Evaluation of an artificial intelligence-based medical device for diagnosis of autism spectrum disorder

Machine Learning Differentiation of Autism Spectrum Sub-Classifications

PURPOSE

Disorders on the autism spectrum have characteristics that can manifest as difficulties with communication, executive functioning, daily living, and more. These challenges can be mitigated with early identification. However, diagnostic criteria has changed from DSM-IV to DSM-5, which can make diagnosing a disorder on the autism spectrum complex. We evaluated machine learning to classify individuals as having one of three disorders of the autism spectrum under DSM-IV, or as non-spectrum.

METHODS

We employed machine learning to analyze retrospective data from 38,560 individuals. Inputs encompassed clinical, demographic, and assessment data.

RESULTS

The algorithm achieved AUROCs ranging from 0.863 to 0.980. The model correctly classified 80.5% individuals; 12.6% of individuals from this dataset were misclassified with another disorder on the autism spectrum.

CONCLUSION

Machine learning can classify individuals as having a disorder on the autism spectrum or as non-spectrum using minimal data inputs.

Use of Telehealth in Autism Spectrum Disorder Assessment in Children: Evaluation of an Online Diagnostic Protocol Including the Brief Observation of Symptoms of Autism

The COVID-19 pandemic revealed the need to develop the field of remote assessment for autism spectrum disorders (ASD). The purpose of the study was to evaluate an online assessment protocol that includes the Brief Observation of Symptoms of Autism (BOSA). The online protocol consisting of BOSA and the Autism Diagnostic Interview-Revised (ADI-R) was administered by experienced examiners to 29 children with suspected ASD. The participants were then evaluated by clinical psychologists in a standard clinical setting using the Autism Diagnostic Observation Schedule-2 (ADOS-2) and other methods, and the ASD diagnosis was confirmed or ruled out. The results show substantial to moderate inter-rater agreement between the online and face-to-face raters with the value of Cohen's Kappa = 0.66 (P < 0.001); this corresponds with 79.8% agreement. The sensitivity of the protocol was approx. 94.7%, the specificity was 70%, the positive predictive value was 85.7%, and the negative predictive value was 87.5%. Further, direct false positive or false negative diagnostic conclusions based on the online protocol were absent when the possible conclusion of "I cannot decide" was included. The items B9 Showing, B10 Spontaneous Initiation of Joint Attention, B1 Unusual Eye Contact, B3 Facial Expressions Directed to Others, and C2 Imagination/Creativity were shown to be well observable in BOSA when related to ADOS-2 scoring. The results indicate that the protocol consisting of BOSA and ADI-R administered by an experienced examiner is a promising combination of tools for remote autism assessment.

DeepASD: a deep adversarial-regularized graph learning method for ASD diagnosis with multimodal data

Autism Spectrum Disorder (ASD) is a prevalent neurological condition with multiple co-occurring comorbidities that seriously affect mental health. Precisely diagnosis of ASD is crucial to intervention and rehabilitation. A single modality may not fully reflect the complex mechanisms underlying ASD, and combining multiple modalities enables a more comprehensive understanding. Here, we propose, DeepASD, an end-to-end trainable regularized graph learning method for ASD prediction, which incorporates heterogeneous multimodal data and latent inter-patient relationships to better understand the pathogenesis of ASD. DeepASD first learns cross-modal feature representations through a multimodal adversarial-regularized encoder, and then constructs adaptive patient similarity networks by leveraging the representations of each modality. DeepASD exploits inter-patient relationships to boost the ASD diagnosis that is implemented by a classifier compositing of graph neural networks. We apply DeepASD to the benchmarking Autism Brain Imaging Data Exchange (ABIDE) data with four modalities. Experimental results show that the proposed DeepASD outperforms eight state-of-the-art baselines on the benchmarking ABIDE data, showing an improvement of 13.25% in accuracy, 7.69% in AUC-ROC, and 17.10% in specificity. DeepASD holds promise for a more comprehensive insight of the complex mechanisms of ASD, leading to improved diagnosis performance.

Provider perspectives on equity in use of mobile health autism screening tools

LAY ABSTRACT

Families may find information about autism online, and health care and education providers may use online tools to screen for autism. However, we do not know if online autism screening tools are easily used by families and providers. We interviewed primary care and educational providers, asking them to review results from online tools that screen for autism. Providers had concerns about how usable and accessible these tools are for diverse families and suggested changes to make tools easier to use.

