Detecting Abnormal Word Utterances in Children With Autism Spectrum Disorders: Machine-Learning-Based Voice Analysis Versus Speech Therapists

Voice as a Biomarker of Pediatric Health: A Scoping Review

The human voice has the potential to serve as a valuable biomarker for the early detection, diagnosis, and monitoring of pediatric conditions. This scoping review synthesizes the current knowledge on the application of artificial intelligence (AI) in analyzing pediatric voice as a biomarker for health. The included studies featured voice recordings from pediatric populations aged 0-17 years, utilized feature extraction methods, and analyzed pathological biomarkers using AI models. Data from 62 studies were extracted, encompassing study and participant characteristics, recording sources, feature extraction methods, and AI models. Data from 39 models across 35 studies were evaluated for accuracy, sensitivity, and specificity. The review showed a global representation of pediatric voice studies, with a focus on developmental, respiratory, speech, and language conditions. The most frequently studied conditions were autism spectrum disorder, intellectual disabilities, asphyxia, and asthma. Mel-Frequency Cepstral Coefficients were the most utilized feature extraction method, while Support Vector Machines were the predominant AI model. The analysis of pediatric voice using AI demonstrates promise as a non-invasive, cost-effective biomarker for a broad spectrum of pediatric conditions. Further research is necessary to standardize the feature extraction methods and AI models utilized for the evaluation of pediatric voice as a biomarker for health. Standardization has significant potential to enhance the accuracy and applicability of these tools in clinical settings across a variety of conditions and voice recording types. Further development of this field has enormous potential for the creation of innovative diagnostic tools and interventions for pediatric populations globally.

Machine Learning-Based Blood RNA Signature for Diagnosis of Autism Spectrum Disorder

Early diagnosis of autism spectrum disorder (ASD) is crucial for providing appropriate treatments and parental guidance from an early age. Yet, ASD diagnosis is a lengthy process, in part due to the lack of reliable biomarkers. We recently applied RNA-sequencing of peripheral blood samples from 73 American and Israeli children with ASD and 26 neurotypically developing (NT) children to identify 10 genes with dysregulated blood expression levels in children with ASD. Machine learning (ML) analyzes data by computerized analytical model building and may be applied to building diagnostic tools based on the optimization of large datasets. Here, we present several ML-generated models, based on RNA expression datasets collected during our recently published RNA-seq study, as tentative tools for ASD diagnosis. Using the random forest classifier, two of our proposed models yield an accuracy of 82% in distinguishing children with ASD and NT children. Our proof-of-concept study requires refinement and independent validation by studies with far larger cohorts of children with ASD and NT children and should thus be perceived as starting point for building more accurate ML-based tools. Eventually, such tools may potentially provide an unbiased means to support the early diagnosis of ASD.

Cross-linguistic patterns of speech prosodic differences in autism: A machine learning study

Differences in speech prosody are a widely observed feature of Autism Spectrum Disorder (ASD). However, it is unclear how prosodic differences in ASD manifest across different languages that demonstrate cross-linguistic variability in prosody. Using a supervised machine-learning analytic approach, we examined acoustic features relevant to rhythmic and intonational aspects of prosody derived from narrative samples elicited in English and Cantonese, two typologically and prosodically distinct languages. Our models revealed successful classification of ASD diagnosis using rhythm-relative features within and across both languages. Classification with intonation-relevant features was significant for English but not Cantonese. Results highlight differences in rhythm as a key prosodic feature impacted in ASD, and also demonstrate important variability in other prosodic properties that appear to be modulated by language-specific differences, such as intonation.

Annual Research Review: Translational machine learning for child and adolescent psychiatry

Children and adolescents could benefit from the use of predictive tools that facilitate personalized diagnoses, prognoses, and treatment selection. Such tools have not yet been deployed using traditional statistical methods, potentially due to the limitations of the paradigm and the need to leverage large amounts of digital data. This review will suggest that a machine learning approach could address these challenges and is designed to introduce new readers to the background, methods, and results in the field. A rationale is first introduced followed by an outline of fundamental elements of machine learning approaches. To provide an overview of the use of the techniques in child and adolescent literature, a scoping review of broad trends is then presented. Selected studies are also highlighted in order to draw attention to research areas that are closest to translation and studies that exhibit a high degree of experimental innovation. Limitations to the research, and machine learning approaches generally, are outlined in the penultimate section highlighting issues related to sample sizes, validation, clinical utility, and ethical challenges. Finally, future directions are discussed that could enhance the possibility of clinical implementation and address specific questions relevant to the child and adolescent psychiatry. The review gives a broad overview of the machine learning paradigm in order to highlight the benefits of a shift in perspective towards practically oriented statistical solutions that aim to improve clinical care of children and adolescents.

