Fusion-Augmented Large Language Models: Boosting Diagnostic Trustworthiness via Model Consensus
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| 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 |