A retrieval-augmented chatbot based on GPT-4 provides appropriate differential diagnosis in gastrointestinal radiology: a proof of concept study

Abstract Background We investigated the potential of an imaging-aware GPT-4-based chatbot in providing diagnoses based on imaging descriptions of abdominal pathologies. Methods Utilizing zero-shot learning via the LlamaIndex framework, GPT-4 was enhanced using the 96 documents from the Radiographics...

Ausführliche Beschreibung

Bibliografische Detailangaben

Hauptverfasser:	Stephan Rau, Alexander Rau, Johanna Nattenmüller, Anna Fink, Fabian Bamberg, Marco Reisert, Maximilian F. Russe
Format:	Artigo
Sprache:	Inglês
Veröffentlicht:	SpringerOpen 2024-05-01
Schriftenreihe:	European Radiology Experimental
Schlagworte:	Artificial intelligence Diagnosis (differential) Gastrointestinal diseases Knowledge acquisition (computer) Zero-shot learning
Online-Zugang:	https://doi.org/10.1186/s41747-024-00457-x
Tags:	Tag hinzufügen Keine Tags, Fügen Sie das erste Tag hinzu!