We provide a dataset that includes visualizations of eye-tracking scanpaths with a particular focus Autism Spectrum Disorder (ASD). The key idea is to transform the dynamics of eye motion into visual patterns, and hence diagnosis-related tasks could be approached using image analysis techniques. The image dataset is publicly available to be used by other studies aiming to experiment the usability of eye-tracking within the ASD context. It is believed that the dataset can allow for the development of further interesting applications using Machine Learning or image processing techniques. For more info, please refer to the publication below and the project website.Original Publication:Carette, R., Elbattah, M., Dequen, G., Guérin, J, & Cilia, F. (2019, February). Learning to predict autism spectrum disorder based on the visual patterns of eye-tracking scanpaths. In Proceedings of the 12th International Conference on Health Informatics (HEALTHINF 2019).Project Website:https://www.researchgate.net/project/Predicting-Autism-Spectrum-Disorder-Using-Machine-Learning-and-Eye-Trackinghttps://mahmoud-elbattah.github.io/ML4Autism/

Dataset

This dataset was created by mhkoosheshi

Contents

Dataset

This dataset was created by Anu Duu

Released under MIT

Contents

Dataset

This dataset was created by Tathagat Banerjee

Released under Apache 2.0

Contents

Analysis of ‘Autism Screening on Adults’ provided by Analyst-2 (analyst-2.ai), based on source dataset retrieved from https://www.kaggle.com/andrewmvd/autism-screening-on-adults on 14 February 2022.

--- Dataset description provided by original source is as follows ---

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

--- Original source retains full ownership of the source dataset ---

Context

Autism Specturm Disorder (ASD) patient's Mutated human Gene Dataset.

Site: https://gene.sfari.org/database/human-gene/

Children with Autism Spectrum Condition (ASC) usually exhibit early signs of emotional dysregulation before the actual meltdown event also known as rumble moments. Prediction of rumble moments may help parents/teachers/caregivers in timely intervention and prevent the situation from escalating. This dataset consists of data points extracted from labelled video segments of children playing Continuous Performance Test (CPT) games using the Python MediaPipe library. This dataset will be useful in studying engagement and arousal in children with autism in learning environments.

Autism is not a disease—it’s a neurodevelopmental condition (Autism Spectrum Disorder, or ASD) that affects how people communicate, interact socially, and experience the world. It’s lifelong and not an illness to be "cured."

Key points:
- 🧠 Brain differences: Autistic brains process information uniquely.
- 🌈 Spectrum: Support needs vary widely (some need help daily; others live independently).
- 🎯 Traits: May include sensory sensitivities, focused interests, or social communication differences.

Autism is part of human diversity. Many autistic people have strengths like creativity, attention to detail, or deep knowledge in specific areas. Acceptance, understanding, and tailored support help them thrive. 🌟

Autism Spectrum Disorder (ASD) is a neurodevelopmental disorder leading to an inability to socially communicate and in extreme cases individuals are completely dependent on caregivers. ASD detection at early ages is crucial as early detection can reduce the effect on social impairment. Deep learning models have shown capability to detect ASD earlier compared to traditional detection methods used by clinics and experts. Ensemble models, renowned for their ability to enhance predictive performance by combining multiple models, have emerged as a powerful tool in machine learning. This study harnesses the strength of ensemble learning to address the critical challenge of ASD diagnosis. This study proposed a deep ensemble model leveraging the strengths of VGG16 and Xception net trained on Facial Images for ASD detection overcoming limitations in existing datasets through extensive preprocessing. Proposed model preprocessed the training dataset of facial images by converting side posed images into frontal face images, using Histogram Equalization (HE) to enhance colors, data augmentation techniques application, and using the Hue Saturation Value (HSV) color model. By integrating the feature extraction strengths of VGG16 and Xception with fully connected layers, our model has achieved a notable 97% accuracy on the Kaggle ASD Face Image Dataset. This approach supports early detection of ASD and aligns with Sustainable Development Goal 3, which focuses on improving health and well-being.

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

Autism Spectrum Disorder (ASD) is a neurodevelopmental disorder leading to an inability to socially communicate and in extreme cases individuals are completely dependent on caregivers. ASD detection at early ages is crucial as early detection can reduce the effect on social impairment. Deep learning models have shown capability to detect ASD earlier compared to traditional detection methods used by clinics and experts. Ensemble models, renowned for their ability to enhance predictive performance by combining multiple models, have emerged as a powerful tool in machine learning. This study harnesses the strength of ensemble learning to address the critical challenge of ASD diagnosis. This study proposed a deep ensemble model leveraging the strengths of VGG16 and Xception net trained on Facial Images for ASD detection overcoming limitations in existing datasets through extensive preprocessing. Proposed model preprocessed the training dataset of facial images by converting side posed images into frontal face images, using Histogram Equalization (HE) to enhance colors, data augmentation techniques application, and using the Hue Saturation Value (HSV) color model. By integrating the feature extraction strengths of VGG16 and Xception with fully connected layers, our model has achieved a notable 97% accuracy on the Kaggle ASD Face Image Dataset. This approach supports early detection of ASD and aligns with Sustainable Development Goal 3, which focuses on improving health and well-being.

This dataset contains factors involved in developing ASD in children. It consists of the following features:

A10 Autism Spectrum Quotient( columns A1-A10), Social Responsiveness Scale, Age Years, Qchat_10_Score, Speech Delay/Language Disorder, Learning disorder, Genetic Disorders,Depression, Global developmental delay/intellectual disability, Social/Behavioural Issues, Childhood Autism Rating Scale, Anxiety disorder, Sex, Ethnicity, Jaundice, Family mem with ASD along with various information

The data here consists of different quantities and factors which have characteristics of ASD in children. It is collected from AUTISM RESEARCH: UNIVERSITY OF ARKANSAS Computer Science Dept to analyze the disease conditions and predict them in beforehand

Description of few columns: The Autism Spectrum Quotient (AQ1 - AQ10) is a 10-item self-scoring questionnaire that helps indicate whether someone aged 16 or older with suspected autism should be referred for an autism assessment. The AQ-10 has a scoring range of 0–10, with a threshold score of 6. A score of 6 or higher may indicate autism or a significant number of autistic traits.

