arXiv Open Access 2025

MedGellan: LLM-Generated Medical Guidance to Support Physicians

Debodeep Banerjee Burcu Sayin Stefano Teso Andrea Passerini
Lihat Sumber

Abstrak

Medical decision-making is a critical task, where errors can result in serious, potentially life-threatening consequences. While full automation remains challenging, hybrid frameworks that combine machine intelligence with human oversight offer a practical alternative. In this paper, we present MedGellan, a lightweight, annotation-free framework that uses a Large Language Model (LLM) to generate clinical guidance from raw medical records, which is then used by a physician to predict diagnoses. MedGellan uses a Bayesian-inspired prompting strategy that respects the temporal order of clinical data. Preliminary experiments show that the guidance generated by the LLM with MedGellan improves diagnostic performance, particularly in recall and $F_1$ score.

Topik & Kata Kunci

Penulis (4)

D

Debodeep Banerjee

B

Burcu Sayin

S

Stefano Teso

A

Andrea Passerini

Format Sitasi

Banerjee, D., Sayin, B., Teso, S., Passerini, A. (2025). MedGellan: LLM-Generated Medical Guidance to Support Physicians. https://arxiv.org/abs/2507.04431

Akses Cepat

Lihat di Sumber
Informasi Jurnal
Tahun Terbit
2025
Bahasa
en
Sumber Database
arXiv
Akses
Open Access ✓