The diagnosis of ASD using multiple machine learning techniques

Autism Spectrum Disorder (ASD) is a highly heterogeneous set of neurodevelopmental disorders with the global prevalence estimates of 2.20%, according to DSM5 criteria. With the advancements of technology and availability of huge amount of data, assistive tools for diagnosis of ASD are being developed using machine learning techniques. The present study examines the possibility of automating the Autism diagnostic tool using various machine learning techniques on a dataset of 701 samples that contains 10 fields from AQ-10-Adult and 10 from individual characteristics. It takes two scenarios into consideration. First one is ideal case, where there are no missing values in the test cases. In this case Artificial Neural Network (ANN), Support Vector Machine (SVM) and Random Forest (RF) classifiers are trained and tested on the pre-processed dataset. To reduce computational complexity Recursive Feature Elimination (RFE) based feature selection algorithm is applied. To deal with the real-world data, in the second case missing values are introduced in the test dataset for the fields' 'age', 'gender', 'jaundice', 'autism', 'used_app_before' and their three combinations. Support Vector Machine, Random Forest, Decision Tree and Logistic Regression based RFE algorithm is introduced to handle this scenario. ANN, SVM and RF classifier based learning models are trained with all the cases. Twelve classification models were generated with RFE, out of which best performing models specific to missing value were evaluated using test cases and suggested for ASD Diagnosis.

Early screening of autism spectrum disorder using cry features

The increase in the number of children with autism and the importance of early autism intervention has prompted researchers to perform automatic and early autism screening. Consequently, in the present paper, a cry-based screening approach for children with Autism Spectrum Disorder (ASD) is introduced which would provide both early and automatic screening. During the study, we realized that ASD specific features are not necessarily observable in all children with ASD and in all instances collected from each child. Therefore, we proposed a new classification approach to be able to determine such features and their corresponding instances. To test the proposed approach a set of data relating to children between 18 to 53 months which had been recorded using high-quality voice recording devices and typical smartphones at various locations such as homes and daycares was studied. Then, after preprocessing, the approach was used to train a classifier, using data for 10 boys with ASD and 10 Typically Developed (TD) boys. The trained classifier was tested on the data of 14 boys and 7 girls with ASD and 14 TD boys and 7 TD girls. The sensitivity, specificity, and precision of the proposed approach for boys were 85.71%, 100%, and 92.85%, respectively. These measures were 71.42%, 100%, and 85.71% for girls, respectively. It was shown that the proposed approach outperforms the common classification methods. Furthermore, it demonstrated better results than the studies which used voice features for screening ASD. To pilot the practicality of the proposed approach for early autism screening, the trained classifier was tested on 57 participants between 10 to 18 months. These 57 participants consisted of 28 boys and 29 girls and the results were very encouraging for the use of the approach in early ASD screening.

Quantifying the Uncertainty of Parameters Measured in Spontaneous Speech of Speakers With Dementia

Purpose Corpus analyses of spontaneous language fragments of varying length provide useful insights in the language change caused by brain damage, such as caused by some forms of dementia. Sample size is an important experimental parameter to consider when designing spontaneous language analyses studies. Sample length influences the confidence levels of analyses. Machine learning approaches often favor to use as much language as available, whereas language evaluation in a clinical setting is often based on truncated samples to minimize annotation labor and to limit any discomfort for participants. This article investigates, using Bayesian estimation of machine learned models, what the ideal text length should be to minimize model uncertainty. Method We use the Stanford parser to extract linguistic variables and train a statistic model to distinguish samples by speakers with no brain damage from samples by speakers with probable Alzheimer's disease. We compare the results to previously published models that used CLAN for linguistic analysis. Results The uncertainty around six individual variables and its relation to sample length are reported. The same model with linguistic variables that is used in all three experiments can predict group membership better than a model without them. One variable (concept density) is more informative when measured using the Stanford tools than when measured using CLAN. Conclusion For our corpus of German speech, the optimal sample length is found to be around 700 words long. Longer samples do not provide more information.

Application of Supervised Machine Learning for Behavioral Biomarkers of Autism Spectrum Disorder Based on Electrodermal Activity and Virtual Reality

OBJECTIVE

Sensory processing is the ability to capture, elaborate, and integrate information through the five senses and is impaired in over 90% of children with autism spectrum disorder (ASD). The ASD population shows hyper-hypo sensitiveness to sensory stimuli that can generate alteration in information processing, affecting cognitive and social responses to daily life situations. Structured and semi-structured interviews are generally used for ASD assessment, and the evaluation relies on the examiner's subjectivity and expertise, which can lead to misleading outcomes. Recently, there has been a growing need for more objective, reliable, and valid diagnostic measures, such as biomarkers, to distinguish typical from atypical functioning and to reliably track the progression of the illness, helping to diagnose ASD. Implicit measures and ecological valid settings have been showing high accuracy on predicting outcomes and correctly classifying populations in categories.

