BACKGROUND: At present, the world is in the background of severe aging population challenges. Mild cognitive impairment (MCI), an intermediate state between normal aging and dementia, is a syndrome of cognitive impairment. Early recognition and intervention of MCI have great value for delaying the decline of cognitive function and improving the quality of life in the elderly. Machine learning (ML) is the core sub-branch direction in the field of artificial intelligence. In recent years, evaluating the potential application of machine learning in medicine has been popular, including the field of mild cognitive impairment. However, there is currently no bibliometrics to evaluate the scientific advances in this field. OBJECTIVE: This study aims to visually analyze the current research trends regarding the application of machine learning in the field of MCI through bibliometry and visualization techniques. METHODS: Using the Web of Science Core Collection database (Wo SCC), relevant articles and reviews of the collection database 2015-2024. Subsequently, the collected papers were subjected to bibliometric analysis utilizing CiteSpace, VOSviewer, and the "bibliometric" package in R language. RESULTS: A total of 2056 papers related to machine learning in patients with MCI were retrieved from the Wo SCC database. The number of papers is increasing year by year. These papers are mainly from 9,577 organizations in 498 countries, most of which are from the United States and China. The journal with the largest number of publications is the FRONTIERS IN AGING NEUROSCIENCE. Folstein M is an authoritative author from the Johns Hopkins University School of Medicine. His paper "Mini-mental state: A practical method for grading the cognitive state of patients for the clinician" is the most cited article in this field. Literature and keyword analysis indicate that MCI prediction, automated monitoring of MCI, continuous evaluation and remote monitoring of cognitive function in individuals with MCI, and interdisciplinary data integration and personalized medicine are current research hotspots and development directions. CONCLUSION: This study is the first to use bibliometric methods to visualize and analyze the application field of machine learning in MCI, revealing research trends and frontiers in this field. This information will provide a useful reference for researchers focusing on machine learning applications in the field of MCI.