Off-body Sleep Analysis for Predicting Adverse Behavior in Individuals with Autism Spectrum Disorder

Poor sleep quality in Autism Spectrum Disorder (ASD) individuals is linked to severe daytime behaviors. This study explores the relationship between a prior night's sleep structure and its predictive power for next-day behavior in ASD individuals. The motion was extracted using a low-cost near-infrared camera in a privacy-preserving way. Over two years, we recorded overnight data from 14 individuals, spanning over 2,000 nights, and tracked challenging daytime behaviors, including aggression, self-injury, and disruption. We developed an ensemble machine learning algorithm to predict next-day behavior in the morning and the afternoon. Our findings indicate that sleep quality is a more reliable predictor of morning behavior than afternoon behavior the next day. The proposed model attained an accuracy of 74% and a F1 score of 0.74 in target-sensitive tasks and 67% accuracy and 0.69 F1 score in target-insensitive tasks. For 7 of the 14, better-than-chance balanced accuracy was obtained (p-value<0.05), with 3 showing significant trends (p-value<0.1). These results suggest off-body, privacy-preserving sleep monitoring as a viable method for predicting next-day adverse behavior in ASD individuals, with the potential for behavioral intervention and enhanced care in social and learning settings.

Home Videos for Remote Assessment in Children with Disabilities: A Scoping Review

Background: Analysis of parent-provided home videos is a mode of technology that can facilitate a telehealth assessment, allowing observation of function in the child's natural home environment. This scoping review investigated areas of use of home videos for functional assessment by health professionals with a pediatric population with disabilities. Methods: Four databases were searched for articles in which parent-provided home videos were employed by health professionals for functional assessment in children with disabilities. Articles published from 2013 to 2023 were included in the review if they met the inclusion criteria, and the data were extracted into an Excel file. Results: After screening 3,019 articles, 30 articles were included in the data extraction. The majority of studies utilized home videos for diagnosis of autism, followed by assessment of motor development in infants. Studies found that using home videos for assessment is feasible and empowers parents. The validity and reliability of various home video platforms were demonstrated. Conclusions: Analysis of home videos can aid in making a timely diagnosis for prompt intervention, and can be used to assess various body functions, interchangeable with a live clinic assessment. It is important to provide parents with clear instructions when using this method. Future studies are necessary to determine whether parent-provided home videos can be utilized by a multidisciplinary team to assess diverse factors, including activity, participation, and the environment, in a variety of populations of children with disabilities, thus extending services beyond the physical borders of the clinic.

Seeing beyond words: Visualizing autism spectrum disorder biomarker insights

Objective

This study employs bibliometric and visual analysis to elucidate global research trends in Autism Spectrum Disorder (ASD) biomarkers, identify critical research focal points, and discuss the potential integration of diverse biomarker modalities for precise ASD assessment.

Methods

A comprehensive bibliometric analysis was conducted using data from the Web of Science Core Collection database until December 31, 2022. Visualization tools, including R, VOSviewer, CiteSpace, and gCLUTO, were utilized to examine collaborative networks, co-citation patterns, and keyword associations among countries, institutions, authors, journals, documents, and keywords.

Results

ASD biomarker research emerged in 2004, accumulating a corpus of 4348 documents by December 31, 2022. The United States, with 1574 publications and an H-index of 213, emerged as the most prolific and influential country. The University of California, Davis, contributed significantly with 346 publications and an H-index of 69, making it the leading institution. Concerning journals, the Journal of Autism and Developmental Disorders, Autism Research, and PLOS ONE were the top three publishers of ASD biomarker-related articles among a total of 1140 academic journals. Co-citation and keyword analyses revealed research hotspots in genetics, imaging, oxidative stress, neuroinflammation, gut microbiota, and eye tracking. Emerging topics included "DNA methylation," "eye tracking," "metabolomics," and "resting-state fMRI."

Conclusion

The field of ASD biomarker research is dynamically evolving. Future endeavors should prioritize individual stratification, methodological standardization, the harmonious integration of biomarker modalities, and longitudinal studies to advance the precision of ASD diagnosis and treatment.

Validation of plasma protein glycation and oxidation biomarkers for the diagnosis of autism

