Lung cancer management is complex and requires a multi-disciplinary approach to provide comprehensive care. Interventional pulmonology (IP) is an evolving field that utilizes minimally invasive modalities for the initial diagnosis and staging of suspected lung cancers. Endobronchial ultrasound guided sampling of mediastinal lymph nodes for staging and detection of driver mutations is instrumental for prognosis and treatment of early and later stage lung cancers. Advances in navigational bronchoscopy allow for histological sampling of suspicious peripheral lesions with minimal complication rates, as well as assisting with fiducial marker placements for stereotactic radiation therapy. Furthermore, IP can also offer palliation for inoperable cancers and those with late stage diseases. As the trend towards early lung cancer detection with low dose computed tomography is developing, it is paramount for the pulmonary physician with expertise in lung nodule management, minimally invasive sampling and staging to integrate into the paradigm of multi-specialty care.
ObjectiveTo analyze publications of the application of artificial intelligence related methods in medicine.MethodsPubMed and EMbase databases were electronically searched. Pathfinder Networks (PFNETs) algorithm, co-word network analysis and visualization technology were applied to analyze the time trend, journal distribution, and co-word structure of high-frequency medical keywords in key journals.ResultsThe amount of literature published on the application of artificial intelligence related methods in the medical field had been increasing annually. Nowadays, the number of studies published in the United States was the largest, and that in China, it was the sixth (first in developing countries). The number of the first author from the United States or China were among the top two, which were significantly more than any other regions. In 2012, IEEE Trans Neural Netw Learn Syst in the computer field became one of the major contributing journals. In recent years, the methods and applications proposed in the medical field were closely related to natural language processing, neural networks, and support vector machines.ConclusionsAt present, the United States is in a leading position in terms of artificial intelligence in medicine, and China has also abundant research strength. The number of medical literature published in interdisciplinary journals is increasing gradually, showing that the research and application of artificial intelligence related methods in medicine have become a research hotspot in recent years.
In recent years, the research on artificial intelligence medical devices has risen markedly along with the expanding application scenarios, exhibiting prominent interdisciplinary characteristics. From 2000 to 2024, the variety of research in artificial intelligence medical devices has significantly increased, while the balance of disciplines has slightly declined, and Simpson's diversity index has continuously increased. Medicine and biology are the main research themes and supportive disciplines in this field. Knowledge from computer science, engineering technology, and mathematics is widely involved and shows an upward trend, while content from the humanities and social sciences is less involved in the research. Compared to the United States and the United Kingdom, China has relatively less biological and chemical knowledge content in the research of this field, but more content related to computer science, engineering technology and material science is involved. This study analyzes the current state and trends of interdisciplinary on artificial intelligence medical devices from the perspective of macro-categories of disciplines, aiming to provide references for research planning, talent training and interdisciplinary cooperation in the field.
