Bibliometric Examination of Artificial Intelligence Studies on Infants

Abstract

The infancy period is a critical stage in which neurobiological, motor, cognitive and socio-emotional development progresses most rapidly and sensitively. Therefore, artificial intelligence applications make an important contribution to the more sensitive monitoring of early developmental indicators related to infants. The aim of this study was to conduct a bibliometric analysis of studies on artificial intelligence on infants. The study is a descriptive study using bibliometric analysis. In the study, 1380 publications obtained from the Web of Science Core Collection database using the keywords ‘infant and artificial intelligence’ were analysed. R programme and Biblimotrix–Biblioshiny programme were used for data analysis. After the analysis, the findings are presented under four headings: main information, word cloud, trending topics and thematic map. Publications on the subject cover the period between 1983 and 2025, with an average publication age of 5.19 years. The annual growth rate of these publications is 9.18%. Published by a very large number of different authors (10,554), each of these works received an average of 12 citations. The most active country was found to be the USA, and the journal with the highest number of publications was ‘Artificial Intelligence in Medicıne’. ‘Machine learning’ was found to be the most frequently used and leading theme of the field. It was determined that the themes that shape the field the most are ‘pregnancy, preterm birth, covid-19’. It was determined that the specific themes specific to the field are ‘fuzzy logic, ECG’. It was determined that ‘segmentation, MRI, ensemble learning’ are among the emerging or disappearing themes of the field. The increase in publications between 1983 and 2025 is important in terms of showing the increasing interest in the subject. While machine learning constitutes the main themes of the field, concepts such as ‘pregnancy, preterm birth, covid-19’ have emerged as critical foci that increase the social and clinical impact of the field. While original themes such as ‘fuzzy logic’ and ‘ECG’ encourage specialisation in the field, new and changing topics such as ‘segmentation, MRI, ensemble learning’ provide insight into the directions of future research. All of these trends enable the more sensitive and holistic assessment of motor, cognitive and physiological developmental indicators specific to infancy through artificial intelligence methods.