Deep-Learning-Based Detection of Infants with Autism Spectrum Disorder Using Auto-Encoder Feature Representation

Abstract

Autism spectrum disorder (ASD) is a developmental disorder with a life-span disability. While diagnostic instruments have been developed and qualified based on the accuracy of the discrimination of children with ASD from typical development (TD) children, the stability of such procedures can be disrupted by limitations pertaining to time expenses and the subjectivity of clinicians. Consequently, automated diagnostic methods have been developed for acquiring objective measures of autism, and in various fields of research, vocal characteristics have not only been reported as distinctive characteristics by clinicians, but have also shown promising performance in several studies utilizing deep learning models based on the automated discrimination of children with ASD from children with TD. However, difficulties still exist in terms of the characteristics of the data, the complexity of the analysis, and the lack of arranged data caused by the low accessibility for diagnosis and the need to secure anonymity. In order to address these issues, we introduce a pre-trained feature extraction auto-encoder model and a joint optimization scheme, which can achieve robustness for widely distributed and unrefined data using a deep-learning-based method for the detection of autism that utilizes various models. By adopting this auto-encoder-based feature extraction and joint optimization in the extended version of the Geneva minimalistic acoustic parameter set (eGeMAPS) speech feature data set, we acquire improved performance in the detection of ASD in infants compared to the raw data set.

Classifying Autism From Crowdsourced Semistructured Speech Recordings: Machine Learning Model Comparison Study

“…Prior research [15,16] investigated prosodic disorders in children with autism to varying degrees of success. Cho et al [17] developed models that achieved 76% accuracy on a dataset of recorded interviews between children and unfamiliar adults, trained on data recorded at a consistent location using a specialized biosensor device with 4 directional microphones.…”

The Role of Intelligent Technologies in Early Detection of Autism Spectrum Disorder (ASD): A Scoping Review

“…Each unique article's title and abstract were screened for relevancy, followed by a full-text analysis per the inclusion-exclusion criteria listed in subsection II-A. Thirty-two studies were shortlisted post-full-text analysis, and additional three publications [44]- [46] were uncovered by analyzing the shortlisted study's references, making the total shortlisted study count to 35.…”

“…The quality evaluation suggested ten studies with moderate quality [46], [48]- [50], [52], [53], [56], [57], [63], [76]. While twenty-five studies were classified as high-quality [44], [45], [47], [51], [54], [55], [59]- [62], [64]- [72], [74], [75], [77], [78], [83], [84]. In general, the quality analysis scores highlighted small sample sizes for most studies, unclear study questions and objectives, insufficient information on sampling, recruitment, inclusion and exclusion criteria, and imprecise data analysis and outcomes reporting.…”

“…Volubility refers to syllable production frequency and is usually limited in children with ASD [123]. In the review, three studies analyzed audio data; two used syllable production, speech patterns, and canonical babbling [44], [45], and the third used crying patterns [46] to detect ASD. [44] used a pre-trained feature extraction auto-encoder integrated with a joint optimization method, and trained four ML models on eGeMAPS (Geneva minimalistic acoustic parameter set) dataset [124].…”

“…In the review, three studies analyzed audio data; two used syllable production, speech patterns, and canonical babbling [44], [45], and the third used crying patterns [46] to detect ASD. [44] used a pre-trained feature extraction auto-encoder integrated with a joint optimization method, and trained four ML models on eGeMAPS (Geneva minimalistic acoustic parameter set) dataset [124]. The ML models: SVM, BLSTM (88 features) [125], BLSTM (54 features), and optimized AE BLSTM were tested on 95 ASD and 130 TD utterances across five vocalizations categories: syllables, canonical babbling, calling mother or father, screaming and crying.…”