# Can AI Be Useful in the Early Detection of Pancreatic Cancer in Patients with New-Onset Diabetes?

## TL;DR

This paper explores whether AI can help detect pancreatic cancer early in patients who recently developed diabetes.

## Contribution

The paper reviews recent AI-based approaches for pancreatic cancer screening in new-onset diabetes patients.

## Key findings

- AI models show promise in identifying high-risk patients with new-onset diabetes.
- Current screening tools like ENDPAC have not been effective enough.
- More research is needed to address limitations of AI in this context.

## Abstract

Pancreatic cancer is one of the most lethal neoplasms. Despite considerable research conducted in recent decades, not much has been achieved to improve its survival rate. That may stem from the lack of effective screening strategies in increased pancreatic cancer risk groups. One population that may be appropriate for screening is new-onset diabetes (NOD) patients. Such a conclusion stems from the fact that pancreatic cancer can cause diabetes several months before diagnosis. The most widely used screening tool for this population, the ENDPAC (Enriching New-Onset Diabetes for Pancreatic Cancer) model, has not achieved satisfactory results in validation trials. This provoked the first attempts at using artificial intelligence (AI) to create larger, multi-parameter models that could better identify the at-risk population, which would be suitable for screening. The results shown by the authors of these trials seem promising. Nonetheless, the number of publications is limited, and the downfalls of using AI are not well highlighted. This narrative review presents a summary of previous publications, recent advancements and feasible solutions for effective screening of patients with NOD for pancreatic cancer.