Using Artificial Intelligence for Assessment of Velopharyngeal Competence in Children Born With Cleft Palate With or Without Cleft Lip.

OBJECTIVE: Development of an AI tool to assess velopharyngeal competence (VPC) in children with cleft palate, with/without cleft lip. DESIGN: Innovation of an AI tool using retrospective audio recordings and assessments of VPC. SETTING: Two 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. PARTICIPANTS: SR 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. INTERVENTIONS: Development 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 MEASURES: Accuracy of the networks' VPC scores, with speech and language pathologists scores seen as the true values. A three-point scale was used for VPC assessments. RESULTS: VGGish outperformed CNN, achieving 57.1% accuracy compared to 39.8%. Minor adjustments in data pre-processing and network characteristics improved accuracies. CONCLUSIONS: Network 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.

Surgical treatment of velopharyngeal dysfunction: Incidence and associated factors in the Swedish cleft palate population.

INTRODUCTION: Speech in children with cleft palate can be affected by velopharyngeal dysfunction, which persists after primary palate repair. The incidence of surgery to correct velopharyngeal dysfunction in this patient group has previously been reported as 2.6-37%. We aimed to investigate the incidence of velopharyngeal dysfunction surgery in Swedish children with cleft palate and to examine potential associations of independent variables with this incidence. METHODS: In this cohort study, we analysed data from the Swedish cleft lip and palate quality registry for 1093 children with cleft palate with or without cleft lip. Kaplan-Meier analysis was used to estimate the risk of having velopharyngeal dysfunction surgery. Multivariable Cox proportional hazards models were used to estimate the associated effect of cleft subtype, additional diagnoses, gender, and age at and number of stages for primary palate repair on the primary outcome. RESULTS: The risk of having velopharyngeal dysfunction surgery was 25.6%. Complete primary palate repair after the age of 18 months or in more than one stage was associated with a higher risk, but it could not be determined which of these was the more significant factor. Cleft soft palate was associated with a significantly lower risk than other cleft subtypes. CONCLUSIONS: Primary palate repair at a higher age or in more than one stage may increase the risk of having velopharyngeal dysfunction surgery. Further analysis of potential unknown confounding factors and the association between the incidence of velopharyngeal dysfunction and surgery to correct this condition is needed.

A systematic review of differences in outcome between one and two stage palate repair in cleft lip and palate.

The aim of this systematic review was to determine whether one-stage palatoplasty for children born with cleft lip and palate shows overall advantages in outcome compared with two-stage palatoplasty. The included studies were controlled studies of syndromic and non-syndromic children born with unilateral cleft lip and palate, bilateral cleft lip and palate, or isolated cleft palate. The interventions studied were one-stage palatoplasty and two-stage palatoplasty starting with the soft palate. The outcomes were facial growth, speech, hearing, presence of fistulae, other complications related to surgery, health-related quality of life, and health economics. In total, 14 original studies were included. Results were dichotomized into showing advantage for one- or two-stage palatoplasty for the respective outcome and compared with the results from six included systematic reviews. No overall advantage for either surgical strategy was found for any of the outcome measures. The certainty of evidence was highest for the presence of fistulae, followed by facial growth and speech. For several outcomes, the quality of the existing evidence was too low to allow for any conclusions to be drawn. Neither one- nor two-stage palatoplasty showed significant advantages in clinical outcomes compared with the other. Other aspects such as ethics, economics, or surgeon's preference might hence be of more importance. Homogenous choices of outcome measures and defined minimal clinically important differences would facilitate further research.

Scores of the Cleft Hearing, Appearance and Speech Questionnaire (CHASQ) in Swedish Participants With Cleft lip and/or Cleft Palate and a Control Population.

OBJECTIVE: The primary aim of this study was to investigate whether there was any difference in scores of the Cleft Hearing, Appearance and Speech Questionnaire (CHASQ) between patients with cleft lip and/or cleft palate (CL/P) and a control population. The second aim was to compare CL/P and control population scores in this study with a British norm CL/P population. DESIGN: Single-site, cross-sectional study with an age-matched control population. SETTING: Participants were recruited from a hospital, a school, and a sports club. They answered the CHASQ in the hospital or at home. PARTICIPANTS: Sixty-four participants with CL/P (7-19 years of age) and a control population of 56 participants without CL/P (9-20 years of age). MAIN OUTCOME MEASURE: CHASQ. RESULTS: There was no statistically significant difference in satisfaction with cleft-related features between the CL/P and the control population. Participants with CL/P were significantly more satisfied with non-cleft-related features than the control population. Cleft Hearing, Appearance and Speech Questionnaire scores were also similar to earlier established British normative data of a CL/P population. CONCLUSION: The results indicated that children and young people with CL/P were as satisfied with their appearance, hearing, and speech as children and young people without CL/P. Swedish CHASQ scores were also similar to British scores.

