Screening Children's Intellectual Disabilities with Phonetic Features, Facial Phenotype and Craniofacial Variability Index

• Published in: Brain sciences 2023-01, Vol.13 (1), p.155
• Main Authors: Chen, Yuhe, Ma, Simeng, Yang, Xiaoyu, Liu, Dujuan, Yang, Jun
• Format: Article
• Language: English
• Subjects: Algorithms; Alzheimer's disease; Artificial intelligence; Children; Cognitive ability; Congenital anomalies; craniofacial variability index; Datasets; facial features; Fetal alcohol syndrome; Genotype & phenotype; Intellectual disabilities; intellectual disability; Intelligence tests; Language disorders; Machine learning; Medical diagnosis; Medical personnel; Patients; People with disabilities; Phenotypes; Phonetic features; Phonetics; Psychiatrists; Rehabilitation; Speech
• ISSN: 2076-3425; 2076-3425
• DOI: 10.3390/brainsci13010155

Intellectual Disability (ID) is a kind of developmental deficiency syndrome caused by congenital diseases or postnatal events. This syndrome could be intervened as soon as possible if its early screening was efficient, which may improve the condition of patients and enhance their self-care ability. The early screening of ID is always achieved by clinical interview, which needs in-depth participation of medical professionals and related medical resources. A new method for screening ID has been proposed by analyzing the facial phenotype and phonetic characteristic of young subjects. First, the geometric features of subjects' faces and phonetic features of subjects' voice are extracted from interview videos, then craniofacial variability index (CVI) is calculated with the geometric features and the risk of ID is given with the measure of CVI. Furthermore, machine learning algorithms are utilized to establish a method for further screening ID based on facial features and phonetic features. The proposed method using three feature sets, including geometric features, CVI features and phonetic features was evaluated. The best performance of accuracy was closer to 80%. The results using the three feature sets revealed that the proposed method may be applied in a clinical setting in the future after continuous improvement.