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

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. 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. 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. 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. 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.