Sökning: onr:"swepub:oai:lup.lub.lu.se:9a2c6f3a-5040-4b12-9b9e-a558ffe1d3e5" >
Using Artificial In...
Using Artificial Intelligence for Assessment of Velopharyngeal Competence in Children Born With Cleft Palate With or Without Cleft Lip
-
- Cornefjord, Måns (författare)
- Lund University,Lunds universitet,Kirurgi,Forskargrupper vid Lunds universitet,Surgery,Lund University Research Groups,Skåne University Hospital
-
- Bluhme, Joel (författare)
- Lund University
-
- Jakobsson, Andreas (författare)
- Lund University,Lunds universitet,Biomedical Modelling and Computation,Forskargrupper vid Lunds universitet,Statistical Signal Processing Group,Matematisk statistik,Matematikcentrum,Institutioner vid LTH,Lunds Tekniska Högskola,LTH profilområde: AI och digitalisering,LTH profilområden,LTH profilområde: Teknik för hälsa,LU profilområde: Naturlig och artificiell kognition,Lunds universitets profilområden,Lund University Research Groups,Mathematical Statistics,Centre for Mathematical Sciences,Departments at LTH,Faculty of Engineering, LTH,LTH Profile Area: AI and Digitalization,LTH Profile areas,Faculty of Engineering, LTH,LTH Profile Area: Engineering Health,Faculty of Engineering, LTH,LU Profile Area: Natural and Artificial Cognition,Lund University Profile areas
-
visa fler...
-
- Klintö, Kristina (författare)
- Lund University,Lunds universitet,Logopedi, foniatri och audiologi,Sektion IV,Institutionen för kliniska vetenskaper, Lund,Medicinska fakulteten,Kirurgi,Forskargrupper vid Lunds universitet,Logopedics, Phoniatrics and Audiology,Section IV,Department of Clinical Sciences, Lund,Faculty of Medicine,Surgery,Lund University Research Groups,Skåne University Hospital
-
- Lohmander, Anette (författare)
- Karolinska Institute
-
- Mamedov, Tofig (författare)
- Lund University,Lunds universitet,Matematisk statistik,Matematikcentrum,Institutioner vid LTH,Lunds Tekniska Högskola,Mathematical Statistics,Centre for Mathematical Sciences,Departments at LTH,Faculty of Engineering, LTH
-
- Stiernman, Mia (författare)
- Lund University,Lunds universitet,Kirurgi,Forskargrupper vid Lunds universitet,Surgery,Lund University Research Groups,Skåne University Hospital
-
- Svensson, Rebecca (författare)
- Lund University
-
- Becker, Magnus (författare)
- Lund University,Lunds universitet,Kirurgi,Forskargrupper vid Lunds universitet,Surgery,Lund University Research Groups,Skåne University Hospital
-
visa färre...
-
(creator_code:org_t)
- Engelska.
-
Ingår i: Cleft Palate - Craniofacial Journal. - 1545-1569.
- Relaterad länk:
-
http://dx.doi.org/10...
-
visa fler...
-
https://lup.lub.lu.s...
-
visa färre...
Abstract
Ämnesord
Stäng
- ObjectiveDevelopment of an AI tool to assess velopharyngeal competence (VPC) in children with cleft palate, with/without cleft lip.DesignInnovation of an AI tool using retrospective audio recordings and assessments of VPC.SettingTwo datasets were used. The first, named the SR dataset, included data from follow-up visits to Skåne University Hospital, Sweden. The second, named the SC + IC dataset, was a combined dataset (SC + IC dataset) with data from the Scandcleft randomized trials across five countries and an intercenter study performed at six Swedish CL/P centers.ParticipantsSR dataset included 153 recordings from 162 children, and SC + IC dataset included 308 recordings from 399 children. All recordings were from ages 5 or 10, with corresponding VPC assessments.InterventionsDevelopment of two networks, a convolutional neural network (CNN) and a pre-trained CNN (VGGish). After initial testing using the SR dataset, the networks were re-tested using the SC + IC dataset and modified to improve performance.Main Outcome MeasuresAccuracy of the networks' VPC scores, with speech and language pathologistś scores seen as the true values. A three-point scale was used for VPC assessments.ResultsVGGish outperformed CNN, achieving 57.1% accuracy compared to 39.8%. Minor adjustments in data pre-processing and network characteristics improved accuracies.ConclusionsNetwork accuracies were too low for the networks to be useful alternatives for VPC assessment in clinical practice. Suggestions for future research with regards to study design and dataset optimization were discussed.
Ämnesord
- MEDICIN OCH HÄLSOVETENSKAP -- Klinisk medicin -- Pediatrik (hsv//swe)
- MEDICAL AND HEALTH SCIENCES -- Clinical Medicine -- Pediatrics (hsv//eng)
Publikations- och innehållstyp
- art (ämneskategori)
- ref (ämneskategori)
Hitta via bibliotek
Till lärosätets databas