Autism Spectrum Disorder (ASD) is a common neurodevelopmental disorder in children. It is currently diagnosed by behaviour-based assessments made by observation and interview. In 2018 we reported a discovery study of a blood biomarker diagnostic test for ASD based on a combination of four plasma protein glycation and oxidation adducts. The test had 88% accuracy in children 5-12 years old. Herein, we present an international multicenter clinical validation study (N = 478) with application of similar biomarkers to a wider age range of 1.5-12 years old children. Three hundred and eleven children with ASD (247 male, 64 female; age 5.2 ± 3.0 years) and 167 children with typical development (94 male, 73 female; 4.9 ± 2.4 years) were recruited for this study at Sidra Medicine and Hamad Medical Corporation hospitals, Qatar, and Hospital Regional Universitario de Málaga, Spain. For subjects 5-12 years old, the diagnostic algorithm with features, advanced glycation endproducts (AGEs)-Nε-carboxymethyl-lysine (CML), Nω-carboxymethylarginine (CMA) and 3-deoxyglucosone-derived hydroimidazolone (3DG-H), and oxidative damage marker, o,o'-dityrosine (DT), age and gender had accuracy 83% (CI 79 - 89%), sensitivity 94% (CI 90-98%), specificity 67% (CI 57-76%) and area-under-the-curve of receiver operating characteristic plot (AUROC) 0.87 (CI 0.84-0.90). Inclusion of additional plasma protein glycation and oxidation adducts increased the specificity to 74%. An algorithm with 12 plasma protein glycation and oxidation adduct features was optimum for children of 1.5-12 years old: accuracy 74% (CI 70-79%), sensitivity 75% (CI 63-87%), specificity 74% (CI 58-90%) and AUROC 0.79 (CI 0.74-0.84). We conclude that ASD diagnosis may be supported using an algorithm with features of plasma protein CML, CMA, 3DG-H and DT in 5-12 years-old children, and an algorithm with additional features applicable for ASD screening in younger children. ASD severity, as assessed by ADOS-2 score, correlated positively with plasma protein glycation adducts derived from methylglyoxal, hydroimidazolone MG-H1 and Nε(1-carboxyethyl)lysine (CEL). The successful validation herein may indicate that the algorithm modifiable features are mechanistic risk markers linking ASD to increased lipid peroxidation, neuronal plasticity and proteotoxic stress.

Promises, Pitfalls, and Clinical Applications of Artificial Intelligence in Pediatrics

Artificial intelligence (AI) broadly describes a branch of computer science focused on developing machines capable of performing tasks typically associated with human intelligence. Those who connect AI with the world of science fiction may meet its growing rise with hesitancy or outright skepticism. However, AI is becoming increasingly pervasive in our society, from algorithms helping to sift through airline fares to substituting words in emails and SMS text messages based on user choices. Data collection is ongoing and is being leveraged by software platforms to analyze patterns and make predictions across multiple industries. Health care is gradually becoming part of this technological transformation, as advancements in computational power and storage converge with the rapid expansion of digitized medical information. Given the growing and inevitable integration of AI into health care systems, it is our viewpoint that pediatricians urgently require training and orientation to the uses, promises, and pitfalls of AI in medicine. AI is unlikely to solve the full array of complex challenges confronting pediatricians today; however, if used responsibly, it holds great potential to improve many aspects of care for providers, children, and families. Our aim in this viewpoint is to provide clinicians with a targeted introduction to the field of AI in pediatrics, including key promises, pitfalls, and clinical applications, so they can play a more active role in shaping the future impact of AI in medicine.

Digitally Diagnosing Multiple Developmental Delays Using Crowdsourcing Fused With Machine Learning: Protocol for a Human-in-the-Loop Machine Learning Study

BACKGROUND

A considerable number of minors in the United States are diagnosed with developmental or psychiatric conditions, potentially influenced by underdiagnosis factors such as cost, distance, and clinician availability. Despite the potential of digital phenotyping tools with machine learning (ML) approaches to expedite diagnoses and enhance diagnostic services for pediatric psychiatric conditions, existing methods face limitations because they use a limited set of social features for prediction tasks and focus on a single binary prediction, resulting in uncertain accuracies.

OBJECTIVE

This study aims to propose the development of a gamified web system for data collection, followed by a fusion of novel crowdsourcing algorithms with ML behavioral feature extraction approaches to simultaneously predict diagnoses of autism spectrum disorder and attention-deficit/hyperactivity disorder in a precise and specific manner.

METHODS

The proposed pipeline will consist of (1) gamified web applications to curate videos of social interactions adaptively based on the needs of the diagnostic system, (2) behavioral feature extraction techniques consisting of automated ML methods and novel crowdsourcing algorithms, and (3) the development of ML models that classify several conditions simultaneously and that adaptively request additional information based on uncertainties about the data.

RESULTS

A preliminary version of the web interface has been implemented, and a prior feature selection method has highlighted a core set of behavioral features that can be targeted through the proposed gamified approach.

CONCLUSIONS

The prospect for high reward stems from the possibility of creating the first artificial intelligence-powered tool that can identify complex social behaviors well enough to distinguish conditions with nuanced differentiators such as autism spectrum disorder and attention-deficit/hyperactivity disorder.

INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID)

PRR1-10.2196/52205.

