Can Artificial Intelligence help with Autism?

AI-powered educational platforms create personalized learning experiences that match individual abilities.

In recent years, AI has transformed how we solve challenges, including those faced by individuals with autism spectrum disorder (ASD). Autism involves difficulties with social interaction, communication, and repetitive behaviors, and AI technologies are starting to address these issues.

Enhancing Communication

AI offers valuable tools to help individuals with autism communicate better. Speech-generating devices and social robots, powered by AI, assist non-verbal or minimally verbal individuals. Augmentative and Alternative Communication (AAC) technologies provide non-verbal options, making it easier for individuals to express their needs.

Personalised Assistive Technologies

AI enhances the personalization of assistive technologies for individuals with autism by analyzing complex data, such as behaviors and responses, to determine which tools are most suitable. These tools adapt in real-time, offering support based on user interactions. For example, if someone appears stressed—through fidgeting or changes in behavior—AI could one day adjust lighting, reduce noise, or suggest calming activities. While current systems can detect stress, fully autonomous responses remain a future potential. As these technologies evolve, they will continue to improve and adapt to changing needs.

Supporting Learning and Independence

AI-powered educational platforms create personalized learning experiences that match individual abilities. They help with language and cognitive development, allowing individuals with autism to learn at their own pace. By improving communication and decision-making, AI also promotes independence, helping individuals gain more control over daily life.

Early Detection and Diagnosis

AI technologies are advancing early detection and diagnosis of autism. While ASD is typically diagnosed around age 3, AI is increasingly used to predict diagnostic outcomes based on developmental evaluations before this age. For instance, Bussu et al. (2021) applied a supervised machine learning algorithm (support vector machine, or SVM) to predict an ASD diagnosis at age 3, using early assessments like the Mullen Scales of Early Learning (MSEL) and the Vineland Adaptable Behavior Scale (VABS). The study demonstrated high predictive accuracy by comparing AI predictions with clinical judgments from the Autism Diagnostic Observation Schedule (ADOS) and Autism Diagnostic Interview Revised (ADI-R). This research highlights how combining different assessment tools with AI can improve early detection, leading to earlier intervention and better outcomes.

Conclusion

AI has great potential to help people with autism. It can improve communication, personalize education, and assist with early diagnosis. However, there are challenges in using AI in research and clinical settings. For example, many studies use unbalanced data, and simplifying assessments might miss important details about autistic symptoms. This shows the need for more research. There are also ethical and cybersecurity concerns. If AI is trained on unrepresentative data, it could reinforce biases. Key issues like privacy, informed consent, and fairness must be addressed to make AI inclusive. Since data is sensitive, strong cybersecurity measures are crucial to protect privacy and prevent misuse.

In summary, while AI can benefit individuals with autism, solving these technical, ethical, and security issues is necessary to use it responsibly and effectively.

Written by: Hayley

References

Freepik. (n.d.). Technology human touch background. Modern remake of The Creation of Adam [Image]. Freepik. https://www.freepik.com/free-photo/technology-human-touch-background-modern-remake-creation-adam_17851045.htm

Adako, O., Adeusi, O., & Alaba, P. (2024). Integrating AI tools for enhanced autism education: a comprehensive review. International Journal of Developmental Disabilities, 1–13. https://doi.org/10.1080/20473869.2024.2392983

Bussu G, Jones EJH, Charman T, Johnson MH, Buitelaar JK BASIS Team. Prediction of autism at 3 years from behavioural and developmental measures in high-risk infants:a longitudinal cross-domain classifier analysis. J Autism Dev Disord. 2018;48:2418–2433. doi: 10.1007/s10803-018-3509-x

Iannone A, Giansanti D. Breaking Barriers-The Intersection of AI and Assistive Technology in Autism Care: A Narrative Review. J Pers Med. 2023 Dec 28;14(1):41. doi: 10.3390/jpm14010041. PMID: 38248742; PMCID: PMC10817661.

Shahamiri, S.R., Thabtah, F. Autism AI: a New Autism Screening System Based on Artificial Intelligence. Cogn Comput 12, 766–777 (2020). https://doi.org/10.1007/s12559-020-09743-3

Song DY, Kim SY, Bong G, Kim JM, Yoo HJ. The Use of Artificial Intelligence in Screening and Diagnosis of Autism Spectrum Disorder: A Literature Review. Soa Chongsonyon Chongsin Uihak. 2019 Oct 1;30(4):145-152. doi: 10.5765/jkacap.190027. PMID: 32595335; PMCID: PMC7298904.