Journal Article

DKFZ-2026-01701

http://join2-wiki.gsi.de/foswiki/pub/Main/Artwork/join2_logo100x88.png Large language models enable prognostic stratification of cancer patients using real-world clinical notes.

Kiermeyer, N.DKFZ* ; Lenfers, T. ; Dada, A. ; Friedrich, J. ; Khattab, S. ; Knop, E. ; Egger, J. ; Pauly, M. ; Jung, A. ; Montavon, G. ; Siveke, J.DKFZ* ; Wiesweg, M.DKFZ* ; Kasper, S.DKFZ* ; Neumann, U. P. ; Klauschen, F.DKFZ* ; Hartmann, S. ; Schuler, M.DKFZ* ; Keyl, P. ; Kleesiek, J. ; Keyl, J.

2026
PLoS San Francisco, CA

Abstract: In medical documentation, vast amounts of unstructured text are generated that are still underutilized in current prognostic models. We investigate the potential of self-hosted large language models (LLM) to extract clinically meaningful, patient-specific information from routine clinical notes for personalized risk stratification in cancer care. We collected real-world medical notes from 2,708 non-small cell lung cancer (NSCLC) patients and 814 colon cancer patients documented before treatment at a large comprehensive cancer center. LLMs extracted key prognostic indicators, including comorbidities, metastatic sites, and qualitative descriptors of patient condition, in a zero-shot manner without prior task-specific training. Integrating these LLM-derived features into machine learning models significantly improved the prediction of overall survival compared to TNM staging alone (C-Index: NSCLC, 0.72 vs 0.64; colon cancer, 0.70 vs 0.59), and surpassed models using text embeddings. Based on the LLM-informed risk scores, patients were stratified into four distinct risk groups, enabling reclassification of 61.4% of NSCLC and 68.3% of colon cancer patients. Analysis of model drivers revealed that LLM-derived factors, such as the physical condition, substantially modulated the prognostic impact of TNM stage. These findings highlight the potential of self-hosted LLM to derive prognostically relevant information from unstructured clinical documentation and support clinical decision-making.

Note: #DKTKZFB26# / #NCTZFB26#

---

Contributing Institute(s):

1. DKTK Koordinierungsstelle Essen/Düsseldorf (ED01)
2. DKTK ED Translationale Onkologie Solider Tumore (ED04)
3. Koordinierungsstelle NCT West (WT01)

Research Program(s):

1. 899 - ohne Topic (POF4-899) (POF4-899)

Appears in the scientific report 2026

---

Database coverage:
; ; ; Article Processing Charges ; Clarivate Analytics Master Journal List ; DOAJ Seal ; Emerging Sources Citation Index ; Fees ; PubMed Central ; SCOPUS ; Web of Science Core Collection

---