Assessment of Autism Spectrum Disorder

Autism Spectrum Disorder (ASD) is a neurodevelopmental condition characterized by challenges in social interaction and communication and the presence of restricted interests and repetitive behaviors. The importance of early detection of ASD and subsequent early intervention is well documented. Efforts have been made over the years to clarify ASD diagnostic criteria and develop predictive, accurate screening tools and evidence-based, standardized diagnostic instruments to aid in the identification of ASD. In this article, we review the most recent changes in ASD diagnostic criteria in the Diagnostic and Statistical Manual of Mental Disorders, Fifth Edition, Text Revision, summarize evidence-based instruments for ASD screening and diagnostic evaluations as well as the assessment of co-occurring conditions in ASD, the impact of COVID-19 on ASD assessment, and directions for future research in the field of ASD assessment.

A comprehensive analysis towards exploring the promises of AI-related approaches in autism research

Autism Spectrum Disorder (ASD) is a neurodevelopmental condition that presents challenges in communication, social interaction, repetitive behaviour, and limited interests. Detecting ASD at an early stage is crucial for timely interventions and an improved quality of life. In recent times, Artificial Intelligence (AI) has been increasingly used in ASD research. The rise in ASD diagnoses is due to the growing number of ASD cases and the recognition of the importance of early detection, which leads to better symptom management. This study explores the potential of AI in identifying early indicators of autism, aligning with the United Nations Sustainable Development Goals (SDGs) of Good Health and Well-being (Goal 3) and Peace, Justice, and Strong Institutions (Goal 16). The paper aims to provide a comprehensive overview of the current state-of-the-art AI-based autism classification by reviewing recent publications from the last decade. It covers various modalities such as Eye gaze, Facial Expression, Motor skill, MRI/fMRI, and EEG, and multi-modal approaches primarily grouped into behavioural and biological markers. The paper presents a timeline spanning from the history of ASD to recent developments in the field of AI. Additionally, the paper provides a category-wise detailed analysis of the AI-based application in ASD with a diagrammatic summarization to convey a holistic summary of different modalities. It also reports on the successes and challenges of applying AI for ASD detection while providing publicly available datasets. The paper paves the way for future scope and directions, providing a complete and systematic overview for researchers in the field of ASD.

Challenging the Chatbot: An Assessment of ChatGPT's Diagnoses and Recommendations for DBP Case Studies

OBJECTIVE

Chat Generative Pretrained Transformer-3.5 (ChatGPT) is a publicly available and free artificial intelligence chatbot that logs billions of visits per day; parents may rely on such tools for developmental and behavioral medical consultations. The objective of this study was to determine how ChatGPT evaluates developmental and behavioral pediatrics (DBP) case studies and makes recommendations and diagnoses.

METHODS

ChatGPT was asked to list treatment recommendations and a diagnosis for each of 97 DBP case studies. A panel of 3 DBP physicians evaluated ChatGPT's diagnostic accuracy and scored treatment recommendations on accuracy (5-point Likert scale) and completeness (3-point Likert scale). Physicians also assessed whether ChatGPT's treatment plan correctly addressed cultural and ethical issues for relevant cases. Scores were analyzed using Python, and descriptive statistics were computed.

RESULTS

The DBP panel agreed with ChatGPT's diagnosis for 66.2% of the case reports. The mean accuracy score of ChatGPT's treatment plan was deemed by physicians to be 4.6 (between entirely correct and more correct than incorrect), and the mean completeness was 2.6 (between complete and adequate). Physicians agreed that ChatGPT addressed relevant cultural issues in 10 out of the 11 appropriate cases and the ethical issues in the single ethical case.

CONCLUSION

While ChatGPT can generate a comprehensive and adequate list of recommendations, the diagnosis accuracy rate is still low. Physicians must advise caution to patients when using such online sources.

Neuroimaging genetics approaches to identify new biomarkers for the early diagnosis of autism spectrum disorder

Autism-spectrum disorders (ASDs) are developmental disabilities that manifest in early childhood and are characterized by qualitative abnormalities in social behaviors, communication skills, and restrictive or repetitive behaviors. To explore the neurobiological mechanisms in ASD, extensive research has been done to identify potential diagnostic biomarkers through a neuroimaging genetics approach. Neuroimaging genetics helps to identify ASD-risk genes that contribute to structural and functional variations in brain circuitry and validate biological changes by elucidating the mechanisms and pathways that confer genetic risk. Integrating artificial intelligence models with neuroimaging data lays the groundwork for accurate diagnosis and facilitates the identification of early diagnostic biomarkers for ASD. This review discusses the significance of neuroimaging genetics approaches to gaining a better understanding of the perturbed neurochemical system and molecular pathways in ASD and how these approaches can detect structural, functional, and metabolic changes and lead to the discovery of novel biomarkers for the early diagnosis of ASD.

