PANCDetect: Early Detection of Pancreatic Cancer from Multimodal EHR data with LLM Embeddings.

ABSTRACT:

Background

Pancreatic cancer (PANC) is often diagnosed at late stages due to the absence of specific early symptoms, resulting in one of the highest cancer mortality rates. While imaging modalities such as MRI and CT offer high diagnostic accuracy, their population-wide application is however impractical due to the cost. Electronic health records (EHRs) provide a routine, easily accessible, longitudinal and scalable data source for risk prediction, particularly for diseases with no specific symptom such as PANC.

Method

We introduce PANCDetect, a multimodal framework that leverages large language model (LLM)-derived embeddings of diagnoses, procedures, medications, and laboratory tests, and integrates these data modalities through a Transformer-based architecture. We train th

SUBMITTER: Jin Z 

PROVIDER: S-EPMC12633566 | biostudies-literature | 2025 Nov

REPOSITORIES: biostudies-literature