by":"crossref","first-page":"816","DOI":"10.1097\/SCS.0000000000010147","article-title":"Machine learning for automatic detection of velopharyngeal dysfunction: a preliminary report","volume":"36","author":"Lucas","year":"2025","journal-title":"J Craniofac Surg"},{"key":"bib14-20260717","doi-asserted-by":"crossref","first-page":"3451","DOI":"10.1109\/TASLP.2021.3122291","article-title":"Hubert: self-supervised speech representation learning by masked prediction of hiden units","volume":"29","author":"Hsu","year":"2021","journal-title":"IEEE\/ACM Transact Audio Speech Lang Process"},{"key":"bib15-20260717","first-page":"1298","article-title":"Data2vec: a general framework for self-supervised learning in speech, vision and language","author":"Baevski","year":"2022","journal-title":"Proc Machine Learn Res"},{"key":"bib16-20260717","article-title":"Robust speech recognition via large-scale weak supervision","author":"Radford","year":"2023","journal-title":"Proc Machine Learn Res"},{"key":"bib17-20260717","doi-asserted-by":"crossref","first-page":"23","DOI":"10.1007\/s10916-022-01807-1","article-title":"Domain shifts in machine learning based Covid-19 diagnosis from blood tests","volume":"46","author":"Roland","year":"2022","journal-title":"J Med Syst"},{"key":"bib18-20260717","doi-asserted-by":"crossref","first-page":"104902","DOI":"10.1016\/j.jbi.2025.104902","article-title":"Strategies for detecting and mitigating dataset shift in machine learning for health predictions: a systematic review","volume":"170","author":"Silva","year":"2025","journal-title":"J Biomed Inform"},{"key":"bib19-20260717","doi-asserted-by":"crossref","first-page":"2986","DOI":"10.1109\/TBME.2021.3058424","article-title":"A deep learning algorithm for objective assessment of hypernasality in children with cleft palate","volume":"68","author":"Mathad","year":"2021","journal-title":"IEEE Trans Biomed Eng"},{"key":"bib20-20260717","doi-asserted-by":"crossref","first-page":"587","DOI":"10.1114\/1.1380422","article-title":"A noninvasive estimation of hypernasality using a linear predictive model","volume":"29","author":"Rah","year":"2001","journal-title":"Ann Biomed Eng"},{"key":"bib21-20260717","doi-asserted-by":"crossref","first-page":"1552746","DOI":"10.3389\/fdgth.2025.1552746","article-title":"Leveraging large language models for automated detection of velopharyngeal dysfunction in patients with cleft palate","volume":"7","author":"Shirk","year":"2025","journal-title":"Front Digit Health"},{"key":"bib22-20260717","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.ijmedinf.2019.05.023","article-title":"HypernasalityNet: deep recurrent neural network for automatic hypernasality detection","volume":"129","author":"Wang","year":"2019","journal-title":"Int J Med Inform"},{"key":"bib23-20260717","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1044\/1059-0889(2000\/003)","article-title":"ANSI update: maximum permissible ambient noise levels for audiometric test rooms","volume":"9","author":"Frank","year":"2000","journal-title":"Am J Audiol"},{"key":"bib32-20260717","doi-asserted-by":"crossref","first-page":"195","DOI":"10.1186\/s12916-019-1426-2","article-title":"Key challenges for delivering clinical impact with artificial intelligence","volume":"17","author":"Kelly","year":"2019","journal-title":"BMC Med"},{"key":"bib33-20260717","doi-asserted-by":"crossref","first-page":"2423","DOI":"10.11124\/JBIES-24-00042","article-title":"Monitoring performance of clinical artificial intelligence in health care: a scoping review","volume":"22","author":"Andersen","year":"2024","journal-title":"JBI Evid Synth"},{"key":"bib34-20260717","doi-asserted-by":"crossref","first-page":"29224","DOI":"10.1038\/s41598-024-79838-6","article-title":"The risk of shortcutting in deep learning algorithms for medical imaging research","volume":"14","author":"Hill","year":"2024","journal-title":"Sci Rep"},{"key":"bib35-20260717","doi-asserted-by":"crossref","first-page":"929","DOI":"10.1121\/1.4976056","article-title":"Automatic identification of hypernasality in normal and cleft lip and palate patients with acoustic analysis of speech","volume":"141","author":"Golabbakhsh","year":"2017","journal-title":"J Acoust Soc Am"},{"key":"bib36-20260717","doi-asserted-by":"crossref","first-page":"4133","DOI":"10.1007\/s00034-025-03007-x","article-title":"Spectral analysis based objective assessment of hypernasality in cleft palate speech: a review","volume":"44","author":"Dubey","year":"2025","journal-title":"Circuits Syst Signal Process"},{"key":"bib37-20260717","doi-asserted-by":"crossref","first-page":"73","DOI":"10.1515\/bmt-2018-0181","article-title":"Automatic hypernasality grade assessment in cleft palate speech based on the spectral envelope method","volume":"65","author":"Zhang","year":"2020","journal-title":"Biomed Tech (Berl)"},{"key":"bib38-20260717","doi-asserted-by":"crossref","first-page":"2714","DOI":"10.3390\/diagnostics13162714","article-title":"Automatic detection system for velopharyngeal insufficiency based on acoustic signals from nasal and oral channels","volume":"13","author":"Zhang","year":"2023","journal-title":"Diagnostics (Basel)"},{"key":"bib39-20260717","doi-asserted-by":"crossref","first-page":"22787","DOI":"10.1038\/s41598-023-49352-2","article-title":"Towards interpretable speech biomarkers: exploring MFCCs","volume":"13","author":"Tracey","year":"2023","journal-title":"Sci Rep"}],"container-title":["Annals of Plastic Surgery"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/journals.lww.com\/10.1097\/SAP.0000000000004633","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T06:00:13Z","timestamp":1784268013000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.lww.com\/10.1097\/SAP.0000000000004633"}},"subtitle":["Out-of-Domain Validation of Machine Learning Models for Velopharyngeal Dysfunction Detection"],"short-title":[],"issued":{"date-parts":[[2026,1,9]]},"references-count":31,"journal-issue":{"issue":"1S","published-print":{"date-parts":[[2026]]}},"URL":"https:\/\/doi.org\/10.1097\/sap.0000000000004633","relation":{},"ISSN":["1536-3708","0148-7043"],"issn-type":[{"value":"1536-3708","type":"electronic"},{"value":"0148-7043","type":"print"}],"subject":[],"published":{"date-parts":[[2026,1,9]]}}}