The prevalence of autism spectrum disorder (ASD) among children in the United States has risen dramatically over the past two decades. In 2022, an estimated 32.2 out of every 1,000 8-year-old children were identified with ASD, marking a nearly fivefold increase from the rate of 6.7 per 1,000 children in 2000. This significant upward trend underscores the growing importance of understanding and addressing ASD in American society. Gender disparities in autism diagnosis The increase in ASD prevalence is not uniform across genders. From 2016 to 2019, male children were nearly four times more likely to be diagnosed with ASD than their female counterparts. Approximately 4.8 percent of boys aged 3 to 17 years had received an ASD diagnosis at some point in their lives, compared to only 1.3 percent of girls in the same age group. This substantial gender gap highlights the need for further research into potential biological and social factors influencing ASD diagnosis rates. Racial and ethnic variations in autism prevalence Autism prevalence also varies across racial and ethnic groups. Data from 2016 to 2019 show that non-Hispanic white children aged 3 to 17 years had an ASD prevalence of 2.9 percent, while around 3.5 percent of Hispanic children had ASD. While this statistic provides insight, it is essential to consider potential disparities in diagnosis and access to services among different racial and ethnic communities. Further research and targeted interventions may be necessary to ensure equitable identification and support for children with ASD across all populations.

These statistics present a group of measures on waiting times for autism spectrum disorder diagnostic pathways, based on the time between a referral for suspected autism and the first care contact associated with that referral. There are also multiple breakdowns based on the progression and outcomes of those referrals. Each of these measures contributes to an overall picture of waiting times for diagnostic pathways. The approach is outlined in the methodology section of this publication.

The prevalence rate of autism spectrum disorder among children aged eight years in the state Georgia was estimated to be around **** per 1,000 children. Autism spectrum disorder is a developmental disability characterized by deficits in social communication and interaction as well as repetitive behavior, interest, or activity patterns. Autism spectrum disorder in childrenAmong 14 U.S. states with areas that were monitored for autism spectrum disorder in 2022, California had the highest prevalence rates of autism spectrum disorder (ASD) among children aged eight years. In 2022, California’s prevalence rate was estimated to be **** cases per 1,000 children, while the rate was about **** cases per 1,000 children in Indiana. ASD is more common among male than female children, with an estimated ** male cases per 1,000 children and ** female cases per 1,000 children in California in 2022. Limitations in a child with autism can vary between individuals and develop over time. In California, the median age of diagnosis among children with an ASD diagnosis with an IQ greater than 70 was ********* of age, in comparison to ********* for children with an ASD diagnosis and an IQ less than or equal to 70, indicating a co-occurring intellectual disability. The prevalence of ASD has increased significantly since the late 1960s by about ** to ** times. Many studies suggest that this is due to improved awareness and recognition, as well as diagnostic capabilities. Autism is likely caused by a combination of genetics and environmental factors, where people with ASD may have abnormal levels of brain serotonin, which could disrupt early brain development.

This data table provides a collection of information from peer-reviewed autism prevalence studies. Information reported from each study includes the autism prevalence estimate and additional study characteristics (e.g., case ascertainment and criteria). A PubMed search was conducted to identify studies published at any time through September 2020 using the search terms: autism (title/abstract) OR autistic (title/abstract) AND prevalence (title/abstract). Data were abstracted and included if the study fulfilled the following criteria: • The study was published in English; • The study produced at least one autism prevalence estimate; and • The study was population-based (any age range) within a defined geographic area.

Children aged eight years with an autism spectrum disorder diagnosis and an IQ of less than or equal to 70, indicating a co-occurring intellectual disability, had a median initial diagnosis age of ********* in the state of Georgia. Autism spectrum disorder is a developmental disability characterized by deficits in social communication and interaction as well as repetitive behavior, interest, or activity patterns. This statistic shows the median age at the first autism diagnosis among U.S. children aged eight years in selected U.S. states by subtype in 2022.