App Characteristics and Accuracy Metrics of Available Digital Biomarkers for Autism: Scoping Review

BACKGROUND

Diagnostic delays in autism are common, with the time to diagnosis being up to 3 years from the onset of symptoms. Such delays have a proven detrimental effect on individuals and families going through the process. Digital health products, such as mobile apps, can help close this gap due to their scalability and ease of access. Further, mobile apps offer the opportunity to make the diagnostic process faster and more accurate by providing additional and timely information to clinicians undergoing autism assessments.

OBJECTIVE

The aim of this scoping review was to synthesize the available evidence about digital biomarker tools to aid clinicians, researchers in the autism field, and end users in making decisions as to their adoption within clinical and research settings.

METHODS

We conducted a structured literature search on databases and search engines to identify peer-reviewed studies and regulatory submissions that describe app characteristics, validation study details, and accuracy and validity metrics of commercial and research digital biomarker apps aimed at aiding the diagnosis of autism.

RESULTS

We identified 4 studies evaluating 4 products: 1 commercial and 3 research apps. The accuracy of the identified apps varied between 28% and 80.6%. Sensitivity and specificity also varied, ranging from 51.6% to 81.6% and 18.5% to 80.5%, respectively. Positive predictive value ranged from 20.3% to 76.6%, and negative predictive value fluctuated between 48.7% and 97.4%. Further, we found a lack of details around participants' demographics and, where these were reported, important imbalances in sex and ethnicity in the studies evaluating such products. Finally, evaluation methods as well as accuracy and validity metrics of available tools were not clearly reported in some cases and varied greatly across studies. Different comparators were also used, with some studies validating their tools against the Diagnostic and Statistical Manual of Mental Disorders criteria and others through self-reported measures. Further, while in most cases, 2 classes were used for algorithm validation purposes, 1 of the studies reported a third category (indeterminate). These discrepancies substantially impact the comparability and generalizability of the results, thus highlighting the need for standardized validation processes and the reporting of findings.

CONCLUSIONS

Despite their popularity, systematic evaluations and syntheses of the current state of the art of digital health products are lacking. Standardized and transparent evaluations of digital health tools in diverse populations are needed to assess their real-world usability and validity, as well as help researchers, clinicians, and end users safely adopt novel tools within clinical and research practices.

Paisley: Preliminary validation of a novel app-based e-Screener for ASD in children 18-36 months

The purpose of this study was to assess the validity of an autism e-screener, Paisley, when utilized in a clinical research setting via a tablet application. The Paisley application used a series of play-based activities, all of which incorporated varying aspects of the ASD-PEDS. Participants included children (18-36 months; n = 198) referred for evaluation of autism spectrum disorder (ASD) and community providers (n = 66) with differing levels of familiarity with ASD. Community providers administered the Paisley application to children who then completed a comprehensive psychological evaluation. Based on comprehensive evaluation, 75% of children met diagnostic criteria for ASD. Paisley scores were significantly higher for children diagnosed with ASD (15.06) versus those not diagnosed (9.34). The newly determined cutoff ASD-PEDS cutoff score of 13 had significantly higher specificity and positive predictive value than the originally proposed cutoff of 11. Results support the use of Paisley by community providers to identify autism risk in toddlers. Limitations and strengths of the work, as well as opportunities for future clinical validation, are described.

Equivalence of the autism spectrum disorders diagnostics in children in telemedicine and face-to-face consultations: a literature review

BACKGROUND

The use of remote forms of mental health care has become widespread during the period of epidemiological restrictions due to the COVID-19 pandemic. Methodological and organizational issues remain insufficiently developed, including the level of equivalence of the use of telemedicine technologies in the diagnosis of autistic spectrum disorders.

AIM

Study of the equivalence of diagnostic tools in the framework of telemedicine and face-to-face consultations in children with autistic spectrum disorders according to modern scientific literature.

METHODS

A descriptive review of scientific studies published between January 2017 and May 2023 was carried out. The papers presented in the electronic databases PubMed, Web of Science, and eLibrary were analyzed. Descriptive analysis was used to summarize the obtained data.

RESULTS

The conducted analysis convincingly indicates sufficient equivalence of remote tools used in different countries for level I screening, assessment scales, and structured procedures for diagnosing autistic spectrum disorders with a high level of specificity from 60.0 to 94.4%, sensitivity from 75 dog 98.4%, and satisfaction of patients and their legal representatives.

CONCLUSION

The widespread use of validated telemedicine diagnostic systems in clinical practice contributes to the early detection of autistic spectrum disorders, increasing the timeliness and effectiveness of medical, corrective psychological, pedagogical, and habilitation interventions.

Diagnostic Accuracy of Primary Care Clinicians Across a Statewide System of Autism Evaluation

OBJECTIVES

To evaluate the diagnostic accuracy of the Early Autism Evaluation (EAE) Hub system, a statewide network that provides specialized training and collaborative support to community primary care providers in the diagnosis of young children at risk for autism spectrum disorder (ASD).

