This paper presents a scientometric and analytical examination of machine learning applications in human factors research using a Scopus indexed dataset of 1,708 publications from 2019 to 2025. Keyword cooccurrence analysis was conducted using VOSviewer with a minimum occurrence threshold of 10, resulting in a network of 75 keywords grouped into eight thematic clusters. The thematic structure indicates a dominant empirical stream focused on cognitive state assessment, especially mental workload and fatigue detection using physiological signals such as electroencephalography and deep learning methods. Complementary clusters emphasize human AI interaction, explainable AI, decision support, automation and human reliability, affective computing, ergonomics in Industry 4.0/5.0 contexts, and healthcare oriented clinical decision support and patient safety. Overlay analysis shows recent growth in generative AI, large language models, fairness, and human centered AI concepts in 2024-2025. An analytical synthesis identifies major gaps, including limited human-in-the-loop validation, weak cross domain generalizability, insufficient longitudinal evaluation of human AI collaboration, and emerging explainability work that remains under validated empirically. The results provide a structured map of the field and a focused research agenda for responsible, transparent, and effective human centered intelligent systems.

Lung cancer remains a major global health burden, and deep learning, especially convolutional neural networks, has become a widely used approach for CT-based detection and diagnostic support. This scientometric study maps how this research area has developed and how its main themes and collaborations are organized, using a workflow that combines bibliometrix (R) with VOSviewer. From a broader Scopus query result set, an exported core subset of 200 journal articles published between 2017 and 2025 was selected for in-depth bibliometric analysis, spanning 139 sources and including 1,659 cited references. The citation overview reports 7,167 total citations across 175 cited documents, corresponding to a corpus h-index of 42. Thematic mapping and keyword co-occurrence analyses show a stable CT-centric backbone that connects most studies, alongside faster-growing streams focused on model generalization and optimization, and smaller niche lines such as 3D CNN–driven lung nodule detection. Collaboration indicators point to moderate internationalization, with 43 multi-country publications (21.5%). Overall, the field is consolidating around CT-based deep learning pipelines, while a key gap remains in translation-ready evidence, multi-center external validation, robustness to protocol heterogeneity, and more consistent reporting practices to support reproducibility and clinical adoption.