BackgroundThe standard approaches to diagnosing autism spectrum disorder (ASD) evaluate between 20 and 100 behaviors and take several hours to complete. This has in part contributed to long wait times for a diagnosis and subsequent delays in access to therapy. We hypothesize that the use of machine learning analysis on home video can speed the diagnosis without compromising accuracy. We have analyzed item-level records from 2 standard diagnostic instruments to construct machine learning classifiers optimized for sparsity, interpretability, and accuracy. In the present study, we prospectively test whether the features from these optimized models can be extracted by blinded nonexpert raters from 3-minute home videos of children with and without ASD to arrive at a rapid and accurate machine learning autism classification.Methods and findingsWe created a mobile web portal for video raters to assess 30 behavioral features (e.g., eye contact, social smile) that are used by 8 independent machine learning models for identifying ASD, each with >94% accuracy in cross-validation testing and subsequent independent validation from previous work. We then collected 116 short home videos of children with autism (mean age = 4 years 10 months, SD = 2 years 3 months) and 46 videos of typically developing children (mean age = 2 years 11 months, SD = 1 year 2 months). Three raters blind to the diagnosis independently measured each of the 30 features from the 8 models, with a median time to completion of 4 minutes. Although several models (consisting of alternating decision trees, support vector machine [SVM], logistic regression (LR), radial kernel, and linear SVM) performed well, a sparse 5-feature LR classifier (LR5) yielded the highest accuracy (area under the curve [AUC]: 92% [95% CI 88%–97%]) across all ages tested. We used a prospectively collected independent validation set of 66 videos (33 ASD and 33 non-ASD) and 3 independent rater measurements to validate the outcome, achieving lower but comparable accuracy (AUC: 89% [95% CI 81%–95%]). Finally, we applied LR to the 162-video-feature matrix to construct an 8-feature model, which achieved 0.93 AUC (95% CI 0.90–0.97) on the held-out test set and 0.86 on the validation set of 66 videos. Validation on children with an existing diagnosis limited the ability to generalize the performance to undiagnosed populations.ConclusionsThese results support the hypothesis that feature tagging of home videos for machine learning classification of autism can yield accurate outcomes in short time frames, using mobile devices. Further work will be needed to confirm that this approach can accelerate autism diagnosis at scale.

Abstract

Improve Autism Screening by creating predicting the likelihood of having this condition.

About this dataset

What is Autism

Autism, or autism spectrum disorder (ASD), refers to a broad range of conditions characterized by challenges with social skills, repetitive behaviors, speech and nonverbal communication.

Causes and Challenges

It is mostly influenced by a combination of genetic and environmental factors. Because autism is a spectrum disorder, each person with autism has a distinct set of strengths and challenges. The ways in which people with autism learn, think and problem-solve can range from highly skilled to severely challenged. Research has made clear that high quality early intervention can improve learning, communication and social skills, as well as underlying brain development. Yet the diagnostic process can take several years.

The Role of Machine Learning

This dataset is composed of survey results for more than 700 people who filled an app form. There are labels portraying whether the person received a diagnosis of autism, allowing machine learning models to predict the likelihood of having autism, therefore allowing healthcare professionals prioritize their resources.

How to use

• Predict the likelihood of a person having autism using survey and demographic variables.
• Explore Autism across Gender, Age, and other variables

Acknowledgements

If you this dataset in your research, please credit the authors.

Citations

• Tabtah, F. (2017). Autism Spectrum Disorder Screening: Machine Learning Adaptation and DSM-5 Fulfillment. Proceedings of the 1st International Conference on Medical and Health Informatics 2017, pp.1-6. Taichung City, Taiwan, ACM.
• Thabtah, F. (2017). Machine Learning in Autistic Spectrum Disorder Behavioural Research: A Review. To Appear in Informatics for Health and Social Care Journal. December, 2017

License

Public Domain

Splash banner

Photo by Nathan Anderson on Unsplash

Splash icon

Icons made by Smashicons from www.flaticon.com.

More Information about Autism

More Datasets

According to a survey carried out in the United States in 2023, ** percent of those aged between 45 and 64 years of age believed the diagnosis rate for autism was increasing. Furthermore, more than half of over ** year olds also believed autism diagnoses were increasing.

Background: Diagnosis of autism spectrum disorder (ASD) can be made early in childhood, but also later in adolescence or adulthood. In the latter cases, concerns about an individual's behavior typically lead to consultation of a mental health professional (MHP). As part of the initial clinical examination by the MHP, a clinical diagnostic interview is performed, in order to obtain the patient's history, and may lead to the hypothesis of ASD. We were here interested to study family and developmental history as key parts of the patient's history. The aim of the study was to investigate empirical differences between adolescents with ASD and adolescent control persons in family and developmental history.Method: Clinical diagnostic interview items addressing family and developmental history were adopted from their regular use at several university hospitals and in leading textbooks. Parents of male adolescents with normal intelligence and an ASD diagnosis (n = 67) and parents of male adolescents without psychiatric diagnosis (n = 51) between the age of 12 and 17 years were investigated. Data were operationalized into three categories: 0 = normal behavior, 1 = minor pathological behavior, and 2 = major pathological behavior. Differences were analyzed by multiple t-test of two-way ANOVA.Results: Adolescents with ASD expressed a profile of items significantly differing from control persons. Comparison of significant items with the empirical ASD literature indicated robust accordance.Conclusions: Our findings support the importance and feasibility of the clinical diagnostic interview of family and developmental history for initiation of the diagnostic process of ASD in adolescents.