METHODS

EAE Hub clinicians referred children, aged 14 to 48 months, to this prospective diagnostic study for blinded follow-up expert evaluation including assessment of developmental level, adaptive behavior, and ASD symptom severity. The primary outcome was agreement on categorical ASD diagnosis between EAE Hub clinician (index diagnosis) and ASD expert (reference standard).

RESULTS

Among 126 children (mean age: 2.6 years; 77% male; 14% Latinx; 66% non-Latinx white), 82% (n = 103) had consistent ASD outcomes between the index and reference evaluation. Sensitivity was 81.5%, specificity was 82.4%, positive predictive value was 92.6%, and negative predictive value was 62.2%. There was no difference in accuracy by EAE Hub clinician or site. Across measures of development, there were significant differences between true positive and false negative (FN) cases (all Ps < .001; Cohen's d = 1.1-1.4), with true positive cases evidencing greater impairment.

CONCLUSIONS

Community-based primary care clinicians who receive specialty training can make accurate ASD diagnoses in most cases. Diagnostic disagreements were predominately FN cases in which EAE Hub clinicians had difficulty differentiating ASD and global developmental delay. FN cases were associated with a differential diagnostic and phenotypic profile. This research has significant implications for the development of future population health solutions that address ASD diagnostic delays.

Review of Machine Learning and Artificial Intelligence (ML/AI) for the Pediatric Neurologist

Artificial intelligence (AI) and a popular branch of AI known as machine learning (ML) are increasingly being utilized in medicine and to inform medical research. This review provides an overview of AI and ML (AI/ML), including definitions of common terms. We discuss the history of AI and provide instances of how AI/ML can be applied to pediatric neurology. Examples include imaging in neuro-oncology, autism diagnosis, diagnosis from charts, epilepsy, cerebral palsy, and neonatal neurology. Topics such as supervised learning, unsupervised learning, and reinforcement learning are discussed.

Machine learning determination of applied behavioral analysis treatment plan type

BACKGROUND

Applied behavioral analysis (ABA) is regarded as the gold standard treatment for autism spectrum disorder (ASD) and has the potential to improve outcomes for patients with ASD. It can be delivered at different intensities, which are classified as comprehensive or focused treatment approaches. Comprehensive ABA targets multiple developmental domains and involves 20-40 h/week of treatment. Focused ABA targets individual behaviors and typically involves 10-20 h/week of treatment. Determining the appropriate treatment intensity involves patient assessment by trained therapists, however, the final determination is highly subjective and lacks a standardized approach. In our study, we examined the ability of a machine learning (ML) prediction model to classify which treatment intensity would be most suited individually for patients with ASD who are undergoing ABA treatment.

METHODS

Retrospective data from 359 patients diagnosed with ASD were analyzed and included in the training and testing of an ML model for predicting comprehensive or focused treatment for individuals undergoing ABA treatment. Data inputs included demographics, schooling, behavior, skills, and patient goals. A gradient-boosted tree ensemble method, XGBoost, was used to develop the prediction model, which was then compared against a standard of care comparator encompassing features specified by the Behavior Analyst Certification Board treatment guidelines. Prediction model performance was assessed via area under the receiver-operating characteristic curve (AUROC), sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV).

RESULTS

The prediction model achieved excellent performance for classifying patients in the comprehensive versus focused treatment groups (AUROC: 0.895; 95% CI 0.811-0.962) and outperformed the standard of care comparator (AUROC 0.767; 95% CI 0.629-0.891). The prediction model also achieved sensitivity of 0.789, specificity of 0.808, PPV of 0.6, and NPV of 0.913. Out of 71 patients whose data were employed to test the prediction model, only 14 misclassifications occurred. A majority of misclassifications (n = 10) indicated comprehensive ABA treatment for patients that had focused ABA treatment as the ground truth, therefore still providing a therapeutic benefit. The three most important features contributing to the model's predictions were bathing ability, age, and hours per week of past ABA treatment.

CONCLUSION

This research demonstrates that the ML prediction model performs well to classify appropriate ABA treatment plan intensity using readily available patient data. This may aid with standardizing the process for determining appropriate ABA treatments, which can facilitate initiation of the most appropriate treatment intensity for patients with ASD and improve resource allocation.

