Large Language Models in Colorectal Cancer Care and Clinical Decision Support: Systematic Review
Große Sprachmodelle in der kolorektalen Krebsversorgung und klinischen Entscheidungsunterstützung: systematische Übersicht
Journal of Medical Internet Research · 21.05.2026 · 28 · e89862-e89862
DOI: 10.2196/89862 ↗Auf einen Blick
Die Übersicht zeigt Anwendungen von LLMs in der CRC-Versorgung und eine mögliche Unterstützung von Diagnostik, Patientenaufklärung und Entscheidungsfindung. Die Evidenz ist insgesamt von niedriger Qualität.
Fragestellung
Welche Anwendungen, Leistungsfaktoren und klinischen Implikationen haben LLMs entlang des gesamten Versorgungspfads bei kolorektalem Krebs?
Methode
Systematische Übersicht nach PRISMA; 6 Datenbanken bis 1. April 2026; 37 eingeschlossene Originalstudien zu LLMs bei CRC-Aufgaben; narrative Synthese nach SWiM.
Ergebnisse
37 Studien (2023–2026) wurden eingeschlossen. GPT-Serien wurden am häufigsten untersucht. Das Verzerrungsrisiko war in 10/37 Studien gering, in 14/37 moderat, in 7/37 unklar und in 6/37 hoch oder schwerwiegend.
Einschränkungen
Heterogene Aufgaben, LLM-Typen, Prompts, Referenzstandards und Endpunkte; viele Studien ohne Verblindung, Störfaktorkontrolle oder prospektive multizentrische Validierung.
Schlussfolgerung der Autor:innen
Die Übersichtsarbeit zeigt das klinische Potenzial von LLMs bei CRC, die Ergebnisse sollen wegen der niedrigen Gesamtqualität der Evidenz aber vorsichtig interpretiert werden.
Kernaussagen
- LLMs zeigten Nutzen bei Datenerfassung, Patientenaufklärung, Diagnostik und klinischer Entscheidungshilfe.
- Prompt-Design beeinflusste die Leistung deutlich, von Zero-Shot bis Fine-Tuning.
- Domänenspezifische und multimodale Modelle waren in einigen Aufgaben allgemeinen Modellen überlegen.
Deutsche Zusammenfassung: KI-gestützt aus dem Original-Abstract erstellt; alle Zahlen wurden automatisch mit dem Original abgeglichen. Maßgeblich ist der Original-Abstract.
Kurz gefasst
Systematische Übersicht in der Zeitschrift Journal of Medical Internet Research, online erschienen am 21.05.2026. Verfasst von Jinglei Tian und 5 weiteren Autor:innen. Beteiligte Einrichtung: Zhejiang Chinese Medical University, Zhejiang Chinese Medical University, Hangzhou, China, Hangzhou, Zhejiang, China. Hauptthemen laut MEDLINE: Colorectal Neoplasms, Large Language Models, Decision Support Systems, Clinical. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 101 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar.
Themen: Onkologische Pflege
Abstract (Originalsprache)
Background
Colorectal cancer (CRC) is a leading cause of cancer morbidity and mortality worldwide. The complexity of guideline-concordant care and unstructured clinical data has driven demand for decision-support tools. Large language models (LLMs) show promise for processing clinical data and patient–provider communication, yet evidence is fragmented, and a CRC-specific synthesis across the full care continuum is lacking.
Objective
This systematic review evaluates the current applications, performance determinants, and clinical implications of LLMs across the continuum of CRC care.
Methods
Following PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses), we searched 6 databases (PubMed, Embase, Web of Science, Scopus, CINAHL, Cochrane) through April 1, 2026. Eligible studies were peer-reviewed original investigations of LLMs on CRC tasks with extractable outcomes; reviews, editorials, and abstracts were excluded. Two reviewers assessed quality with QUADAS-2 (Quality Assessment of Diagnostic Accuracy Studies-2), PROBAST (prediction model risk of bias assessment tool), and ROBINS-I (Risk of Bias in Nonrandomized Studies - of Interventions). Data on model types, applications, prompts, input/output formats, and outcomes were analyzed descriptively, with narrative synthesis per synthesis without meta-analysis (SWiM) guidelines.
Results
Of 8880 records, 37 studies met inclusion criteria (2023‐2026), mostly from China and the United States, with GPT series most frequently evaluated. Overall risk of bias was low in 10/37 studies (27.0%), moderate in 14/37 (37.8%), unclear in 7/37 (18.9%), and high or serious in 6/37 (16.2%). Problematic domains included outcome measurement, intervention classification, patient selection, and lack of blinded assessment. LLMs showed utility in automating data extraction from clinical texts, supporting patient education, aiding diagnosis, and assisting clinical decision-making, with emerging visual interpretation and multimodal capacities. Domain-specific and multimodal models showed advantages over general-purpose models in certain tasks. Performance was significantly influenced by prompt design, from zero-shot queries to fine-tuning. Despite efficiency and outcome benefits, challenges persist regarding methodological quality, data privacy, and generalizability.
Conclusions
This review provides an integrative framework synthesizing evidence across study designs and LLM categories in CRC care. Unlike prior reviews addressing gastroenterology broadly or limited to one design, it covers the full CRC continuum and, for the first time, comparatively evaluates general-purpose, domain-specific, and multimodal LLMs, clarifying how prompt engineering and heterogeneous metrics shape outcomes. Although findings support LLMs’ clinical potential, results must be interpreted cautiously, given low overall evidence quality. Most studies lacked safeguards against bias—blinded assessment, confounder adjustment, or prospective multicenter validation. Substantial heterogeneity across tasks, LLM types, prompts, reference standards, and outcomes means reported advantages cannot be generalized. Future work should prioritize real-world integration via prospective multicenter validation, robust privacy frameworks, and rigorous human oversight. Amid rising global CRC burden and health care disparities, this review informs clinical translation, equitable scaling, and policy on LLM deployment.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Zhejiang Chinese Medical University, Zhejiang Chinese Medical University, Hangzhou, China, Hangzhou, Zhejiang, China.
- Department of Gastroenterology, Hangzhou First People's Hospital, Hangzhou, China, Hangzhou, Zhejiang, China, 86 15267498545.
Zitieren
APA
Tian, J., Lou, Q., Wang, X., Xu, H., Mei, H., & Yu, Y. (2026). Large Language Models in Colorectal Cancer Care and Clinical Decision Support: Systematic Review. Journal of Medical Internet Research, 28, e89862-e89862. https://doi.org/10.2196/89862
Vancouver
Tian J, Lou Q, Wang X, Xu H, Mei H, Yu Y. Large Language Models in Colorectal Cancer Care and Clinical Decision Support: Systematic Review. Journal of Medical Internet Research. 2026;28:e89862-e89862. doi:10.2196/89862
BibTeX
@article{Tian2026,
author = {Tian, Jinglei and Lou, Qifeng and Wang, Xue and Xu, Hangying and Mei, Huiting and Yu, Yanli},
title = {Large Language Models in Colorectal Cancer Care and Clinical Decision Support: Systematic Review},
journal = {Journal of Medical Internet Research},
year = {2026},
volume = {28},
pages = {e89862--e89862},
doi = {10.2196/89862}
}
EUVIMED