National Database for Autism Research (NDAR) is an extensible, scalable informatics platform for autism spectrum disorder-relevant data at all levels of biological and behavioral organization (molecules, genes, neural tissue, behavioral, social and environmental interactions) and for all data types (text, numeric, image, time series, etc.). NDAR was developed to share data across the entire ASD field and to facilitate collaboration across laboratories, as well as interconnectivity with other informatics platforms. NDAR Homepage: http://ndar.nih.gov/

This statistic shows the percentage of children aged 3 to 17 years ever diagnosed with autism spectrum disorder in the U.S. in 2014, by region. In that year, it was estimated that **** percent of children ever diagnosed with autism spectrum disorder belonged to the southern region of the United States.

The global market for the diagnosis and treatment of Autism Spectrum Disorder (ASD) is experiencing robust growth, driven by a confluence of increasing awareness, improved diagnostic tools, and advancements in therapeutic interventions. With an estimated market size of approximately USD 6,500 million in 2025, the sector is projected to expand at a Compound Annual Growth Rate (CAGR) of around 7.5% through 2033. This significant expansion is fueled by rising prevalence rates, greater parental advocacy, and a growing emphasis on early intervention, which are critical for improving outcomes for individuals with ASD. The market is also benefiting from increased government funding for research and support services, as well as a more comprehensive understanding of the diverse needs of the ASD population. Furthermore, the development of innovative diagnostic technologies and personalized treatment approaches, including behavioral therapies, pharmacotherapy, and emerging gene-based therapies, are key drivers contributing to the market's upward trajectory. The increasing demand for specialized care across various settings, from hospitals and clinics to home-based services, underscores the comprehensive nature of the market's evolution. The market landscape for ASD diagnosis and treatment is characterized by a dynamic interplay of established pharmaceutical giants and specialized biotechnology firms. Key players like Otsuka, AstraZeneca, Pfizer, and Eli Lilly are actively involved in developing and marketing pharmacological treatments, while companies such as Behavior Analysis, SynapDx, and Autism Therapeutics are at the forefront of diagnostic tools and specialized therapies. The market is segmented by application (hospitals, clinics, and others) and by type (adults and children), with the pediatric segment currently dominating due to the emphasis on early diagnosis and intervention. Geographically, North America, particularly the United States, leads the market, owing to high prevalence rates, advanced healthcare infrastructure, and substantial investment in research and development. Europe also holds a significant share, driven by strong healthcare systems and increasing awareness. The Asia Pacific region is poised for substantial growth, fueled by a rising population, improving healthcare access, and growing diagnostic capabilities. Despite the promising outlook, challenges such as diagnostic delays in certain regions, limited access to specialized therapies in underserved communities, and the high cost of some advanced treatments present ongoing hurdles that the industry is working to address. This report provides an in-depth analysis of the global market for the diagnosis and treatment of Autism Spectrum Disorder (ASD). Spanning a study period from 2019 to 2033, with a base and estimated year of 2025, this research offers valuable insights into market dynamics, key players, and future trends. The report is designed for stakeholders seeking a granular understanding of this rapidly evolving sector, with an estimated market size of over $20,000 million by 2025.

Functional near-infrared spectroscopic brain imaging data were collected from a Shimadzu LABNIRS during a face to face interaction task from participants that were categorized as either TD or ASD by a trained clinician. Univaraite and Multivariate analyses were used to determine classification of participants as TD or ASD using only FNIRS responses. Typical GLM methods were used for univariate classification. For multivariate classification, an SVM classifier was used to predict ADOS values for the ASD group and categorize all participants as either TD or ASD.