METHODS

Two experiments investigated whether sensory processing can discriminate between ASD and typical development (TD) populations using electrodermal activity (EDA) in two multimodal virtual environments (VE): forest VE and city VE. In the first experiment, 24 children with ASD diagnosis and 30 TDs participated in both virtual experiences, and changes in EDA have been recorded before and during the presentation of visual, auditive, and olfactive stimuli. In the second experiment, 40 children have been added to test the model of experiment 1.

RESULTS

The first exploratory results on EDA comparison models showed that the integration of visual, auditive, and olfactive stimuli in the forest environment provided higher accuracy (90.3%) on sensory dysfunction discrimination than specific stimuli. In the second experiment, 92 subjects experienced the forest VE, and results on 72 subjects showed that stimuli integration achieved an accuracy of 83.33%. The final confirmatory test set (n = 20) achieved 85% accuracy, simulating a real application of the models. Further relevant result concerns the visual stimuli condition in the first experiment, which achieved 84.6% of accuracy in recognizing ASD sensory dysfunction.

CONCLUSION

According to our studies' results, implicit measures, such as EDA, and ecological valid settings can represent valid quantitative methods, along with traditional assessment measures, to classify ASD population, enhancing knowledge on the development of relevant specific treatments.

Towards the automatic detection of social biomarkers in autism spectrum disorder: introducing the simulated interaction task (SIT)

Social interaction deficits are evident in many psychiatric conditions and specifically in autism spectrum disorder (ASD), but hard to assess objectively. We present a digital tool to automatically quantify biomarkers of social interaction deficits: the simulated interaction task (SIT), which entails a standardized 7-min simulated dialog via video and the automated analysis of facial expressions, gaze behavior, and voice characteristics. In a study with 37 adults with ASD without intellectual disability and 43 healthy controls, we show the potential of the tool as a diagnostic instrument and for better description of ASD-associated social phenotypes. Using machine-learning tools, we detected individuals with ASD with an accuracy of 73%, sensitivity of 67%, and specificity of 79%, based on their facial expressions and vocal characteristics alone. Especially reduced social smiling and facial mimicry as well as a higher voice fundamental frequency and harmony-to-noise-ratio were characteristic for individuals with ASD. The time-effective and cost-effective computer-based analysis outperformed a majority vote and performed equal to clinical expert ratings.

Pre- and Paralinguistic Vocal Production in ASD: Birth Through School Age

PURPOSE OF REVIEW

We review what is known about how pre-linguistic vocal differences in autism spectrum disorder (ASD) unfold across development and consider whether vocalization features can serve as useful diagnostic indicators.

RECENT FINDINGS

Differences in the frequency and acoustic quality of several vocalization types (e.g., babbles and cries) during the first year of life are associated with later ASD diagnosis. Paralinguistic features (e.g., prosody) measured during early and middle childhood can accurately classify current ASD diagnosis using cross-validated machine learning approaches. Pre-linguistic vocalization differences in infants are promising behavioral markers of later ASD diagnosis. In older children, paralinguistic features hold promise as diagnostic indicators as well as clinical targets. Future research efforts should focus on (1) bridging the gap between basic research and practical implementations of early vocalization-based risk assessment tools, and (2) demonstrating the clinical impact of targeting atypical vocalization features during social skill interventions for older children.

Review of Machine Learning Algorithms for Diagnosing Mental Illness

OBJECTIVE

Enhanced technology in computer and internet has driven scale and quality of data to be improved in various areas including healthcare sectors. Machine Learning (ML) has played a pivotal role in efficiently analyzing those big data, but a general misunderstanding of ML algorithms still exists in applying them (e.g., ML techniques can settle a problem of small sample size, or deep learning is the ML algorithm). This paper reviewed the research of diagnosing mental illness using ML algorithm and suggests how ML techniques can be employed and worked in practice.

METHODS

Researches about mental illness diagnostic using ML techniques were carefully reviewed. Five traditional ML algorithms-Support Vector Machines (SVM), Gradient Boosting Machine (GBM), Random Forest, Naïve Bayes, and K-Nearest Neighborhood (KNN)-frequently used for mental health area researches were systematically organized and summarized.

RESULTS

Based on literature review, it turned out that Support Vector Machines (SVM), Gradient Boosting Machine (GBM), Random Forest, Naïve Bayes, and K-Nearest Neighborhood (KNN) were frequently employed in mental health area, but many researchers did not clarify the reason for using their ML algorithm though every ML algorithm has its own advantages. In addition, there were several studies to apply ML algorithms without fully understanding the data characteristics.

CONCLUSION

Researchers using ML algorithms should be aware of the properties of their ML algorithms and the limitation of the results they obtained under restricted data conditions. This paper provides useful information of the properties and limitation of each ML algorithm in the practice of mental health.