Feature Signature Discovery for Autism Detection: An Automated Machine Learning Based Feature Ranking Framework

Autism spectrum disorder is the most used umbrella term for a myriad of neuro-degenerative/developmental conditions typified by inappropriate social behavior, lack of communication/comprehension skills, and restricted mental and emotional maturity. The intriguing factor of this disorder is attributed to the fact that it can be detected only by close monitoring of developmental milestones after childbirth. Moreover, the exact causes for the occurrence of this neurodevelopmental condition are still unknown. Besides, autism is prevalent across individuals irrespective of ethnicity, genetic/familial history, and economic/educational background. Although research suggests that autism is genetic in nature and early detection of this disorder can greatly enhance the independent lifestyle and societal adaptability of affected individuals, there is still a great dearth of information to support the statement of proven facts and figures. This research work places emphasis on the application of automated machine learning incorporated with feature ranking techniques to generate significant feature signatures for the early detection of autism. Publicly available datasets based on the Q-chat scores of individuals across diverse age groups-toddlers, children, adolescents, and adults have been employed in this study. A machine learning framework based on automated hyperparameter optimization is proposed in this work to rank the potential nonclinical markers for autism. Moreover, this study aimed at ranking the AutoML models based on Mathew's correlation coefficient and balanced accuracy via which nonclinical markers were identified from these datasets. Besides, the feature signatures and their significance in distinguishing between classes are being reported for the first time in autism detection. The proposed framework yielded ∼90% MCC and ∼95% balanced accuracy across all four age groups of autism datasets. Deep learning approaches have yielded a maximum of 92.7% accuracy on the same datasets but are limited in their ability to extract significant markers, have not reported on MCC for unbalanced data, and cannot adapt automatically to new data entries. However, AutoML approaches are more flexible, easier to implement, and provide automated optimization, thereby yielding the highest accuracy with minimal user intervention.

Racial and Ethnic Disparities in Geographic Access to Autism Resources Across the US

Importance

While research has identified racial and ethnic disparities in access to autism services, the size, extent, and specific locations of these access gaps have not yet been characterized on a national scale. Mapping comprehensive national listings of autism health care services together with the prevalence of autistic children of various races and ethnicities and evaluating geographic regions defined by localized commuting patterns may help to identify areas within the US where families who belong to minoritized racial and ethnic groups have disproportionally lower access to services.

Objective

To evaluate differences in access to autism health care services among autistic children of various races and ethnicities within precisely defined geographic regions encompassing all serviceable areas within the US.

Design, Setting, and Participants

This population-based cross-sectional study was conducted from October 5, 2021, to June 3, 2022, and involved 530 965 autistic children in kindergarten through grade 12. Core-based statistical areas (CBSAs; defined as areas containing a city and its surrounding commuter region), the Civil Rights Data Collection (CRDC) data set, and 51 071 autism resources (collected from October 1, 2015, to December 18, 2022) geographically distributed into 912 CBSAs were combined and analyzed to understand variation in access to autism health care services among autistic children of different races and ethnicities. Six racial and ethnic categories (American Indian or Alaska Native, Asian, Black or African American, Hispanic or Latino, Native Hawaiian or other Pacific Islander, and White) assigned by the US Department of Education were included in the analysis.

Main Outcomes and Measures

A regularized least-squares regression analysis was used to measure differences in nationwide resource allocation between racial and ethnic groups. The number of autism resources allocated per autistic child was estimated based on the child's racial and ethnic group. To evaluate how the CBSA population size may have altered the results, the least-squares regression analysis was run on CBSAs divided into metropolitan (>50 000 inhabitants) and micropolitan (10 000-50 000 inhabitants) groups. A Mann-Whitney U test was used to compare the model estimated ratio of autism resources to autistic children among specific racial and ethnic groups comprising the proportions of autistic children in each CBSA.

Results

Among 530 965 autistic children aged 5 to 18 years, 83.9% were male and 16.1% were female; 0.7% of children were American Indian or Alaska Native, 5.9% were Asian, 14.3% were Black or African American, 22.9% were Hispanic or Latino, 0.2% were Native Hawaiian or other Pacific Islander, 51.7% were White, and 4.2% were of 2 or more races and/or ethnicities. At a national scale, American Indian or Alaska Native autistic children (β = 0; 95% CI, 0-0; P = .01) and Hispanic autistic children (β = 0.02; 95% CI, 0-0.06; P = .02) had significant disparities in access to autism resources in comparison with White autistic children. When evaluating the proportion of autistic children in each racial and ethnic group, areas in which Black autistic children (>50% of the population: β = 0.05; <50% of the population: β = 0.07; P = .002) or Hispanic autistic children (>50% of the population: β = 0.04; <50% of the population: β = 0.07; P < .001) comprised greater than 50% of the total population of autistic children had significantly fewer resources than areas in which Black or Hispanic autistic children comprised less than 50% of the total population. Comparing metropolitan vs micropolitan CBSAs revealed that in micropolitan CBSAs, Black autistic children (β = 0; 95% CI, 0-0; P < .001) and Hispanic autistic children (β = 0; 95% CI, 0-0.02; P < .001) had the greatest disparities in access to autism resources compared with White autistic children. In metropolitan CBSAs, American Indian or Alaska Native autistic children (β = 0; 95% CI, 0-0; P = .005) and Hispanic autistic children (β = 0.01; 95% CI, 0-0.06; P = .02) had the greatest disparities compared with White autistic children.

