Fusion-Augmented Large Language Models: Boosting Diagnostic Trustworthiness via Model Consensus

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Siam, Md Kamrul, Faruk, Md Jobair Hossain, Cheng, Jerry Q., Gu, Huanying
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908600527486976
author Siam, Md Kamrul
Faruk, Md Jobair Hossain
Cheng, Jerry Q.
Gu, Huanying
author_facet Siam, Md Kamrul
Faruk, Md Jobair Hossain
Cheng, Jerry Q.
Gu, Huanying
contents This study presents a novel multi-model fusion framework leveraging two state-of-the-art large language models (LLMs), ChatGPT and Claude, to enhance the reliability of chest X-ray interpretation on the CheXpert dataset. From the full CheXpert corpus of 224,316 chest radiographs, we randomly selected 234 radiologist-annotated studies to evaluate unimodal performance using image-only prompts. In this setting, ChatGPT and Claude achieved diagnostic accuracies of 62.8% and 76.9%, respectively. A similarity-based consensus approach, using a 95% output similarity threshold, improved accuracy to 77.6%. To assess the impact of multimodal inputs, we then generated synthetic clinical notes following the MIMIC-CXR template and evaluated a separate subset of 50 randomly selected cases paired with both images and synthetic text. On this multimodal cohort, performance improved to 84% for ChatGPT and 76% for Claude, while consensus accuracy reached 91.3%. Across both experimental conditions, agreement-based fusion consistently outperformed individual models. These findings highlight the utility of integrating complementary modalities and using output-level consensus to improve the trustworthiness and clinical utility of AI-assisted radiological diagnosis, offering a practical path to reduce diagnostic errors with minimal computational overhead.
format Preprint
id arxiv_https___arxiv_org_abs_2510_16057
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Fusion-Augmented Large Language Models: Boosting Diagnostic Trustworthiness via Model Consensus
Siam, Md Kamrul
Faruk, Md Jobair Hossain
Cheng, Jerry Q.
Gu, Huanying
Computation and Language
Artificial Intelligence
This study presents a novel multi-model fusion framework leveraging two state-of-the-art large language models (LLMs), ChatGPT and Claude, to enhance the reliability of chest X-ray interpretation on the CheXpert dataset. From the full CheXpert corpus of 224,316 chest radiographs, we randomly selected 234 radiologist-annotated studies to evaluate unimodal performance using image-only prompts. In this setting, ChatGPT and Claude achieved diagnostic accuracies of 62.8% and 76.9%, respectively. A similarity-based consensus approach, using a 95% output similarity threshold, improved accuracy to 77.6%. To assess the impact of multimodal inputs, we then generated synthetic clinical notes following the MIMIC-CXR template and evaluated a separate subset of 50 randomly selected cases paired with both images and synthetic text. On this multimodal cohort, performance improved to 84% for ChatGPT and 76% for Claude, while consensus accuracy reached 91.3%. Across both experimental conditions, agreement-based fusion consistently outperformed individual models. These findings highlight the utility of integrating complementary modalities and using output-level consensus to improve the trustworthiness and clinical utility of AI-assisted radiological diagnosis, offering a practical path to reduce diagnostic errors with minimal computational overhead.
title Fusion-Augmented Large Language Models: Boosting Diagnostic Trustworthiness via Model Consensus
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2510.16057