Autism is a relatively common neurodevelopmental difference with considerable phenotypic heterogeneity impacting cognitive, sensory, and social processing, and often co-occurs with other conditions. Therefore, there is not a one-size-fits-all clinical support pathway for autistic individuals following diagnosis. DNA sequencing technology has enabled the discovery of genes causative of, or associated with, autism. Unsurprisingly, genetic heterogeneity goes hand-in-hand with the phenotypic heterogeneity for this condition; with causative genetic variation ranging from single base pair changes to complex chromosomal rearrangements in more than 100 different genes. This study captures a snapshot (201 individuals) of the autistic population (both clinically referred and self-referred) in Aotearoa New Zealand and documents a decade’s research effort to refine diagnosis using a flexible and customised genome-wide sequencing approach. The diagnostic yield in this phenotypically disparate cohort was 12.9%, with an additional 15.9% of individuals harbouring ‘likely causal’ variants, providing the groundwork to tailor clinical, social, and educational care. Importantly, this study reveals the diagnostic utility of customised genetic screening for autism across a phenotypically diverse autistic population.

This statistic shows the percentage of children aged 3 to 17 years ever diagnosed with autism spectrum disorder in the U.S. in 2014, by ethnicity. In that year, it was estimated that **** percent of the children ever diagnosed with autism spectrum disorder were Non-Hispanic white.

Autistic Spectrum Disorder (ASD) is a neurodevelopmental condition associated with significant healthcare costs, and early diagnosis can significantly reduce these. Unfortunately, waiting times for an ASD diagnosis are lengthy and procedures are not cost effective. The economic impact of autism and the increase in the number of ASD cases across the world reveals an urgent need for the development of easily implemented and effective screening methods. Therefore, a time-efficient and accessible ASD screening is imminent to help health professionals and inform individuals whether they should pursue formal clinical diagnosis. The rapid growth in the number of ASD cases worldwide necessitates datasets related to behaviour traits. However, such datasets are rare making it difficult to perform thorough analyses to improve the efficiency, sensitivity, specificity and predictive accuracy of the ASD screening process. Presently, very limited autism datasets associated with clinical or screening are available and most of them are genetic in nature. Hence, we propose a new dataset related to autism screening of toddlers that contained influential features to be utilised for further analysis especially in determining autistic traits and improving the classification of ASD cases. In this dataset, we record ten behavioural features plus other individuals characteristics that have proved to be effective in detecting the ASD cases from controls in behaviour science.

A1-A10: Items within Q-Chat-10 in which questions possible answers : “Always, Usually, Sometimes, Rarly & Never” items’ values are mapped to “1” or “0” in the dataset. For questions 1-9 (A1-A9) in Q-chat-10, if the respose was Sometimes / Rarly / Never “1” is assigned to the question (A1-A9). However, for question 10 (A10), if the respose was Always / Usually / Sometimes then “1” is assigned to that question. If the user obtained More than 3 Add points together for all ten questions. If your child scores more than 3 (Q-chat-10- score) then there is a potential ASD traits otherwise no ASD traits are observed. The other details are collected through an application.

A1 - Does your child look at you when you call his/her name? A2 - How easy is it for you to get eye contact with your child? A3 - Does your child point to indicate that s/he wants something? (e.g. a toy that is out of reach) A4 - Does your child point to share interest with you? (e.g. pointing at an interesting sight) A5 - Does your child pretend? (e.g. care for dolls, talk on a toy phone) A6 - Does your child follow where you’re looking? A7 - If you or someone else in the family is visibly upset, does your child show signs of wanting to comfort them? (e.g. stroking hair, hugging them) A8 - Would you describe your child’s first words as unusual? A9 - Does your child use simple gestures? (e.g. wave goodbye) A10 - Does your child stare at nothing with no apparent purpose?

The aim of this publication is to provide information about the key differences in healthcare between people with a learning disability and those without. It contains aggregated data on key health issues for people who are recorded by their GP as having a learning disability, and comparative data about a control group who are not recorded by their GP as having a learning disability. Six new indicators were introduced in the 2022-23 reporting year for patients with and without a recorded learning disability. These relate to: • Patients with an eating disorder • Patients with both an eating disorder and autism diagnosis • Patients with a diagnosis of autism who are currently treated with antidepressants More information on these changes can be found in the Data Quality section of this publication. Data has been collected from participating practices using EMIS and Cegedim Healthcare Systems GP systems.

Autism Spectrum Disorder (ASD) is a complex neurodevelopmental condition characterized by difficulties in social interaction, communication challenges, and repetitive behaviors. Symptoms can vary widely in type and severity, often appearing in early childhood and continuing throughout a person's life. Early screening and accurate diagnosis are essential for effective support and intervention.

To support research and machine learning applications in ASD detection across different age groups, this dataset collection includes three curated datasets:

Children: Thabtah, F. (2017). Autistic Spectrum Disorder Screening Data for Children [Dataset]. UCI Machine Learning Repository. https://doi.org/10.24432/C5659W.