Conclusions and Relevance

In this study, autistic children from several minoritized racial and ethnic groups, including Black and Hispanic autistic children, had access to significantly fewer autism resources than White autistic children in the US. This study pinpointed the specific geographic regions with the greatest disparities, where increases in the number and types of treatment options are warranted. These findings suggest that a prioritized response strategy to address these racial and ethnic disparities is needed.

A systematic review of telehealth screening, assessment, and diagnosis of autism spectrum disorder

There is a significant delay between parents having concerns and receiving a formal assessment and Autism Spectrum Disorder (ASD) diagnosis. Telemedicine could be an effective alternative that shortens the waiting time for parents and primary health providers in ASD screening and diagnosis. We conducted a systematic review examining the uses of telemedicine technology for ASD screening, assessment, or diagnostic purposes and to what extent sample characteristics and psychometric properties were reported. This study searched four databases from 2000 to 2022 and obtained 26 studies that met the inclusion criteria. The 17 applications used in these 26 studies were divided into three categories based on their purpose: screening, diagnostic, and assessment. The results described the data extracted, including study characteristics, applied methods, indicators seen, and psychometric properties. Among the 15 applications with psychometric properties reported, the sensitivity ranged from 0.70 to 1, and the specificity ranged from 0.38 to 1. The present study highlights the strengths and weaknesses of current telemedicine approaches and provides a basis for future research. More rigorous empirical studies with larger sample sizes are needed to understand the feasibility, strengths, and limitations of telehealth technologies for screening, assessing, and diagnosing ASD.

Feasibility and impact of integrating an artificial intelligence-based autism spectrum disorder diagnosis aid into the primary care ECHO Autism STAT Model: protocol for a prospective observational study (Preprint)

Background

The Extension for Community Health Outcomes (ECHO) Autism Program trains clinicians to screen, diagnose, and care for children with autism spectrum disorder (ASD) in primary care settings. This study will assess the feasibility and impact of integrating an artificial intelligence (AI)–based ASD diagnosis aid (the device) into the existing ECHO Autism Screening Tool for Autism in Toddlers and Young Children (STAT) diagnosis model. The prescription-only Software as a Medical Device, designed for use in children aged 18 to 72 months at risk for developmental delay, produces ASD diagnostic recommendations after analyzing behavioral features from 3 distinct inputs: a caregiver questionnaire, 2 short home videos analyzed by trained video analysts, and a health care provider questionnaire. The device is not a stand-alone diagnostic and should be used in conjunction with clinical judgment.

Objective

This study aims to assess the feasibility and impact of integrating an AI-based ASD diagnosis aid into the ECHO Autism STAT diagnosis model. The time from initial ECHO Autism clinician concern to ASD diagnosis is the primary end point. Secondary end points include the time from initial caregiver concern to ASD diagnosis, time from diagnosis to treatment initiation, and clinician and caregiver experience of device use as part of the ASD diagnostic journey.

Methods

Research participants for this prospective observational study will be patients suspected of having ASD (aged 18-72 months) and their caregivers and up to 15 trained ECHO Autism clinicians recruited by the ECHO Autism Communities research team from across rural and suburban areas of the United States. Clinicians will provide routine clinical care and conduct best practice ECHO Autism diagnostic evaluations in addition to prescribing the device. Outcome data will be collected via a combination of electronic questionnaires, reviews of standard clinical care records, and analysis of device outputs. The expected study duration is no more than 12 months. The study was approved by the institutional review board of the University of Missouri-Columbia (institutional review board–assigned project number 2075722).

Results

Participant recruitment began in April 2022. As of June 2022, a total of 41 participants have been enrolled.

Conclusions

This prospective observational study will be the first to evaluate the use of a novel AI-based ASD diagnosis aid as part of a real-world primary care diagnostic pathway. If device integration into primary care proves feasible and efficacious, prolonged delays between the first ASD concern and eventual diagnosis may be reduced. Streamlining primary care ASD diagnosis could potentially reduce the strain on specialty services and allow a greater proportion of children to commence early intervention during a critical neurodevelopmental window.

Trial Registration

ClinicalTrials.gov NCT05223374; https://clinicaltrials.gov/ct2/show/NCT05223374

International Registered Report Identifier (IRRID)

PRR1-10.2196/37576