If you find this dataset useful for your research, please do upvote.

Autism Spectrum Disorder (ASD) is a neurodevelopmental disorder leading to an inability to socially communicate and in extreme cases individuals are completely dependent on caregivers. ASD detection at early ages is crucial as early detection can reduce the effect on social impairment. Deep learning models have shown capability to detect ASD earlier compared to traditional detection methods used by clinics and experts. Ensemble models, renowned for their ability to enhance predictive performance by combining multiple models, have emerged as a powerful tool in machine learning. This study harnesses the strength of ensemble learning to address the critical challenge of ASD diagnosis. This study proposed a deep ensemble model leveraging the strengths of VGG16 and Xception net trained on Facial Images for ASD detection overcoming limitations in existing datasets through extensive preprocessing. Proposed model preprocessed the training dataset of facial images by converting side posed images into frontal face images, using Histogram Equalization (HE) to enhance colors, data augmentation techniques application, and using the Hue Saturation Value (HSV) color model. By integrating the feature extraction strengths of VGG16 and Xception with fully connected layers, our model has achieved a notable 97% accuracy on the Kaggle ASD Face Image Dataset. This approach supports early detection of ASD and aligns with Sustainable Development Goal 3, which focuses on improving health and well-being.

Autism Spectrum Disorder (ASD) is a neurodevelopmental disorder leading to an inability to socially communicate and in extreme cases individuals are completely dependent on caregivers. ASD detection at early ages is crucial as early detection can reduce the effect on social impairment. Deep learning models have shown capability to detect ASD earlier compared to traditional detection methods used by clinics and experts. Ensemble models, renowned for their ability to enhance predictive performance by combining multiple models, have emerged as a powerful tool in machine learning. This study harnesses the strength of ensemble learning to address the critical challenge of ASD diagnosis. This study proposed a deep ensemble model leveraging the strengths of VGG16 and Xception net trained on Facial Images for ASD detection overcoming limitations in existing datasets through extensive preprocessing. Proposed model preprocessed the training dataset of facial images by converting side posed images into frontal face images, using Histogram Equalization (HE) to enhance colors, data augmentation techniques application, and using the Hue Saturation Value (HSV) color model. By integrating the feature extraction strengths of VGG16 and Xception with fully connected layers, our model has achieved a notable 97% accuracy on the Kaggle ASD Face Image Dataset. This approach supports early detection of ASD and aligns with Sustainable Development Goal 3, which focuses on improving health and well-being.

Autism Spectrum Disorder (ASD) is a severe neurodevelopmental disorder. To enhance the understanding of the gut microbiota structure in ASD children at different ages as well as the relationship between gut microbiota and fecal metabolites, we first used the 16S rRNA sequencing to evaluate the gut microbial population in a cohort of 143 children aged 2–13 years old. We found that the α-diversity of ASD group showed no significant change with age, while the TD group showed increased α-diversity with age, which indicates that the compositional development of the gut microbiota in ASD varies at different ages in ways that are not consistent with TD group. Recent studies have shown that chronic constipation is one of the most commonly obvious gastrointestinal (GI) symptoms along with ASD core symptoms. To further investigate the potential interaction effects between ASD and GI symptoms, the 30 C-ASD and their aged-matched TD were picked out to perform metagenomics analysis. We observed that C-ASD group displayed decreased diversity, depletion of species of Sutterella, Prevotella, and Bacteroides as well as dysregulation of associated metabolism activities, which may involve in the pathogenesis of C-ASD. Consistent with metagenomic analysis, liquid chromatography-mass spectrometry (LC/MS) revealed some of the differential metabolites between C-ASD and TD group were involved in the metabolic network of neurotransmitters including serotonin, dopamine, histidine, and GABA. Furthermore, we found these differences in metabolites were associated with altered abundance of specific bacteria. The study suggested possible future modalities for ASD intervention through targeting the specific bacteria associated with neurotransmitter metabolism.

restricted

Questions, answers, and metadata collected from 13,256 Empathizing-Systemizing Tests. The data was hosted on OpenPsychometrics.org a nonprofit effort to educate the public about psychology and to collect data for psychological research. Their notes on the data collected in the codebook.txt

From Wikipedia:

The empathizing–systemizing (E–S) theory is a theory on the psychological basis of autism and male–female neurological differences originally put forward by English clinical psychologist Simon Baron-Cohen. It classifies individuals based on abilities in empathic thinking (E) and systematic thinking (S). It measures skills using an Empathy Quotient (EQ) and Systemizing Quotient (SQ) and attempts to explain the social and communication symptoms in autism spectrum disorders as deficits and delays in empathy combined with intact or superior systemizing.

According to Baron-Cohen, the E–S theory has been tested using the Empathy Quotient (EQ) and Systemizing Quotient (SQ), developed by him and colleagues, and generates five different 'brain types' depending on the presence or absence of discrepancies between their scores on E or S. E–S profiles show that the profile E>S is more common in females than in males, and the profile S>E is more common in males than in females.[1] Baron-Cohen and associates say the E–S theory is a better predictor than gender of who chooses STEM subjects (Science, Technology, Engineering and Mathematics). The E–S theory has been extended into the extreme male brain (EMB) theory of autism and Asperger syndrome, which are associated in the E–S theory with below-average empathy and average or above-average systemizing.