→ This dataset contains screening results based on a standard autism assessment tool designed for children. Features include social behavior indicators, parental information, and screening test scores.

Adolescent : Tabtah, F. (2017). Autistic Spectrum Disorder Screening Data for Adolescent [Dataset]. UCI Machine Learning Repository. https://doi.org/10.24432/C5V89T.

→ Designed for adolescent subjects, this dataset includes questionnaire responses that assess behavioral traits aligned with autism diagnosis.

Adult: Thabtah, F. (2017). Autism Screening Adult [Dataset]. UCI Machine Learning Repository. https://doi.org/10.24432/C5F019.

→ Focused on adult participants, this dataset incorporates demographic features, screening scores, and psychological indicators to support adult ASD detection.

Disclaimer: We do not claim ownership of any of the datasets included here. All credit goes to the original author, Faisal Thabtah, and the UCI Machine Learning Repository, which hosts the data for public use.

This Kaggle dataset compilation is created solely for educational and research purposes, to allow easier access, comparison, and application of ASD screening data across different age groups. No modifications have been made to the original data other than format structuring for consistency.

If you use this dataset in your work, please ensure to cite the original sources as well.

Autism Spectrum Condition (ASC) is still very unknown. As its name depicts it covers a very broad range of conditions that makes it difficult to define and deal with. Important research is being undertaken in genetics to try to understand its origin, cause and typification but no major advances have been made yet.

In the meantime, ASC people need pragmatic solutions to help them in a number of aspects of their daily lives, such as social interaction. ICT has become an important source of intervention and therapeutic tools in the last 10 years. There is a complete lack of sharing of data from trials of ICT tools for ASC. This data could be useful to many researchers to compare results and to build research in different directions from that same data. Within the available ICT tools Embodied Interaction is increasingly showing its potential in ASC. Data from these tools is multimodal in nature and is hence complex to store and analyze.

In our project we investigated a technological system, a full-body interactive Mixed Reality (MR) experience, to understand how full-body interactive systems can help children with Autism improve in social initiation behaviors. The approach of our project was to compare results from our MR experience with a typical LEGO based social intervention, where both mediate a face-to-face play session between an ASC child and a non-ASC child.

The project created a database called ASCMEOR which is a reference database of multimodal data from sessions of ASC children and youngsters using ICT therapy and intervention tools. This is the first time that this type of data is collected from ASC children interacting with complex ICT systems in a database and shared with experts around the world.

As a result of a collaboration with the “Multidisciplinary Unit on Autism Spectrum Disorder” of the Hospital Sant Joan de Déu, the unit provided links to the end users (i.e. high-functioning ASC children) on a local basis in the city of Barcelona. The demography was defined as children and young teenagers (8-12 years old). Participants had been formally diagnosed with ASC as determined by the Autism Diagnostic Observation Schedule (ADOS) module 3, which is designed for young people with verbal fluency, with a minimum diagnosed severity of 4. Verbal fluency being essential to achieve the level of collaboration required to play the game without the help of a psychologist or parent. As a measure to prevent problems playing or comprehending the game, both the ASC and non-ASC children, had to have a minimum IQ of 70 according to the Wechsler Intelligence Scale for Children (WISC) and were screened for epilepsy. All procedures performed were in accordance with the 1964 Helsinki declaration and its later amendments or comparable ethical standards and ethical approval was obtained from the ethical committee of the hospital and Universitat Pompeu Fabra. Informed consent was obtained from the legal representatives of all participants included in the study.

The experimental procedure was run with 36 ASC/non-ASC dyads following a repeated-measure design with two conditions: Full-body interaction MR environment and the typical social intervention strategy based on LEGO bricks. The children with ASC played with their non-ASC partner for 15 minutes in the MR system, and with the same partner for 15 minutes in the LEGO setup. All children participated in both experimental conditions, and the order was randomized for each pair to counterbalance any learning effects. There was a 5 min break followed by a relaxation training between the 2 conditions. As a result of the experimental trials, the ASCMEOR dataset has been generated. Each experimental trial has a trial no associated with it e.g., the first trial has the trial no: “0001”. The data from each trial is organized in the following format:

(0) Experiment Timeline

(1) Video-coding of overt behaviors;

(2) System log files detailing system triggering of events;

(3) Questionnaires to the children and to the parents;

(4)Psychophysiological measures, i.e. electrocardiogram (ECG), electrodermal activity (EDA) and accelerometer (ACC)