JMIR Publications

ABSTRACT

Background:

Pancreatic cancer is the 12th most common cancer worldwide with an overall survival rate of 4.9%. Early diagnosis of pancreatic cancer is essential for necessary treatment and prevention. Artifi-cial intelligence (AI) provides advanced models and algorithms for better diagnosis of pancreatic cancer.

Objective:

This study aims to explore AI models used for the prediction and early diagnosis of pancreatic cancers as reported in the literature.

Methods:

A scoping review was conducted and reported in line with the guidelines of the PRISMA extension for scoping reviews. PubMed, Google scholar, IEEExplore, ScienceDi-rect, BioRXiv, and MedRxiv were explored to identify relevant articles. Study selection and data extraction were independently conducted by two reviewers. Data extracted from the stud-ies included were synthesized narratively.

Results:

Out of the 1185 publications, 30 studies were included in the scoping review. The included articles reported the use of AI for six different purposes. Of these included articles, AI techniques were mostly employed for the diagnosis of pancreatic cancer (14/30, 46.7%). Radiological images (14/30, 46.7%) were the most frequently used data in the included articles. Most of the included articles used data sets with a size of < 1000 samples (11/30, 36.7%). Deep learning models were the most prominent branch of AI used for pancreatic cancer diagnosis in the studies, and the convolutional neural network was the most used algorithm (18/30, 60%). Six validation approaches were used in the included studies, out of which the most frequently used approaches were k-fold cross-validation (10/30, 33.3%) and external validation (10/30, 33.3%). A higher level of accuracy (99%) was found in studies that used support vector machine, decision trees, and k-mean clustering algorithms.

Conclusions:

This review presents an overview of studies based on artificial intelligence mod-els and algorithms used to predict and diagnose pancreatic cancer patients. AI is expected to play a vital role in advancing pancreatic cancer diagnosis and prediction. Further research is required to provide data that support clinical decisions in healthcare sectors.