AUTHOR=Chen Xi , Fu Ruibiao , Shao Qian , Chen Yan , Ye Qinghuang , Li Sheng , He Xiongxiong , Zhu Jinhui 

TITLE=Application of artificial intelligence to pancreatic adenocarcinoma

JOURNAL=Frontiers in Oncology

VOLUME=Volume 12 - 2022

YEAR=2022

URL=https://www.frontiersin.org/journals/oncology/articles/10.3389/fonc.2022.960056

DOI=10.3389/fonc.2022.960056

ISSN=2234-943X

ABSTRACT=Background and objectives: Although substantial progress has been made in the comprehensive treatment of pancreatic cancer (PC), it remains one of the deadliest cancers worldwide. The development of artificial intelligence (AI) technology has allowed its clinical applications to expand remarkably in recent years. AI supports using different methods and algorithms to extract additional information from clinical data to aid in the treatment of PC. In this review, we will summarize the application of AI in various areas of PC diagnosis and treatment and discuss its limitations and possible future research directions.
Methods: We review the latest literature concerning the application of AI for PC. The articles are analyzed and categorized according to the medical task of their algorithm. Articles were screened with two search engines: Pubmed and Google Scholar.
Results: Overall, 64 papers published in 2001 and after were selected. Of the four medical tasks (risk assessment, diagnosis, treatment, and prognosis prediction), the diagnosis was the most frequently researched, and retrospective single-center studies were the most prevalent. We found that the different medical tasks and algorithms included in the reviewed studies caused the performance of their models to vary greatly. However, the approaches using deep learning methods yielded high performance in each of the subdivisions considered.
Conclusions: AI is a promising tool for helping PC patients and may contribute to improved patient outcomes. The integration of humans and AI in clinical medicine is still in its infancy and requires the in-depth cooperation of multidisciplinary personnel.