Artificial Intelligence Empowering Oncology Precision Medicine: Current Status, Key Insights, and Future Perspectives

Jianwen Zeng¹Shiying Shen¹Wenhao Qi¹Sixie Li¹Xin Liu¹Shihua Cao^1*Guanmian Liang²Meizhen Ye³

• ¹Hangzhou Normal University, Hangzhou, China
• ²Department of Urology, Zhejiang Cancer Hospital, Hangzhou, Jiangsu Province, China
• ³Department of Oncology, Zhejiang Provincial People's Hospital, Hangzhou, Jiangsu Province, China

The rapid evolution of artificial intelligence (AI) in precision oncology has underscored the growing importance of evaluating its current development trends and research priorities. This study leverages bibliometric data mining to systematically assess AI's contributions to oncology precision medicine and to measure the scale of its research development.Objective: This study aims to comprehensively evaluate the current state, key topics, and emerging trends in global research on artificial intelligence in oncology precision medicine.We conducted a thorough analysis of the literature on the application of AI in oncology precision medicine, utilizing data from the Web of Science Core Collection. Our analysis spans various dimensions, including publication volume, authorship, institutional contributions, journals, and geographic distribution. Text mining techniques were also employed to quantify the relationships between oncology and algorithms, followed by a detailed examination of the data.To date, 709 papers have been published in this field, distributed across 332 journals, 64 countries, and 1,448 key research institutions, with contributions from 4,675 researchers. The most commonly used algorithms are neural networks, random forests, and support vector machines. The cancers most frequently studied include gastric, colorectal, breast, and lung cancers. Recent advancements have emphasized the integration of AI with radiomics, multi-omics, and other data modalities, as well as its application in biomarker screening and identification. However, challenges associated with the deployment of AI technologies in this domain remain a critical area for ongoing attention.Conclusions: This field is experiencing steady growth, with significant global interest from various countries, institutions, and researchers. However, the establishment of stable collaborative research networks is still in its nascent stages, and interdisciplinary collaboration requires further strengthening. The continuous advancement of algorithms, particularly the application of neural networks, random forests, and support vector machines in precision oncology, has shown promising results. Moving forward, the integration of AI with multimodal data analysis and its role in AI-assisted biomarker research are expected to become key areas of focus, advancing the field of precision oncology.