Agentic education · Learning science

Actionable companion · Accessibility & inclusion

Learning with agency: The Current Research Landscape on the Machine Learning Application in Autism Spectrum Disorder: A Bibliometric Analysis From 1999 to 2023

AI-assisted editorial implementation guide, separate from the original research. Proposed actions are not claims or recommendations attributed to the source authors. No independent peer review of this guide is asserted.

Read original paperSearch paper agentCC BY 4.0

Evidence and context

Title and abstract screening; stage labels describe reported settings, not verified numerical ages. Design labels require full-text appraisal. Reported stage(s): Higher education, Children · stage unspecified. Verify the participant population and task before transferring the findings.

Original authors’ abstract, reproduced under the linked source license:

Background Language deficits, restricted and repetitive interests, and social difficulties are among the characteristics of autism spectrum disorder (ASD). Machine learning and neuroimaging have also been combined to examine ASD. Utilizing bibliometric analysis, this study examines the current state and hot topics in machine learning for ASD. Objective A research bibliometric analysis of the machine learning application in ASD trends, including research trends and the most popular topics, as well as proposed future directions for research. Methods From 1999 to 2023, the Web of Science Core Collection (WoSCC) was searched for publications relating to machine learning and ASD. Authors, articles, journals, institutions, and countries were characterized using Microsoft Excel 2021 and VOSviewer. Analysis of knowledge networks, collaborative maps, hotspots, and trends was conducted using VOSviewer and CiteSpace. Results A total of 1357 papers were identified between 1999 and 2023. There was a slow growth in publications until 2016; then, between 2017 and 2023, a sharp increase was recorded. Among the most important contributors to this field were the United States, China, India, and England. Among the top major research institutions with numerous publications were Stanford University, Harvard Medical School, the University of California, the University of Pennsylvania, and the Chinese Academy of Sciences. Wall, Dennis P. was the most productive and highest-cited author. Scientific Reports, Frontiers In Neuroscience Autism Research, and Frontiers In Psychiatry were the three productive journals. “autism spectrum disorder”, “machine learning”, “children”, “classification” and “deep learning” are the central topics in this period. Conclusion Cooperation and communication between countries/regions need to be enhanced in future research. A shift is taking place in the research hotspot from “Alzheimer's Disease”, “Mild Cognitive Impairment” and “cortex” to “artificial intelligence”, “deep learning”, “electroencephalography” and “pediatrics”. Crowdsourcing machine learning applications and electroencephalography for ASD diagnosis should be the future development direction. Future research about these hot topics would promote understanding in this field.

What kind of evidence is this?

Supporting AI learning science · Bibliometric / mapping study

Stage: Higher education; Children · stage unspecified. Screening labels describe reported context and study-design language. They are not a risk-of-bias rating or proof of effectiveness for an age band.

Limitations and uncertainty · source passage

In this study, several limitations were identified. At first, because of the data format required for VOSviewer and CiteSpace, the manuscripts about machine learning application in ASD were searched from a single database (WOSCC), leading to selection bias. Data from other sources, such as PubMed, could retrieve the comprehensive literature with high quality in this field but should be merged to become compatible with VOSviewer and CiteSpace. As a result, we employed two bibliometric tools (CiteSpace and VOSviewer) to reduce selection bias and eliminate duplicate literature from multiple sources. In addition, this study only included articles in English, so there may be language bias. It would be beneficial to incorporate publications in other languages into future research in order to obtain comprehensive results.

Design the system before the pilot

Use this study to inform a learning mechanism or implementation question. It is not direct evidence that autonomous agents improve learning. Keep the proposed agent behavior separate from what the source actually tested.

  • Co-design accommodations with learners and specialists. Check access and error burden across groups without inferring subgroup effectiveness from small or unreported samples.

A 90-day district pilot

  1. Days 1–15 · Appraise. Have the curriculum lead and a teacher read the methods and limitations. Record the study design, sample, comparator, outcomes and evidence gaps. Define a local question that the study can help inform.
  2. Days 16–30 · Design. Choose one disciplinary task. Require a first attempt, a documented AI consultation, a critique of the output and an independent explanation. Align the comparison group and scoring rubric with the same objective. Name an accountable owner and set the baseline, success threshold and budget before implementation.
  3. Days 31–60 · Test. Start with a small voluntary cohort, preserve an accessible non-AI route and require teacher review. Use synthetic or de-identified examples; approve data handling and tool terms through district processes.
  4. Days 61–90 · Decide. Blind-score reasoning and accuracy on a new task without AI. Distinguish model examination scores, student perceptions and actual learner gains; only the last directly tests educational benefit. Compare with baseline, document uncertainty and stop or revise if learning worsens, access is unequal or critical errors persist.

The board decision brief

Report the learning problem, evidence quality, participating population, total cost including review time, measured benefit, errors, access differences and remaining uncertainties. Make a dated recommendation to stop, revise or expand. A positive perception survey alone does not establish learning improvement.

Attribution and reuse

Xinyu Li; Wei Huang; Rongrong Tan; Caijuan Xu; Xi Chen; Qian Zhang; Sixin Li; Ying Liu; Huiwen Qiu; Changlong Bi; Hui Cao. The Current Research Landscape on the Machine Learning Application in Autism Spectrum Disorder: A Bibliometric Analysis From 1999 to 2023. Current Neuropharmacology (2025-01-01). https://doi.org/10.2174/011570159x332833241222191422

Companion prepared 2026-10-30. Original authorship and DOI are preserved. The abstract is an attributed source extract; the implementation plan is new AI-assisted editorial material, offered under the same CC BY 4.0 license. This guide has not undergone independent peer review.