ArticleNPJ digital medicine2025
Enhancing EHR-based pancreatic cancer prediction with LLM-derived embeddings.
Article in NPJ digital medicine, 2025. The graph could read no effect estimate from its abstract, so it casts no vote on the map. Cited by 13 papers.
What it found
Each row is one number read from the abstract, on the scale the paper reported it, with its interval. Left of the dashed line favours the treatment, right favours the comparator. Under each row is the sentence it came from. New to these charts? A ten-minute tutorial.
The abstract states no effect estimate the extractor could read, or names no intervention and outcome on the map, so this paper lights no cell and moves no belief. It is still indexed, cited and linked below.
The trial behind it
Trials whose registry record cites this paper, or whose number appears in the abstract. A trial that started after this paper was published is citing it as background, not reporting it.
Neither the registry nor the abstract names a trial number. If this is a trial report, that itself is worth knowing.
Who cites it
13 citing papers in PubMed.
- Large Language Models for Heterogeneous Data Mining in Liver Disease: Framework Development and Retrospective Validation Study.Journal of medical Internet research · 2026Article
- Toward scalable early cancer detection: evaluating EHR-based predictive models against traditional screening criteria.NPJ precision oncology · 2026Article
- Klf4-Tymp axis promotes inflammation-driven early tumorigenesis by enhancing kras mutation-induced acinar-to-ductal metaplasia through Pi3k/Akt and Mek/Erk pathways.Journal of experimental & clinical cancer research : CR · 2026Article
- Development and Validation of a Parsimonious Risk Stratification Model for Pancreatic Cancer.JAMA oncology · 2026Article
- Factors Associated with Stage at Diagnosis in Pancreatic Cancer: Implications for Precision Screening and Early Detection.Biomedicines · 2026Review
- Article
- Real-world evidence on data quality in precision oncology platforms: insights from the Molecular Twin Research Umbrella protocol.Frontiers in digital health · 2026Article
- Instability of LLM text embeddings for unsupervised dimension reduction of tabular data.Frontiers in bioinformatics · 2026Article
- Generative AI-augmented transcriptomic and microbiome analysis across inflammatory and fibrotic disease states in Crohn's disease.Frontiers in artificial intelligence · 2026Article
- Multiomics Analysis of Nucleotide Metabolism Highlights the Important Role of Adenylate Kinase 4 in Pancreatic Cancer.Human mutation · 2026Article
- PANCDetect: Early Detection of Pancreatic Cancer from Multimodal EHR data with LLM Embeddings.medRxiv : the preprint server for health sciences · 2025Article
- Enhancing cancer risk awareness and screening management through artificial intelligence: a narrative review.Frontiers in oncology · 2025Review
- Article
Corrections and comments
PubMed lists nothing against this paper. Absence here is not a guarantee, only a check that was made.
Authors and funding
6 authors.
Funding
Abstract
Pancreatic cancer (PC) is often diagnosed late, as early symptoms and effective screening tools are lacking, and genetic or familial factors explain only ~10% of cases. Leveraging longitudinal electronic health record (EHR) data may offer a promising avenue for early detection. We developed a predictive model using large language model (LLM)-derived embeddings of medical condition names to enhance learning from EHR data. Across two sites-Columbia University Medical Center and Cedars-Sinai Medical Center-LLM embeddings improved 6-12 month prediction AUROCs from 0.60 to 0.67 and 0.82 to 0.86, respectively. Excluding data from 0-3 months before diagnosis further improved AUROCs to 0.82 and 0.89. Our model achieved a higher positive predictive value (0.141) than using traditional risk factors (0.004), and identified many PC patients without these risk factors or known genetic variants. These findings suggest that the EHR-based model may serve as an independent approach for identifying high-risk individuals.
Identifiers
What OpenQuestion holds
Registered trials
Read under generation 80e0d062 · epoch 390. Bibliography from PubMed, PubMed Central and OpenAlex; grants from NIH RePORTER; trial links from ClinicalTrials.gov; estimates, votes and beliefs from the OpenQuestion graph.