Comparison of Corresponding Scores From the Cleft Hearing Appearance and Speech Questionnaire (CHASQ) and CLEFT-Q in Swedish Patients With Cleft Lip and/or Palate.

OBJECTIVE: The primary aim of this study was to compare corresponding scores between 2 existing cleft-specific patient-reported outcome measures (PROMs)-Cleft Hearing Appearance and Speech Questionnaire (CHASQ) and CLEFT-Q. The second aim of the study was to investigate patient opinion on the 2 PROMs. DESIGN: Cross-sectional questionnaire study. SETTING: Participants were recruited from a University Hospital. They answered CHASQ and CLEFT-Q either in the hospital or at home. PARTICIPANTS: Thirty-three participants with cleft lip and/or palate, aged 10 to 19 years. MAIN OUTCOME MEASURE: CHASQ and CLEFT-Q. RESULTS: The CHASQ scores and the corresponding CLEFT-Q scores on appearance correlated significantly. Corresponding scores regarding speech did not correlate significantly. A majority, 15 (58%) participants, answered that they liked CLEFT-Q more than CHASQ, 18 participants (69%) thought CHASQ was easier to complete, and 19 (76%) thought CLEFT-Q would better inform health care professionals. CONCLUSION: Both instruments showed strengths and limitations. Clinicians will have to consider each instrument's respective qualities when choosing to implement either PROM.

Psychometric findings and normative values for the CLEFT-Q based on 2434 children and young adult patients with cleft lip and/or palate from 12 countries.

BACKGROUND: Patients with cleft lip and/or palate can undergo numerous procedures to improve appearance, speech, dentition and hearing. We developed a cleft-specific patient-reported outcome instrument to facilitate rigorous international measurement and benchmarking. METHODS: Data were collected from patients aged 8-29 years with cleft lip and/or palate at 30 hospitals in 12 countries between October 2014 and November 2016. Rasch measurement theory analysis was used to refine the scales and to examine reliability and validity. Normative CLEFT-Q values were computed for age, sex and cleft type. RESULTS: Analysis led to the refinement of an eating and drinking checklist and 12 scales measuring appearance (of the face, nose, nostrils, teeth, lips, jaws and cleft lip scar), health-related quality of life (psychological, social, school, speech distress) and speech function. All scales met the requirements of the Rasch model. Analysis to explore differential item functioning by age, sex and country provided evidence to support the use of a common scoring algorithm for each scale for international use. Lower (worse) scores on CLEFT-Q scales were associated with having a speech problem, being unhappy with facial appearance, and needing future cleft-related treatments, providing evidence of construct validity. Normative values for age, sex and cleft type showed poorer outcomes associated with older age, female sex and having a visible cleft. INTERPRETATION: The CLEFT-Q represents a rigorously developed instrument that can be used internationally to collect and compare evidence-based outcomes data from patients aged 8-29 years of age with cleft lip and/or palate.

Subjective outcomes after treatment for velopharyngeal dysfunction.

BACKGROUND: Velopharyngeal dysfunction (VPD) can have various causes and may be a significant disability for the affected patient. Treatment options include surgery and speech therapy, but the success rates are often inconsistent. METHODS: In this study, self-assessment questionnaires were sent out to 222 Swedish patients with VPD. The questionnaire included questions about satisfaction with speech, perceived speech quality, perceived improvement from VPD-surgery, and/or speech therapy. Out of 117 (52.7%) respondents, 114 (51.4%) patients were included in the study. The participants were 7-71 years of age (median = 14 years), diagnosed with cleft palate, neurological/developmental delay, congenital hypernasality, or acquired VPD. All patients had previously undergone videofluoroscopy, and 61.4% had undergone VPD-surgery. RESULTS: Seventy-one per cent of the patients perceived their speech to be normal or slightly deviant, but only 55% were satisfied with their speech. Sixty per cent of the operated on patients felt that the treatment had improved their speech much or very much, 10% thought that they had moderate improvement, and 30% stated that they had no or little improvement. Out of the patients that had received speech therapy, 41% felt that the treatment had improved their speech much or very much, 21% thought that they had moderate improvement, and 33% stated that they had no or little improvement. CONCLUSION: In conclusion, most patients with VPD in this study who underwent evaluation and treatment felt that surgery and speech therapy had improved their speech, but only about half of them were in the end satisfied with the quality of their speech.